WO2020105151A1 - Facility maintenance inspection assisting system and order of inspection determination method - Google Patents

Facility maintenance inspection assisting system and order of inspection determination method

Info

Publication number
WO2020105151A1
WO2020105151A1 PCT/JP2018/043037 JP2018043037W WO2020105151A1 WO 2020105151 A1 WO2020105151 A1 WO 2020105151A1 JP 2018043037 W JP2018043037 W JP 2018043037W WO 2020105151 A1 WO2020105151 A1 WO 2020105151A1
Authority
WO
WIPO (PCT)
Prior art keywords
equipment
inspection
data
facility
maintenance
Prior art date
Application number
PCT/JP2018/043037
Other languages
French (fr)
Japanese (ja)
Inventor
朱音 山崎
洋平 河田
Original Assignee
株式会社日立製作所
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 株式会社日立製作所 filed Critical 株式会社日立製作所
Priority to PCT/JP2018/043037 priority Critical patent/WO2020105151A1/en
Publication of WO2020105151A1 publication Critical patent/WO2020105151A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management

Definitions

  • the present invention relates to a facility maintenance and inspection support system that optimizes the inspection sequence of wide-area facilities.
  • condition-based maintenance the equipment whose condition has deteriorated is inspected with priority.
  • State-based maintenance increases the probability that inspections, inspections, and repairs will be carried out before a failure, so that it is possible to prevent a decrease in reliability and to suppress repair costs and compensation costs due to a failure. Therefore, in recent years, it is necessary to shift from time-based maintenance to state-based maintenance.
  • Patent Document 1 Japanese Patent Laid-Open No. 2002-1422464 discloses a communication base for providing a patrol route for a maintenance service and a trouble response service for the plurality of communication base stations in which various devices are installed.
  • a center for determining the patrol route is provided, and each of the communication base stations detects an operating state of the installed device and an environmental condition of the communication base station.
  • Each communication based on communication means for receiving data, a maintenance database in which maintenance data regarding equipment of each communication base station is stored, and monitoring data received by the communication means and maintenance data read from the maintenance database
  • a communication base station characterized by comprising a circuit route determining means for calculating a service requirement for a base station and determining a circuit route of each communication base station according to the calculated service requirement.
  • a service patrol route providing system is described (see claim 1).
  • Patent Document 2 Japanese Patent Laid-Open No. 2009-3517 discloses a maintenance management support device for inspecting a deterioration state of equipment constituting a plant and formulating a maintenance plan, and a degree of coincidence with a plurality of evaluation items.
  • An input unit for receiving a calculation condition including a signal input unit for measuring and inputting a state signal in the plant, and estimating a deterioration state of a device based on the state signal, and performing maintenance by the deterioration state and the calculation condition.
  • a calculation unit that evaluates the plurality of evaluation items with respect to a countermeasure plan including work content and implementation time, and corrects and recalculates the countermeasure plan when the evaluation result is out of the range of the degree of coincidence, and the countermeasure.
  • An assisting device is described (see claim 1).
  • the inspection order In order to carry out state-based maintenance, it is necessary to understand the state of each facility and formulate an optimal inspection and maintenance / inspection order (hereinafter referred to as the inspection order).
  • the inspection order When a sensor for measuring the condition of the equipment is attached to the equipment, the sensor data can be analyzed to grasp the condition.
  • a large number of facilities are installed over a wide area for a long period of time such as a distribution facility represented by a pole transformer, it is costly to attach a sensor to each facility and monitor the state.
  • many facilities are installed outdoors and are directly affected by the environment and weather such as sunlight, wind and rain. Therefore, when the condition-based maintenance is applied to wide area equipment, in addition to equipment information such as the installation location and age of the equipment, information about the installation environment of the equipment is required.
  • Patent Document 1 since the condition of the device and the environmental condition are used, it is necessary to attach sensors such as temperature, humidity, and air volume to the device itself. When the technique described in Patent Document 1 is applied to power distribution equipment, a large number of sensors are required, and the installation cost and maintenance cost of the sensors are high, which is not realistic.
  • the number of open data observation stations is smaller than that of the equipment, and the observation data associated with the equipment may differ from the actual installation environment of the equipment depending on the distance between the equipment and the observation stations. Also, due to the circumstances of the observation station, observation may not be performed, and the average, maximum, and minimum observed values may differ from the actual values. Therefore, it is necessary to evaluate the reliability of the open data associated with the equipment.
  • the Japan Meteorological Agency publishes open data with quality information. From the above, it is necessary to evaluate the reliability of the observation data associated with each facility and formulate the inspection sequence in consideration of it.
  • Patent Document 2 proposes a method for determining a maintenance plan based on the current failure stop probability of equipment.
  • the condition of the equipment may suddenly deteriorate within a few years after the inspection is performed, but the failure probability after a few years is not taken into consideration in formulating the maintenance plan. Therefore, by predicting the future equipment state and formulating the inspection order in consideration of the present and future equipment states, the probability that the inspection and maintenance / inspection can be performed before the failure is improved.
  • the object of the present invention is to optimize the inspection order based on the estimated equipment status and the reliability of data when performing patrol, inspection, and maintenance of wide area equipment based on status standard maintenance.
  • a facility maintenance inspection support system that determines the inspection order in the maintenance work of the equipment, an input unit that accepts conditions for determining the inspection order, environmental data related to the environment in which the equipment is installed, and the inspection target
  • a data collection unit that collects equipment data including equipment information and inspection results, and current and future equipment soundness is calculated based on the collected data, and the uncertainty of the data used to calculate the equipment soundness Calculation unit that determines the inspection order based on the calculated facility soundness and the calculated uncertainty, and the result of the determined inspection order and the improvement status by the determined inspection order
  • an output unit for displaying that determines the inspection order in the maintenance work of the equipment, an input unit that accepts conditions for determining the inspection order, environmental data related to the environment in which the equipment is installed, and the inspection target
  • a data collection unit that collects equipment data including equipment information and inspection results, and current and future equipment soundness is calculated based on the collected data, and the uncertainty of the data used to calculate the equipment soundness Calculation unit that determines the inspection order based on the calculated facility sound
  • the inspection order can be optimized. Problems, configurations and effects other than those described above will be clarified by the following description of the embodiments.
  • Example 1 First, as a first embodiment of the present invention, an example in which the equipment maintenance and inspection support system of the present invention is applied to formulate an inspection sequence of power distribution equipment will be described.
  • 1A is a schematic configuration diagram of an equipment maintenance and inspection support system.
  • the facility maintenance and inspection support system includes an input device 101, a data collection device 102, a calculation device 103, and an output device 104.
  • FIG. 1A illustrates a configuration in which the input device 101, the data collection device 102, the calculation device 103, and the output device 104 are different computers, the input device 101, the data collection device 102, the calculation device 103, and the output device 104 are the same. It may be implemented in one computer.
  • the input device 101 is a computer used by the inspection planner, and the number of facilities that can be inspected in a year is input by the inspection planner in consideration of resources such as the number of inspection workers and the number of work vehicles. Further, the inspection planner inputs the inspection cycle set when the time-based maintenance is carried out to the input device 101.
  • the data collection device 102 is a computer that collects open data indicating the environment in which the equipment is installed and data of the equipment, and stores the data in the environment information database 105 and the equipment maintenance database 106, respectively.
  • the arithmetic unit 103 is a computer that uses the data stored in the data collecting unit 102 to execute the main processing of the facility maintenance and inspection support system of the present embodiment.
  • the output device 104 is a computer that outputs an inspection plan and is installed at an inspection work site. The inspection worker inspects the power distribution equipment according to the inspection plan output from the output device 104.
  • the environmental information database 105 stores data used for analysis as open data, and includes meteorological data 108, atmospheric data 109, and geographical data 110.
  • the meteorological data 108 is periodically acquired by the automatic data collection unit 107 from the past meteorological data download site of the Meteorological Agency. Since monthly values are used in this embodiment, the meteorological data may be acquired once a month when the data is updated.
  • the automatic data collection unit 107 acquires it from the environmental numerical database of the National Institute for Environmental Studies once a month.
  • the geographic data 110 is provided by the Geospatial Information Authority of Japan, and since it rarely changes and the update frequency is low, the data may be manually updated once every several years.
  • the equipment maintenance database 106 includes equipment data 111 and inspection history data 112.
  • the facility data 111 is automatically collected by the automatic data collection unit 107 from the facility ledger of the power distribution company at regular intervals.
  • the automatic data collection unit 107 automatically collects inspection result data in which the electric power distribution company stores the inspection results of the inspection workers.
  • FIG. 1B is a block diagram showing the physical configuration of a computer that constitutes the facility maintenance and inspection support system.
  • the computer constituting the system of this embodiment has a processor (CPU) 1, a memory 2, an auxiliary storage device 3 and a communication interface 4.
  • the calculator may have an input interface 5 and an output interface 8.
  • the processor 1 is a computing device that executes a program stored in the memory 2.
  • the various functions of the computer are realized by the processor 1 executing various programs. Note that a part of the processing performed by the processor 1 by executing the program may be executed by another computing device (for example, FPGA or ASIC).
  • the memory 2 includes a ROM which is a non-volatile storage element and a RAM which is a volatile storage device.
  • the ROM stores an immutable program (for example, BIOS) and the like.
  • the RAM is a high-speed and volatile storage device such as a DRAM (Dynamic Random Access Memory), and temporarily stores a program executed by the processor 1 and data used when the program is executed.
  • the auxiliary storage device 3 is a large-capacity and non-volatile storage device such as a magnetic storage device (HDD) or a flash memory (SSD). Further, the auxiliary storage device 3 stores data used by the processor 1 when executing the program and the program executed by the processor 1. That is, the program realizes each function of the computer by being read from the auxiliary storage device 3, loaded into the memory 2, and executed by the processor 1.
  • HDD magnetic storage device
  • SSD flash memory
  • the communication interface 4 is a network interface device that controls communication with other devices according to a predetermined protocol.
  • the input interface 5 is an interface to which input devices such as a keyboard 6, a mouse 7 and a touch panel (not shown) are connected and which receives an input from an operator.
  • the output interface 8 is an interface to which an output device such as a display device 9 and a printer (not shown) is connected and which outputs the execution result of the program in a format that can be visually recognized by the operator.
  • the program executed by the processor 1 is provided to the computer via a removable medium (CD-ROM, flash memory, etc.) or a network, and is stored in the non-volatile auxiliary storage device 3 which is a non-transitory storage medium. Therefore, the computer may have an interface for reading data from the removable medium.
  • the data collection device 102 and the arithmetic device 103 are a computer system configured on a single computer physically or on a plurality of logically or physically configured computers, and on a plurality of physical computer resources. It may operate on a virtual machine built in.
  • the meteorological data 108 of the environment information database 105 holds observation items, latitude and longitude of observation stations, observation station names, observation dates, observation values, quality information, and the like.
  • the quality information may be, for example, a ratio of the number of times the observed value is obtained in a predetermined period.
  • the Japan Meteorological Agency also publishes open data with quality information.
  • 3A and 3B are diagrams showing examples of data items collected and held by the data collection device 102.
  • the equipment health level (VHI: Virtual Health Index) of equipment varies depending on the number of years since installation and the environment in which it is installed. Therefore, the equipment information and the information indicating the environment in which the equipment is installed are used to calculate the VHI.
  • open data such as meteorological data 108 published by the Japan Meteorological Agency, atmospheric data 109 published by the National Institute for Environmental Studies, and geographic data (national land numerical information) 110 published by the Geographical Survey Institute are converted into VHI. It is used to calculate.
  • the open data used in this embodiment can be obtained from the websites of the Meteorological Agency, National Institute for Environmental Studies, and Geographical Survey Institute.
  • FIG. 3A is a diagram showing some of the data items stored in the facility maintenance database 106
  • FIG. 3B is a diagram showing some of the data items stored in the environment information database 105.
  • the items for which monthly values can be acquired as the meteorological data 108 are measured values such as temperature, precipitation, sunshine / solar radiation, snow / snowfall, wind, humidity / pressure, cloud amount / weather, and the like. For each item, it is possible to obtain statistically processed numerical values. For example, as the statistically processed temperature, the maximum temperature, the minimum temperature, the average temperature of the month, the number of days satisfying a certain condition of the month, and the like can be acquired.
  • the observation items that can be acquired as the atmospheric data 109 are measured values of SO2, NO, NO2, NOX, CO, OX, NMHC, CH4, THC, SPM, SP, PM2.5, etc.
  • the actual values can be downloaded as monthly values. Atmospheric data observation items can also be downloaded as a result of statistically processing the actual values.
  • the geographic data 110 elevation, slope, land use, main road, coastline, lake, river data, etc. are used from the national numerical information of the Geographical Survey Institute.
  • the format of national numerical information varies depending on the data.
  • the altitude and the gradient are mesh data, and each mesh has an average altitude, a maximum altitude, a minimum altitude, an average inclination angle, a maximum inclination angle, a minimum inclination angle, a maximum inclination direction, and a minimum inclination direction.
  • the area of use division such as rice fields, other agricultural land, forests, wastelands, building land, roads, railways, other land, rivers and lakes, beaches, seawater areas, golf courses, etc.
  • the coastline and river data can be acquired in the shapefile format.
  • the arithmetic device 103 includes a data processing unit 113, a VHI calculation model creation unit 114, a VHI calculation unit 115, a storage unit 116, and an inspection order determination unit 117.
  • the data processing unit 113 associates and cleanses the data collected by the data collection device 102.
  • VHI can be accurately calculated by excluding abnormal values and data collected only for a short period of time in the cleansing process.
  • the VHI calculator 115 calculates VHI from the processed data.
  • VHI is a numerical index that indicates the soundness of the equipment to be maintained. The higher the value, the better the sound, and the lower the value, the worse the deterioration.
  • the VHI shows the highest value at the time of manufacture, and may be normalized by setting the value at the time of manufacture to 1 and the value at the time of failure to 0.
  • VHI is a value calculated for each facility. For example, since a power pole, a switch, and a transformer have different materials and deterioration mechanisms, different VHI calculation models are created and VHI is calculated.
  • the storage unit 116 stores the processed data and the calculated VHI.
  • the inspection order determination unit 117 optimizes the inspection order based on the calculated VHI and the reliability of the data used for the VHI calculation. The optimized inspection sequence and the effect of the optimization are displayed on the screen of the output device 104.
  • FIG. 4 is a flowchart of the inspection order determination processing executed by the data processing unit 113, the VHI calculation unit 115, and the inspection order determination unit 117 when the arithmetic device 103 calculates the current VHI.
  • the data processing unit 113 converts the data stored in the environment information database 105 and the equipment maintenance database 106 into data suitable for analysis, and executes a data processing process for associating (401).
  • Two types of data conversion are implemented.
  • the first is the conversion of equipment data.
  • the date-related data is converted into the number of days elapsed up to the present.
  • the construction date described in the equipment data is converted into the number of elapsed days up to the present.
  • the second is the processing of open data. In the processing of open data, first, open data is converted into an analyzable format and associated with each facility.
  • the amount of precipitation and the amount of snowfall are significant to the monthly added value obtained by accumulating the daily observed values, and the temperature and wind speed are significant to the monthly average value, maximum value, minimum value, etc. of the daily observed values.
  • the equipment data, the inspection history data, and the open data are associated with the equipment ID as a key item.
  • the open data of the observation point closest to the facility data is associated. The above processing / calculation results are held in the storage unit 116 of the arithmetic device 103.
  • the VHI calculation step 402 is executed by the VHI calculation model creation unit 114 and the VHI calculation unit 115.
  • the VHI calculation model creation unit 114 creates a VHI calculation model in advance using past data.
  • the data items used when creating the VHI calculation model and the model creating method will be described.
  • the characteristic amount (explanatory variable) at the time of creating the VHI calculation model the same items as the data created at step 401 are used, and the inspection history data is used as the objective variable.
  • the feature amount is weather data, atmospheric data, geographical data, facility data, etc. before the model was created. Wide-area equipment installed over a wide area is not equipped with a sensor that individually measures the equipment status.
  • the inspection history data set as the objective variable is "OK", "NG” even if the equipment status is evaluated numerically. You may evaluate by the two values of ".
  • the equipment status is recorded numerically, the current equipment status can be predicted numerically by setting the inspection result as the objective variable when the model was created.
  • the method of indicating the equipment status as a numerical value is adopted by using as.
  • the distance from the boundary surface to the “OK” side is good, the condition of the equipment is good, and if it is far from the “NG” side, the condition of the equipment is bad.
  • the distance from the boundary surface on the “NG” side is given a negative value to set it as VHI, and the higher the VHI value, the higher the soundness, and the smaller the VHI value, the lower the soundness, indicating that the condition requires immediate inspection and repair. ..
  • the VHI calculation method that evaluates the state of equipment by two values can adopt methods other than those described above.
  • the importance of each feature amount used for predicting the target variable (magnitude of contribution to the target variable) can be acquired at the time of creating the VHI calculation model by a method such as SVM. It is possible to know the feature amount that has a large influence on the objective variable by the importance of the feature amount.
  • the inspection result is evaluated in multiple stages such as five stages, the VHI can be calculated using the estimated certainty of each stage. Even in the case of evaluation in multiple stages, it is difficult to determine the order in which the equipment judged in each stage should be inspected and inspected.
  • the data stored in the environment information database 105 and the past data stored in the facility maintenance database 106 are used as inputs in the same manner as in the two-level “OK” “NG” evaluation.
  • the VHI is calculated using the certainty assigned to each deterioration stage evaluation calculated by the VHI calculation model.
  • FIG. 5 is a diagram showing an example of a deterioration stage evaluation table indicating a numerical value of the probability assigned to each deterioration stage evaluation when the inspection result is evaluated in a plurality of stages.
  • VHI is calculated by deterioration stage evaluation and a weighted average of its certainty.
  • the VHI calculation formula is shown below.
  • the probability estimated to be the deterioration evaluation stage n is pn.
  • the VHI calculation method for evaluating the state of the equipment in multiple stages is not limited to this.
  • the VHI calculation unit 115 of the arithmetic unit 103 executes the VHI calculation process of step 402.
  • the data created by the data processing of step 401 is input to the model calculated by the VHI calculation model creation unit 114, and the current VHI is calculated as a numerical index.
  • the degree of importance of the feature amount is output and stored in the storage unit 116 of the arithmetic device 103.
  • FIG. 11 shows an example of a table showing the degree of importance held. The importance of the feature amount is used in the inspection order optimization process in step 403. Details of each item will be described later.
  • the VHI of each facility is calculated as the execution result of the VHI calculation processing in step 402.
  • the VHI of each equipment is held in the storage unit 116 of the arithmetic device 103 as the VHI output data shown in FIG. 6, and is output (for example, displayed as a list) from the output device 104.
  • the inspection order optimization processing of step 403 the optimum inspection inspection order of the equipment is determined based on the VHI calculated by the VHI calculation processing of step 402.
  • FIG. 7 is a flowchart of a detailed procedure of the inspection order optimization process of step 403 of FIG.
  • the equipment is rearranged in order from the one having the lowest VHI output as a result of the VHI calculation processing in step 401 to create an equipment inspection order list.
  • step 702 the uncertainty of the data associated with each facility is calculated from the importance of each feature amount used when creating the model and the quality information of the data. Details of the process of step 702 will be described later.
  • the equipment inspection order list rearranged in step 701 is divided into segments (for example, divided into a predetermined number of segments from the top), and the degree of uncertainty within the segment is calculated.
  • As a method of dividing the segments there are a method of dividing the value of VHI by a certain numerical value and a method of dividing by the number of facilities that can be inspected in a predetermined period such as one year.
  • the method of dividing the segment is set by the administrator using the keyboard or mouse of the input device 101. Since the number of workers and inspection costs are limited when conducting inspections and inspections of equipment, the number of equipment that can be inspected in one year is limited. Therefore, scheduled inspection years are set in order from the top of the equipment inspection order list.
  • step 704 the feature amount converted into future data is input to the model created in step 402 of FIG. 4 to calculate the future VHI.
  • step 705 the difference between the VHI for the scheduled inspection date and the current VHI is calculated, and the equipment whose equipment condition significantly deteriorates by the scheduled inspection date is extracted, and the inspection is completed before the equipment deterioration occurs. Reorder the inspection order list as you would. Details of the future VHI calculation process will be described later.
  • Confidence level is calculated from the distance between the equipment and the data observation station and the quality information of the open data used for the features when calculating VHI.
  • the data quality information is a value indicating the reliability of the data itself, and in this embodiment, the accuracy of open data (quality information) and the update frequency of the inspection result (degradation evaluation stage n) input as an objective variable. To use.
  • FIG. 8 is a flowchart of the detailed procedure of the uncertainty calculation processing in step 702.
  • the distance to the observation station associated with the equipment is calculated.
  • the distance between the equipment and the observation station is the location information of the equipment stored in the equipment data 111 of the equipment maintenance database 106, and the location information of the observation station stored in each data 108, 109, 110 of the environment information database 105. And is stored in the storage unit 116 of the arithmetic device 103.
  • the observation station closest to the equipment 001 shown in FIG. 9 is the observation station 1.
  • the distance between the equipment 001 and the observation station 1 is d 11 .
  • not all data items used for analysis are observed by one observation station.
  • the observation station 3 and the equipment 001 having the shortest distance among the observation stations having the precipitation amount are also observed.
  • Must be associated In this way, data of a plurality of observation stations may be associated with one piece of equipment.
  • the distance to each observation station associated with the equipment is stored in the storage unit 116. In this way, one piece of equipment is associated with one or a plurality of observation stations, and the table illustrated in FIG. 12 is created by the processing of step 801 in FIG.
  • the uncertainty is calculated using the distance between the facility and the observation station calculated in step 801.
  • the degree of uncertainty R d_1 is calculated by a weighted average using the importance of the feature quantity associated with the distance between the equipment and the observation station.
  • FIG. 11 is a diagram showing an example of a table in which feature amounts used in the uncertainty calculation process of step 802 of FIG. 8, importance of each feature amount, and data acquisition sources are associated.
  • FIG. 12 shows a table recording the observation station, the equipment-observation station distance, and the quality information, which are the feature quantities (observation values) associated with the equipment input to the uncertainty calculation processing in step 802. It is a figure. These tables are stored in the storage unit 116.
  • 1 is recorded when the characteristic amount is recorded in the environment information database 105
  • 2 is recorded when the characteristic amount is recorded in the facility maintenance database 106.
  • the degree of uncertainty can be calculated using either the data collected by the observation station stored in the environment information database 105 or the data stored in the facility maintenance database 106.
  • the degree of uncertainty is calculated using the data stored in the environment information database 105 (the data quality of each observation item and the number of observation days)
  • the non-confidence R Q_1 using quality information of the data used to VHI calculation facility 001
  • the uncertainty level R q — 1 is calculated by the weighted average.
  • the non-confidence R Q_1 based on non confidence R d_1 and quality information based on the distance to calculate the non-confidence R1 equipment 001 by the following equation.
  • the weights w distance and w quality used in the calculation may be set to appropriate values according to the policy of the electric power company.
  • the calculated uncertainties are converted into deterioration stages with reference to the table of FIG. 5, and stored in the storage unit 116 in the inspection order list shown in FIG. Note that by adjusting the weights w distance and w quality , the uncertainty may be calculated using the quality information without using the distance.
  • the degree of uncertainty may be calculated using the equipment inspection interval. For example, if the inspection interval is long, the degree of uncertainty is increased, and if it is short (for example, 3 months), the degree of uncertainty is decreased. This is because the equipment with an inspection interval of 5 years is considered to have a large gap between the estimated equipment status and the actual equipment status with the passage of time after the inspection. This is because the degree of uncertainty increases.
  • the degree of uncertainty may be increased if the elapsed period from the previous inspection date recorded in the inspection information 112 (equipment maintenance database 106) is long, and may be decreased if the period is short.
  • quality information the data quality of each observation item, the number of observation days, the inspection interval, and the elapsed time since the previous inspection were illustrated, but other quality information of observation items that contribute to deterioration depending on the type of equipment is used. Of course, any one or more of these may be used.
  • FIG. 13 is a flowchart of the detailed procedure of the inspection order rearrangement process based on the uncertainty in step 703 of FIG.
  • step 1301 the inspection order list, which is the output result of step 701 in FIG. 7, is divided into a plurality of segments in order from the top.
  • a method of dividing into segments there are a method of dividing by VHI value and a method of dividing by a predetermined number, and the inspection planner selects a method and a numerical value suitable for the facility management policy and purpose.
  • the equipment inspection order list is rearranged within the segment divided at step 1301 based on the uncertainty level calculated at step 702 of FIG. 7.
  • equipment with low uncertainty is arranged in the order of higher inspection.
  • the equipment having a high degree of uncertainty is arranged in the order of higher inspection. The degree of uncertainty makes it possible to evaluate the data reliability of open data.
  • the equipment of the inspection order list shown in FIG. 14 is sorted based on the degree of uncertainty, and then stored in the storage unit 116.
  • FIG. 15 is a flowchart of detailed procedures of future VHI calculation processing in step 704 of FIG.
  • step 705 the inspection order list is rearranged based on the future VHI calculated in step 704.
  • the policy differs depending on the power distribution company, but in the case of time-based maintenance, where maintenance is performed on a time basis, all facilities are inspected once every few years.
  • the cycle set when time-based maintenance is introduced is M years.
  • the planner inputs the cycle set by the time base maintenance from the keyboard.
  • the data up to the current time is used to calculate the VHI at the current time, but in step 704, the future VHI is calculated, so that it is necessary to create data up to M years later.
  • step 1501 of FIG. 15 open data is created for each year from now to M years later. Although it is considered that the altitude and distance from the coastline do not change significantly after M years, the total value is calculated by adding M years worth of precipitation and sunshine. In addition, since it is difficult to obtain detailed weather forecasts up to M years later, multiple patterns are assumed and created based on long-term weather scenarios and past weather data. For example, if it is assumed that the average climate will continue, by adding the average values of precipitation and sunshine for the past several years to calculate the meteorological data for each year, until M years later The weather data suitable for the analysis of each year can be acquired.
  • step 1502 equipment data for each year up to M years after is created and updated.
  • step 1502 the number of years elapsed in each year from the installation of the equipment to M years after is calculated.
  • step 1503 using the VHI calculation model created by the VHI calculation model creation unit 114, the data created in steps 1501 and 1502 and the data that does not change in the year referenced from the environment information database 105 and the equipment maintenance database 106 are used. As an explanatory variable, the VHI of each year up to M years later is calculated. The calculated VHI for each year is stored in the storage unit 116.
  • step 1504 scheduled inspection years are set in order from the top of the inspection sequence list based on the number of facilities that can be inspected in a year and input by the input device 101.
  • FIG. 16 is a flowchart of a detailed procedure of the rearrangement process based on the scheduled inspection year VHI in step 705 of FIG.
  • the future VHI calculated in step 704 of FIG. 7 and the current VHI calculated in step 402 of FIG. 4 are used. Even if the current VHI does not indicate a dangerous value close to a failure, the VHI may decrease rapidly by the scheduled inspection year determined based on the current VHI. Therefore, the inspection order is changed for the equipment in which VHI is expected to be significantly deteriorated, and the inspection order is optimized.
  • the current VHI value and the future VHI value stored in the storage unit 116 are referred to, and the difference between the scheduled inspection year VHI and the current VHI is calculated for each facility. After the VHI difference is calculated, the screen shown in FIG. 17 is presented to the inspection plan creator.
  • FIG. 17 is a diagram showing an example of a screen for the inspection planner to confirm the change in VHI of the equipment scheduled to be inspected in a certain year and the feature amount affecting the change in VHI.
  • the screen example 1701 shown in FIG. 17 includes an average VHI temporal change display area 1702, a VHI difference display area 1703, and a feature amount display area 1704 that influences equipment state estimation.
  • the average VHI temporal change display area 1702 the average VHI of the equipment scheduled to be inspected after N years calculated in step 704 of FIG. 7 and step 1601 of FIG. 16 and the difference between the current VHI and the VHI after N years have passed.
  • a graph showing the change in the average VHI over time is displayed for the equipment where is above the threshold. According to the average VHI temporal change display area 1702, the improvement status of the average VHI can be confirmed.
  • VHI difference display area 1703 a facility ID, a current VHI, and a VHI value after N years are displayed in a list format for a facility in which the difference between the current VHI and the VHI after N years is larger than a threshold value.
  • feature amount display area 1704 feature amounts that have affected the deterioration of the equipment state are displayed in a list format. By checking the feature amount display area 1704, the inspection planner can instruct the inspection person about the target equipment, the points of interest during inspection, and the countermeasures against deterioration.
  • step 1602 of FIG. 16 the result of rearrangement based on the degree of uncertainty in step 703 of FIG. 7 is divided into a plurality of segments.
  • the segments may be divided by year of scheduled inspection, such as yearly, or may be divided by range of VHI values.
  • step 1603 of FIG. 16 the equipment having the VHI difference calculated in step 1601 of FIG. 16 larger than the threshold value t1 is rearranged to the higher rank in the segment.
  • step 1603 the data is rearranged within the segment, but when the difference in VHI is large, it is appropriate to move to another segment. Therefore, in step 1604, the VHI average value for each year up to M years later is calculated for each segment. calculate.
  • step 1605 the VHI for the scheduled inspection year and the average VHI for the scheduled inspection years of other segments are compared for the equipment sorted in the higher order in the segment in step 1603.
  • step 1605 If the condition of step 1605 is satisfied, the process proceeds to step 1606 and the segment to which the record belongs does not change. On the other hand, if the condition of step 1605 is not satisfied, the process proceeds to step 1607, and the record is moved to the segment having the closest average value.
  • step 1608 the scheduled inspection year is updated to the scheduled inspection year of the segment after movement.
  • step 1609 the equipment is rearranged in the segment after the movement in the order of VHI in the scheduled inspection year.
  • FIG. 18 is a diagram showing an example of a screen for the inspection plan creator to confirm the effect of the inspection order optimization as a result of executing the processing shown in FIG.
  • the screen example 1800 shown in FIG. 18 includes a graph 1801 on the left side of the screen and a table 1802 on the right side of the screen.
  • the planned inspection year is the horizontal axis
  • the VHI for each year up to M years calculated in step 704 of FIG. 7 is the vertical axis
  • the equipment not inspected by a certain year inspection Display the average VHI of unimplemented equipment.
  • the graph 1801 the case where the inspection is performed in order from the lowest VHI and the case where the inspection order is optimized according to the present invention are compared and displayed.
  • the inspection plan creator can confirm from the graph 1801 that deterioration of the average VHI can be suppressed even for the equipment in the latter half of the planned inspection year by the optimization by the equipment maintenance and inspection support system.
  • a table 1802 on the right side of the screen displays the planned inspection year and the equipment inspection order before and after the optimization. It can be confirmed from the table 1802 that the order of equipment IDs to be inspected is different before and after the inspection order is optimized.
  • the inspection plan creator can make an inspection plan in which inspection and inspection are performed in the order of the equipment IDs after the optimization.
  • the planner of the inspection plan may input the inspection order proposal optimized based on the equipment state into the system for optimizing the inspection order considering the equipment position.
  • the power distribution equipment is shown as an example of the wide area equipment inspection, but the scope of application of the system of the present invention is not limited to this, and communication and gas having a wide area equipment, inspection and maintenance of gas, water, etc. It is applicable to order optimization.
  • the equipment maintenance / inspection support system includes an input unit (input device 101) that receives a condition for determining the inspection order, and environmental data ( An environmental information database 105), a data collection unit (data collection device 102) that collects equipment data (equipment maintenance database 106) including information on the equipment to be inspected and inspection results, and the current and current data based on the collected data.
  • the future equipment soundness is calculated, the uncertainty level of the data used to calculate the equipment soundness degree is calculated, and the inspection order is determined based on the calculated equipment soundness degree and the calculated uncertainty level.
  • the estimated equipment state and data can be optimized based on reliability. Further, the inspection plan creator can receive the proposal of the inspection sequence optimized in consideration of the reliability of the data used when predicting the equipment state, and confirm the effect. Further, by optimizing the inspection sequence, it is possible to suppress the number of equipment failures that occur before the inspection.
  • the inspection order can be determined based on the latest information without knowing the update timing of the information. .
  • the calculation unit 103 associates the collected environment data 105 with the equipment data 106 and converts the data into an analysis data, and a model for calculating the equipment soundness from the processed analysis data.
  • a VHI calculation model creation unit 114 to be created a VHI calculation unit 115 that calculates equipment soundness from the analysis data using the created model, and an uncertainty level of data used to calculate the equipment soundness
  • an inspection order determination unit 117 that determines an inspection order based on the calculated equipment soundness and the calculated uncertainty level. Therefore, based on the estimated equipment state and the reliability of the data.
  • the inspection order can be optimized.
  • the VHI calculation model creation unit 114 calculates the degree of importance of the contribution of each data input as a feature amount to the model to the equipment soundness calculated using the created model. Therefore, it is possible to understand the data that has affected the deterioration of the equipment condition, and to examine the target equipment, the points of interest at the time of inspection, and the countermeasures against deterioration.
  • the inspection order determination unit 117 a first rearrangement processing 701 that rearranges the equipment having the calculated poor equipment soundness into a higher inspection order, and an uncertainty calculation processing 702 that calculates the uncertainty.
  • a second rearrangement process 703 for rearranging the inspection order of the facilities a future VHI calculation process 704 for calculating a future facility soundness, and the calculated future facility soundness based on the calculated uncertainty. Since the third rearrangement process 705 for rearranging the inspection order of the equipment is executed based on the above, the proper inspection order can be created.
  • the inspection order determination unit 117 calculates the uncertainty level based on the quality of each data input to the model and the calculated importance level in the uncertainty level calculation processing 702. The degree of uncertainty can be calculated considering the contribution, and an appropriate inspection order can be created.
  • the inspection order determination unit 117 calculates the uncertainty in the uncertainty calculation processing 702 based on the importance of the observation included in the environmental data
  • the inspection order determination unit 117 calculates the uncertainty of each observation included in the environmental data. The degree of uncertainty can be calculated considering the contribution, and an appropriate inspection order can be created.
  • the inspection order determination unit 117 in the uncertainty calculation process 702, the observation station calculated using the position information of the equipment included in the equipment data 106 and the position information of the observation station included in the environment data 105. Since the degree of uncertainty is calculated based on the distance between the equipment and the facility, the degree of uncertainty can be calculated in consideration of the deviation of the observed values due to the distance, and an appropriate inspection order can be created.
  • the inspection order determination unit 117 calculates the quality of the data from the inspection interval of the inspection result included in the equipment data 106 in the uncertainty calculation process 702, the degree of uncertainty in consideration of the length of the inspection interval. Can be calculated and an appropriate inspection sequence can be created.
  • the inspection order determination unit 117 rearranges the inspection order of the equipment in the divided segments based on the calculated uncertainties in the second rearrangement process 703, and therefore considers the uncertainties.
  • the proper inspection sequence can be created.
  • the inspection order determination unit 117 in the future VHI calculation processing 704, creates environmental data for each year from the present to the end of the predetermined maintenance cycle (1501), and from the present to the end of the maintenance cycle.
  • Facility data for each year is created (1502)
  • future facility soundness is calculated using the created environment data for each year and the created facility data for each year (1503)
  • Since the scheduled inspection year is set based on the future facility soundness (1504), the future facility soundness can be accurately calculated and an appropriate inspection sequence can be created.
  • the inspection order determination unit 117 sets the scheduled inspection year of the facility based on the number of facilities that can be inspected in one year in the third rearrangement process 705, and the calculated current facility for each facility.
  • the difference between the soundness and the calculated soundness of the facility for the planned inspection year is calculated (1601), the equipment arranged in a predetermined order is divided into segments (1602), and the difference in the soundness of the equipment is predetermined.
  • the equipment larger than the threshold value is rearranged to the higher rank in the segment (1603), the average of the equipment soundness of each segment is calculated (1604), and the average value of the equipment soundness of the scheduled inspection year of the segment to which the equipment belongs is It is judged whether or not the facility soundness is closest to the facility inspection year (1605), and if the VHI average value of the scheduled inspection year of the segment to which the facility belongs is not the closest to the VHI of the facility inspection scheduled year, the average value is determined.
  • the scheduled inspection year of the equipment is updated to the closest scheduled inspection year (1608), and the equipment is sorted in the segment in ascending order of the soundness of the equipment (1609). Therefore, it is appropriate to consider the future soundness of the equipment. You can create an inspection sequence.
  • the output unit 104 is a screen that displays a graph showing an average value of the equipment soundness for each inspection time of the equipment before and after the inspection order is determined, and a list of the inspection order after the inspection order is determined. Since data is output, the effect of optimizing the inspection sequence can be presented in an easy-to-understand manner.
  • the present invention is not limited to the above-described embodiments, but includes various modifications and equivalent configurations within the scope of the appended claims.
  • the above-described embodiments have been described in detail in order to explain the present invention in an easy-to-understand manner, and the present invention is not necessarily limited to those having all the configurations described.
  • part of the configuration of one embodiment may be replaced with the configuration of another embodiment.
  • the configuration of another embodiment may be added to the configuration of one embodiment.
  • a part of the configuration of each embodiment may be added / deleted / replaced with another configuration.
  • each of the above-mentioned configurations, functions, processing units, processing means, etc. may be realized by hardware, for example, by designing a part or all of them with an integrated circuit, and a processor realizes each function. It may be realized by software by interpreting and executing the program.
  • Information such as programs, tables, and files that realize each function can be stored in a memory, a hard disk, a storage device such as SSD (Solid State Drive), or a recording medium such as an IC card, SD card, or DVD.
  • SSD Solid State Drive
  • control lines and information lines are shown to be necessary for explanation, and not all the control lines and information lines necessary for implementation are shown. In reality, it can be considered that almost all configurations are connected to each other.

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Human Resources & Organizations (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Strategic Management (AREA)
  • Tourism & Hospitality (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

A facility maintenance inspection assisting system for determining the order of inspection in a facility maintenance task, comprising: an input unit for accepting a condition for determining the order; a data collection unit for collecting environment data relating to an environment in which the facility is installed and facility data that includes information pertaining to the facility to be inspected and inspection results; a computation unit for calculating the present and future degrees of facility soundness on the basis of the collected data, calculating the nonconfidence degree of the data used in calculating the degrees of facility soundness, and determining the order of inspection on the basis of the calculated degrees of facility soundness and the calculated nonconfidence degree; and an output unit for displaying the result of the determined order of inspection and the state of improvement due to the determined order of inspection.

Description

設備保守点検支援システム及び点検順序決定方法Equipment maintenance inspection support system and inspection order determination method
　本発明は、広域設備の点検順序を適正化する設備保守点検支援システムに関する。 The present invention relates to a facility maintenance and inspection support system that optimizes the inspection sequence of wide-area facilities.
　限られたリソース（点検作業員数、作業に使用する機材など）で広域に設置された設備を点検保守する場合、効率的かつ適切な時期に巡視や点検・保守を行うように点検順序を策定し、設備に故障や事故を発生させないことが重要である。設備点検順序策定の考え方として、主に時間基準保全と状態基準保全の２通りが知られている。時間基準保全では、設備状態によらず周期的に点検が行われる。時間基準保全では、点検や修理が必要な設備の点検順序が点検リストの最後尾に配置される場合がある。また、直ちに点検が必要のない状態の設備を点検することになり、件費がかかる。 When inspecting and maintaining equipment installed in a wide area with limited resources (number of inspection workers, equipment used for work, etc.), formulate an inspection order so that inspections and inspections can be carried out efficiently and at appropriate times. , It is important not to cause equipment failure or accident. There are two main known methods of formulating equipment inspection order: time-based maintenance and state-based maintenance. In time-based maintenance, inspections are carried out periodically, regardless of equipment conditions. In time-based maintenance, the inspection sequence of equipment that requires inspection or repair may be placed at the end of the inspection list. In addition, the facility will be inspected immediately without the need for inspection, which will incur costs.
　一方、状態基準保全では、設備状態が劣化している設備を優先的に点検する。状態基準保全によれば、故障前に巡視や点検・修理が実施される確率が高くなるため、信頼性の低下を防止でき、さらに故障による修理対応費や補償費の発生を抑制できる。そこで、近年、時間基準保全から状態基準保全への移行が必要とされている。 On the other hand, in the condition-based maintenance, the equipment whose condition has deteriorated is inspected with priority. State-based maintenance increases the probability that inspections, inspections, and repairs will be carried out before a failure, so that it is possible to prevent a decrease in reliability and to suppress repair costs and compensation costs due to a failure. Therefore, in recent years, it is necessary to shift from time-based maintenance to state-based maintenance.
　この技術分野の背景技術として、以下の先行技術がある。特許文献１（特開２００２－１４２２４４号公報）には、種々の機器が設置された複数の通信基地局を対象として、前記機器の保守サービスおよび不具合対応サービスのための巡回経路を提供する通信基地局のサービス巡回経路提供システムにおいて、前記巡回経路を決定するセンタが設けられ、前記各通信基地局は、設置された前記機器の動作状態を検出する動作状態検出手段および当該通信基地局の環境状態を検出する環境状態検出手段の少なくとも一方の検出手段と、この検出手段により検出された状態を監視データとして前記センタに送信する通信手段とを備え、前記センタは、前記各通信基地局から前記監視データを受信する通信手段と、前記各通信基地局の機器に関する保守データが格納された保守データベースと、前記通信手段により受信した監視データと前記保守データベースから読み出した保守データとに基づいて前記各通信基地局に対するサービス必要度を算出し、その算出したサービス必要度に応じて各通信基地局の巡回経路を決定する巡回経路決定手段とを備えて構成されていることを特徴とする通信基地局のサービス巡回経路提供システムが記載されている（請求項１参照）。 The following prior art is available as background technology in this technical field. Patent Document 1 (Japanese Patent Laid-Open No. 2002-142244) discloses a communication base for providing a patrol route for a maintenance service and a trouble response service for the plurality of communication base stations in which various devices are installed. In the service patrol route providing system for a station, a center for determining the patrol route is provided, and each of the communication base stations detects an operating state of the installed device and an environmental condition of the communication base station. And at least one of environmental condition detecting means for detecting the state, and a communication means for transmitting the state detected by the detecting means to the center as monitoring data, and the center performs the monitoring from each of the communication base stations. Each communication based on communication means for receiving data, a maintenance database in which maintenance data regarding equipment of each communication base station is stored, and monitoring data received by the communication means and maintenance data read from the maintenance database A communication base station characterized by comprising a circuit route determining means for calculating a service requirement for a base station and determining a circuit route of each communication base station according to the calculated service requirement. A service patrol route providing system is described (see claim 1).
　また、特許文献２（特開２００９－３５１７号公報）には、プラントを構成する機器の劣化状態を検査し、保守計画の策定を行う保守管理支援装置であって、複数の評価項目に対する一致度を含む計算条件を受け付ける入力部と、前記プラント内の状態信号を計測し入力する信号入力部と、前記状態信号に基づいて機器の劣化状態を推定し、該劣化状態と前記計算条件により、保守作業の内容および実施時期を含む対策案について前記複数の評価項目に対する評価を行い、評価結果が前記一致度の範囲外である場合は前記対策案を修正して再計算する計算部と、前記対策案についての計算結果を表示する出力部と、を備え、前記出力部に、前記対策案及び修正した対策案の各々に対し前記複数の評価項目の評価結果を表示することを特徴とする保守管理支援装置が記載されている（請求項１参照）。 Further, Patent Document 2 (Japanese Patent Laid-Open No. 2009-3517) discloses a maintenance management support device for inspecting a deterioration state of equipment constituting a plant and formulating a maintenance plan, and a degree of coincidence with a plurality of evaluation items. An input unit for receiving a calculation condition including a signal input unit for measuring and inputting a state signal in the plant, and estimating a deterioration state of a device based on the state signal, and performing maintenance by the deterioration state and the calculation condition. A calculation unit that evaluates the plurality of evaluation items with respect to a countermeasure plan including work content and implementation time, and corrects and recalculates the countermeasure plan when the evaluation result is out of the range of the degree of coincidence, and the countermeasure. An output unit for displaying a calculation result for the plan, and the output unit displays the evaluation results of the plurality of evaluation items for each of the countermeasure plan and the modified countermeasure plan. An assisting device is described (see claim 1).
特開２００２－１４２２４４号公報JP-A-2002-142244 特開２００９－３５１７号公報JP, 2009-3517, A
　状態基準保全の実施には各設備の状態を把握し、最適な巡視や保守・点検順序（以下、点検順序と称する）を策定する必要がある。設備の状態を測定するセンサが設備に取り付けられている場合には、センサデータを分析して状態を把握できる。しかし、柱上変圧器に代表される配電設備のように、多数の設備が広域に長期間わたって設置される場合には、各設備にセンサを取り付けて状態を監視するとコストが必要になる。また、多くの設備は屋外に設置されており日光や風雨など環境や天候による影響を直接受ける。従って、広域設備へ状態基準保全を適用する際には、設備の設置位置や年数などの設備情報に加えて設備の設置環境の情報が必要となる。特許文献１では、機器の状態及び環境状態を使用するため、機器自体に温度、湿度、風量などのセンサを取り付ける必要がある。特許文献１に記載された技術を配電設備に適用する場合には、多数のセンサが必要となり、センサの設置コストやメンテナンスコストがかかるため現実的ではない。 In order to carry out state-based maintenance, it is necessary to understand the state of each facility and formulate an optimal inspection and maintenance / inspection order (hereinafter referred to as the inspection order). When a sensor for measuring the condition of the equipment is attached to the equipment, the sensor data can be analyzed to grasp the condition. However, when a large number of facilities are installed over a wide area for a long period of time such as a distribution facility represented by a pole transformer, it is costly to attach a sensor to each facility and monitor the state. In addition, many facilities are installed outdoors and are directly affected by the environment and weather such as sunlight, wind and rain. Therefore, when the condition-based maintenance is applied to wide area equipment, in addition to equipment information such as the installation location and age of the equipment, information about the installation environment of the equipment is required. In Patent Document 1, since the condition of the device and the environmental condition are used, it is necessary to attach sensors such as temperature, humidity, and air volume to the device itself. When the technique described in Patent Document 1 is applied to power distribution equipment, a large number of sensors are required, and the installation cost and maintenance cost of the sensors are high, which is not realistic.
　そこで、一般に公開されているオープンデータを活用して設備の状態を把握することが考えられる。しかし、オープンデータの観測局は設備に比べて少なく、設備と観測局との距離によって、設備に関連付けられた観測データが実際の設備設置位置の環境と異なる可能性がある。また、観測局側の事情により、観測が行われない場合があり、観測値の平均値、最高値、最低値が実際とは異なる場合がある。そこで、設備に関連付けられたオープンデータの信頼性を評価する必要がある。例えば、日本の気象庁は、品質情報が付されたオープンデータを公開している。以上より、各設備に関連付けられた観測データの信頼性を評価し、それを考慮して点検順序の策定する必要がある。 Therefore, it is possible to use open data that is open to the public to understand the status of the equipment. However, the number of open data observation stations is smaller than that of the equipment, and the observation data associated with the equipment may differ from the actual installation environment of the equipment depending on the distance between the equipment and the observation stations. Also, due to the circumstances of the observation station, observation may not be performed, and the average, maximum, and minimum observed values may differ from the actual values. Therefore, it is necessary to evaluate the reliability of the open data associated with the equipment. For example, the Japan Meteorological Agency publishes open data with quality information. From the above, it is necessary to evaluate the reliability of the observation data associated with each facility and formulate the inspection sequence in consideration of it.
　また、多数の設備に対して点検作業員数は限られているため、点検を一度に行うことはできない。現在の設備状態順に点検を行う場合、点検予定日が数年後となることがある。特許文献２では、現在の設備の故障停止確率に基づいて保守計画を決定する方法を提案している。しかし、設置環境によっては、点検が実施される数年後までの間に設備の状態が急激に悪化することも考えられが、保守計画の策定において数年後の故障確率は考慮されていない。そこで、将来の設備状態を予測し、現在及び将来の設備状態を考慮して点検順序を策定することによって、故障前に巡視や保守・点検を実施できる確率が向上する。 Also, since the number of inspection workers for many facilities is limited, it is not possible to perform inspections at once. When conducting an inspection in the order of the current equipment condition, the scheduled inspection date may be several years later. Patent Document 2 proposes a method for determining a maintenance plan based on the current failure stop probability of equipment. However, depending on the installation environment, the condition of the equipment may suddenly deteriorate within a few years after the inspection is performed, but the failure probability after a few years is not taken into consideration in formulating the maintenance plan. Therefore, by predicting the future equipment state and formulating the inspection order in consideration of the present and future equipment states, the probability that the inspection and maintenance / inspection can be performed before the failure is improved.
　本発明の目的は、広域設備を状態基準保全に基づいて巡視や点検・保守する場合に、推定された設備状態及びデータの信頼性に基づいて点検順序を適正化することである。 The object of the present invention is to optimize the inspection order based on the estimated equipment status and the reliability of data when performing patrol, inspection, and maintenance of wide area equipment based on status standard maintenance.
　本願において開示される発明の代表的な一例を示せば以下の通りである。すなわち、設備の保守業務における点検順序を決定する設備保守点検支援システムであって、点検順序を決定するための条件を受け付ける入力部と、設備が設置されている環境に関する環境データと、点検対象の設備の情報及び点検結果を含む設備データを収集するデータ収集部と、前記収集されたデータに基づいて現在及び将来の設備健全度を算出し、前記設備健全度の算出に使用したデータの不確信度を算出し、前記算出された設備健全度及び前記算出された不確信度に基づいて点検順序を決定する演算部と、前記決定された点検順序の結果及び前記決定された点検順序による改善状況を表示する出力部とを備えることを特徴とする。 The following is a representative example of the invention disclosed in the present application. That is, a facility maintenance inspection support system that determines the inspection order in the maintenance work of the equipment, an input unit that accepts conditions for determining the inspection order, environmental data related to the environment in which the equipment is installed, and the inspection target A data collection unit that collects equipment data including equipment information and inspection results, and current and future equipment soundness is calculated based on the collected data, and the uncertainty of the data used to calculate the equipment soundness Calculation unit that determines the inspection order based on the calculated facility soundness and the calculated uncertainty, and the result of the determined inspection order and the improvement status by the determined inspection order And an output unit for displaying.
　本発明の一態様によれば、点検順序を適正化できる。前述した以外の課題、構成及び効果は、以下の実施例の説明によって明らかにされる。 According to one aspect of the present invention, the inspection order can be optimized. Problems, configurations and effects other than those described above will be clarified by the following description of the embodiments.
設備保守点検支援システムの概略構成図である。It is a schematic block diagram of an equipment maintenance inspection support system. 設備保守点検支援システムを構成する計算機の物理的な構成を示すブロック図である。It is a block diagram showing the physical composition of a computer which constitutes an equipment maintenance inspection support system. 環境情報データベースの気象データに保持されるデータ項目の例を示す図である。It is a figure which shows the example of the data item hold | maintained at the weather data of an environmental information database. 設備保守データベースに格納されるデータ項目の一部を示す図である。It is a figure which shows a part of data item stored in a facility maintenance database. 環境情報データベースに格納されるデータ項目の一部を示す図である。It is a figure which shows a part of data item stored in an environment information database. 点検順序決定処理のフローチャートである。It is a flow chart of inspection sequence determination processing. 劣化段階評価テーブルの例を示す図である。It is a figure which shows the example of a deterioration stage evaluation table. ＶＨＩ出力データの例を示す図である。It is a figure which shows the example of VHI output data. 点検順序適正化処理の詳細な手順のフローチャートである。It is a flow chart of a detailed procedure of inspection sequence optimization processing. 不確信度算出処理の詳細な手順のフローチャートである。It is a flowchart of a detailed procedure of an uncertainty calculation process. 設備と観測局の関係を示す図である。It is a figure which shows the relationship between equipment and an observation station. 環境情報データベースに格納される観測局毎の観測項目データの例を示す図である。It is a figure which shows the example of the observation item data for every observation station stored in an environmental information database. 特徴量、各特徴量の重要度、及びデータ取得元を関連付けたテーブルの例を示す図である。It is a figure which shows the example of the table which linked | related the characteristic amount, the importance degree of each characteristic amount, and the data acquisition source. 設備ＩＤに関連付けられた特徴量を記録するテーブルを示す図である。It is a figure which shows the table which records the feature-value linked | related with equipment ID. 不確信度に基づく点検順序並べ替え処理の詳細な手順のフローチャートである。It is a flow chart of a detailed procedure of inspection order rearrangement processing based on a degree of uncertainty. 不確信度が追加された点検順序リストの例を示す図である。It is a figure which shows the example of the inspection sequence list to which the uncertainty was added. 将来のＶＨＩ算出処理の詳細な手順のフローチャートである。It is a flow chart of a detailed procedure of future VHI calculation processing. 点検予定年ＶＨＩに基づく並べ替え処理の詳細な手順を示すフローチャートである。It is a flow chart which shows the detailed procedure of the rearrangement processing based on scheduled inspection year VHI. 点検予定設備のＶＨＩの変化とＶＨＩの変化に影響を与える特徴量を確認する画面例を示す図である。It is a figure which shows the example of a screen which confirms the change of VHI of a to-be-inspected facility, and the feature-value which influences the change of VHI. 点検順序適正化の効果を確認するための画面例を示す図である。It is a figure which shows the example of a screen for confirming the effect of the inspection order optimization.
　以下、実施例を図面を用いて説明する。 Hereinafter, an embodiment will be described with reference to the drawings.
　＜実施例１＞
　まず、本発明の実施例１として、本発明の設備保守点検支援システムを配電設備の点検順序策定に適用した例について説明する。 <Example 1>
First, as a first embodiment of the present invention, an example in which the equipment maintenance and inspection support system of the present invention is applied to formulate an inspection sequence of power distribution equipment will be described.
　図１Ａは、設備保守点検支援システムの概略構成図である。 1A is a schematic configuration diagram of an equipment maintenance and inspection support system.
　設備保守点検支援システムは、入力装置１０１、データ収集装置１０２、演算装置１０３及び出力装置１０４から構成される。図１Ａでは、入力装置１０１、データ収集装置１０２、演算装置１０３及び出力装置１０４が別の計算機である構成を図示したが、入力装置１０１、データ収集装置１０２、演算装置１０３及び出力装置１０４が一つの計算機に実装されてもよい。 The facility maintenance and inspection support system includes an input device 101, a data collection device 102, a calculation device 103, and an output device 104. Although FIG. 1A illustrates a configuration in which the input device 101, the data collection device 102, the calculation device 103, and the output device 104 are different computers, the input device 101, the data collection device 102, the calculation device 103, and the output device 104 are the same. It may be implemented in one computer.
　入力装置１０１は、点検計画立案者が使用する計算機であり、点検計画立案者が点検作業員数、作業車数などのリソースを考慮して策定した年間に点検可能な設備数が入力される。また、点検計画立案者は、時間基準保全を実施した際に設定された点検周期を入力装置１０１に入力する。データ収集装置１０２は、設備が設置されている環境を示すオープンデータ及び設備のデータを収集し、それぞれ環境情報データベース１０５及び設備保守データベース１０６にデータを格納する計算機である。演算装置１０３は、データ収集装置１０２に格納されたデータを用いて、本実施例の設備保守点検支援システムの主たる処理を実行する計算機である。出力装置１０４は、点検計画を出力する計算機であり、点検作業拠点に設置される。点検作業者は、出力装置１０４から出力される点検計画に従って配電設備を点検する。 The input device 101 is a computer used by the inspection planner, and the number of facilities that can be inspected in a year is input by the inspection planner in consideration of resources such as the number of inspection workers and the number of work vehicles. Further, the inspection planner inputs the inspection cycle set when the time-based maintenance is carried out to the input device 101. The data collection device 102 is a computer that collects open data indicating the environment in which the equipment is installed and data of the equipment, and stores the data in the environment information database 105 and the equipment maintenance database 106, respectively. The arithmetic unit 103 is a computer that uses the data stored in the data collecting unit 102 to execute the main processing of the facility maintenance and inspection support system of the present embodiment. The output device 104 is a computer that outputs an inspection plan and is installed at an inspection work site. The inspection worker inspects the power distribution equipment according to the inspection plan output from the output device 104.
　環境情報データベース１０５は、オープンデータとして分析に利用するデータを格納し、気象データ１０８、大気データ１０９及び地理データ１１０を含む。気象データ１０８は、気象庁の過去の気象データ・ダウンロードサイトから定期的に自動データ収集部１０７が取得する。本実施例では月別値を使用するため、気象データは一か月に一度データが更新されるタイミングで取得すればよい。同様に大気データ１０９も月別値を利用するため、一か月に一度、国立環境研究所の環境数値データベースから自動データ収集部１０７が取得する。地理データ１１０は、国土地理院が提供しており、変化が少なく更新頻度が低いため数年に一度、手作業でデータを更新すればよい。 The environmental information database 105 stores data used for analysis as open data, and includes meteorological data 108, atmospheric data 109, and geographical data 110. The meteorological data 108 is periodically acquired by the automatic data collection unit 107 from the past meteorological data download site of the Meteorological Agency. Since monthly values are used in this embodiment, the meteorological data may be acquired once a month when the data is updated. Similarly, since the atmospheric data 109 also uses monthly values, the automatic data collection unit 107 acquires it from the environmental numerical database of the National Institute for Environmental Studies once a month. The geographic data 110 is provided by the Geospatial Information Authority of Japan, and since it rarely changes and the update frequency is low, the data may be manually updated once every several years.
　設備保守データベース１０６は、設備データ１１１及び点検履歴データ１１２を含む。設備データ１１１は、配電事業者の設備台帳から定期的に自動データ収集部１０７により自動的に収集する。点検履歴データ１１２は、配電事業者が点検作業員の点検結果を格納する点検結果データを、自動データ収集部１０７で自動的に収集する。 The equipment maintenance database 106 includes equipment data 111 and inspection history data 112. The facility data 111 is automatically collected by the automatic data collection unit 107 from the facility ledger of the power distribution company at regular intervals. As the inspection history data 112, the automatic data collection unit 107 automatically collects inspection result data in which the electric power distribution company stores the inspection results of the inspection workers.
　図１Ｂは、設備保守点検支援システムを構成する計算機の物理的な構成を示すブロック図である。 FIG. 1B is a block diagram showing the physical configuration of a computer that constitutes the facility maintenance and inspection support system.
　本実施例のシステムを構成する計算機は、プロセッサ（ＣＰＵ）１、メモリ２、補助記憶装置３及び通信インターフェース４有する。計算機は、入力インターフェース５及び出力インターフェース８を有してもよい。 The computer constituting the system of this embodiment has a processor (CPU) 1, a memory 2, an auxiliary storage device 3 and a communication interface 4. The calculator may have an input interface 5 and an output interface 8.
　プロセッサ１は、メモリ２に格納されたプログラムを実行する演算デバイスである。プロセッサ１が、各種プログラムを実行することによって、計算機の各種機能が実現される。なお、プロセッサ１がプログラムを実行して行う処理の一部を、他の演算デバイス（例えば、ＦＰＧＡやＡＳＩＣ）で実行してもよい。 The processor 1 is a computing device that executes a program stored in the memory 2. The various functions of the computer are realized by the processor 1 executing various programs. Note that a part of the processing performed by the processor 1 by executing the program may be executed by another computing device (for example, FPGA or ASIC).
　メモリ２は、不揮発性の記憶素子であるＲＯＭ及び揮発性の記憶デバイスであるＲＡＭを含む。ＲＯＭは、不変のプログラム（例えば、ＢＩＯＳ）などを格納する。ＲＡＭは、ＤＲＡＭ（Dynamic Random Access Memory）のような高速かつ揮発性の記憶デバイスであり、プロセッサ１が実行するプログラム及びプログラムの実行時に使用されるデータを一時的に格納する。 The memory 2 includes a ROM which is a non-volatile storage element and a RAM which is a volatile storage device. The ROM stores an immutable program (for example, BIOS) and the like. The RAM is a high-speed and volatile storage device such as a DRAM (Dynamic Random Access Memory), and temporarily stores a program executed by the processor 1 and data used when the program is executed.
　補助記憶装置３は、例えば、磁気記憶装置（ＨＤＤ）、フラッシュメモリ（ＳＳＤ）等の大容量かつ不揮発性の記憶デバイスである。また、補助記憶装置３は、プロセッサ１がプログラムの実行時に使用するデータ及びプロセッサ１が実行するプログラムを格納する。すなわち、プログラムは、補助記憶装置３から読み出されて、メモリ２にロードされて、プロセッサ１によって実行されることによって、計算機の各機能を実現する。 The auxiliary storage device 3 is a large-capacity and non-volatile storage device such as a magnetic storage device (HDD) or a flash memory (SSD). Further, the auxiliary storage device 3 stores data used by the processor 1 when executing the program and the program executed by the processor 1. That is, the program realizes each function of the computer by being read from the auxiliary storage device 3, loaded into the memory 2, and executed by the processor 1.
　通信インターフェース４は、所定のプロトコルに従って、他の装置との通信を制御するネットワークインターフェース装置である。 The communication interface 4 is a network interface device that controls communication with other devices according to a predetermined protocol.
　入力インターフェース５は、キーボード６、マウス７、タッチパネル（図示省略）などの入力装置が接続され、オペレータからの入力を受けるインターフェースである。出力インターフェース８は、ディスプレイ装置９やプリンタ（図示省略）などの出力装置が接続され、プログラムの実行結果をオペレータが視認可能な形式で出力するインターフェースである。 The input interface 5 is an interface to which input devices such as a keyboard 6, a mouse 7 and a touch panel (not shown) are connected and which receives an input from an operator. The output interface 8 is an interface to which an output device such as a display device 9 and a printer (not shown) is connected and which outputs the execution result of the program in a format that can be visually recognized by the operator.
　プロセッサ１が実行するプログラムは、リムーバブルメディア（ＣＤ－ＲＯＭ、フラッシュメモリなど）又はネットワークを介して計算機に提供され、非一時的記憶媒体である不揮発性の補助記憶装置３に格納される。このため、計算機は、リムーバブルメディアからデータを読み込むインターフェースを有するとよい。 The program executed by the processor 1 is provided to the computer via a removable medium (CD-ROM, flash memory, etc.) or a network, and is stored in the non-volatile auxiliary storage device 3 which is a non-transitory storage medium. Therefore, the computer may have an interface for reading data from the removable medium.
　データ収集装置１０２及び演算装置１０３は、物理的に一つの計算機上で、又は、論理的又は物理的に構成された複数の計算機上で構成される計算機システムであり、複数の物理的計算機資源上に構築された仮想計算機上で動作してもよい。 The data collection device 102 and the arithmetic device 103 are a computer system configured on a single computer physically or on a plurality of logically or physically configured computers, and on a plurality of physical computer resources. It may operate on a virtual machine built in.
　各データに含まれる主なデータ項目については後述する。例えば、図２に示すように、環境情報データベース１０５の気象データ１０８は、観測項目、観測局の緯度及び経度、観測局名、観測年月、観測値、及び品質情報などを保持する。品質情報は、例えば、所定期間に観測値が得られた回数の割合でもよい。また、日本の気象庁は、品質情報が付されたオープンデータを公開している。 Main data items included in each data will be described later. For example, as shown in FIG. 2, the meteorological data 108 of the environment information database 105 holds observation items, latitude and longitude of observation stations, observation station names, observation dates, observation values, quality information, and the like. The quality information may be, for example, a ratio of the number of times the observed value is obtained in a predetermined period. The Japan Meteorological Agency also publishes open data with quality information.
　図３Ａ及び図３Ｂは、データ収集装置１０２が収集し、保持するデータ項目の例を示す図である。 3A and 3B are diagrams showing examples of data items collected and held by the data collection device 102.
　設備の設備健全度（ＶＨＩ：Virtual Health Index）は、設置されてからの経過年数や、設置されている環境によって異なる。このため、ＶＨＩの算出には設備情報と設備が設置されている環境を示す情報を使用する。本実施例では、気象庁が公開している気象データ１０８、国立環境研究所が公開している大気データ１０９、国土地理院が公開している地理データ（国土数値情報）１１０などのオープンデータをＶＨＩの算出に使用する。本実施例で使用するオープンデータは、気象庁、国立環境研究所、国土地理院のウェブサイトから取得できる。 The equipment health level (VHI: Virtual Health Index) of equipment varies depending on the number of years since installation and the environment in which it is installed. Therefore, the equipment information and the information indicating the environment in which the equipment is installed are used to calculate the VHI. In this embodiment, open data such as meteorological data 108 published by the Japan Meteorological Agency, atmospheric data 109 published by the National Institute for Environmental Studies, and geographic data (national land numerical information) 110 published by the Geographical Survey Institute are converted into VHI. It is used to calculate. The open data used in this embodiment can be obtained from the websites of the Meteorological Agency, National Institute for Environmental Studies, and Geographical Survey Institute.
　図３Ａは、設備保守データベース１０６に格納されるデータ項目の一部を示し、図３Ｂは、環境情報データベース１０５に格納されるデータ項目の一部を示す図である。 FIG. 3A is a diagram showing some of the data items stored in the facility maintenance database 106, and FIG. 3B is a diagram showing some of the data items stored in the environment information database 105.
　気象データ１０８として月別の値が取得可能な項目は、気温、降水、日照／日射、積雪／降雪、風、湿度／気圧、雲量／天気などの実測値である。各項目は月別に統計処理された数値が取得可能である。例えば、統計的に処理された気温として、月の最高気温、最低気温、平均気温、月のうちある条件を満たす日数などが取得できる。 The items for which monthly values can be acquired as the meteorological data 108 are measured values such as temperature, precipitation, sunshine / solar radiation, snow / snowfall, wind, humidity / pressure, cloud amount / weather, and the like. For each item, it is possible to obtain statistically processed numerical values. For example, as the statistically processed temperature, the maximum temperature, the minimum temperature, the average temperature of the month, the number of days satisfying a certain condition of the month, and the like can be acquired.
　大気データ１０９として取得可能な観測項目は、ＳＯ２、ＮＯ、ＮＯ２、ＮＯＸ、ＣＯ、ＯＸ、ＮＭＨＣ、ＣＨ４、ＴＨＣ、ＳＰＭ、ＳＰ、ＰＭ２．５などの実測値である。それぞれ実績値を月間値としてダウンロード可能である。大気データの観測項目も実績値を統計処理した結果としてダウンロード可能である。 The observation items that can be acquired as the atmospheric data 109 are measured values of SO2, NO, NO2, NOX, CO, OX, NMHC, CH4, THC, SPM, SP, PM2.5, etc. The actual values can be downloaded as monthly values. Atmospheric data observation items can also be downloaded as a result of statistically processing the actual values.
　地理データ１１０は、国土地理院の国土数値情報から標高、傾斜度、土地利用、幹線道路、海岸線、湖沼、河川データなどを使用する。国土数値情報はデータにより形式が異なる。例えば、標高及び傾斜度はメッシュデータで、各メッシュの平均標高、最高標高、最低標高、平均傾斜角度、最大傾斜角度、最低傾斜角度、最大傾斜方向、最小傾斜方向を持つ。土地利用は、各メッシュについて、田、その他の農用地、森林、荒地、建物用地、道路、鉄道、その他の用地、河川地及び湖沼、海浜、海水域、ゴルフ場などの利用区分の面積を平方メートル単位で持つ。海岸線、河川データはシェープファイル形式で取得できる。 As the geographic data 110, elevation, slope, land use, main road, coastline, lake, river data, etc. are used from the national numerical information of the Geographical Survey Institute. The format of national numerical information varies depending on the data. For example, the altitude and the gradient are mesh data, and each mesh has an average altitude, a maximum altitude, a minimum altitude, an average inclination angle, a maximum inclination angle, a minimum inclination angle, a maximum inclination direction, and a minimum inclination direction. For land use, for each mesh, the area of use division such as rice fields, other agricultural land, forests, wastelands, building land, roads, railways, other land, rivers and lakes, beaches, seawater areas, golf courses, etc. To have. The coastline and river data can be acquired in the shapefile format.
　演算装置１０３は、データ加工部１１３、ＶＨＩ算出モデル作成部１１４、ＶＨＩ計算部１１５、記憶部１１６及び点検順序決定部１１７から構成される。データ加工部１１３は、データ収集装置１０２が収集したデータの関連付けやクレンジングを行う。クレンジング処理で、異常値や、短期間しか収集されていないデータを除外することによって、ＶＨＩを正確に算出できる。ＶＨＩ計算部１１５では加工済みデータからＶＨＩを算出する。 The arithmetic device 103 includes a data processing unit 113, a VHI calculation model creation unit 114, a VHI calculation unit 115, a storage unit 116, and an inspection order determination unit 117. The data processing unit 113 associates and cleanses the data collected by the data collection device 102. VHI can be accurately calculated by excluding abnormal values and data collected only for a short period of time in the cleansing process. The VHI calculator 115 calculates VHI from the processed data.
　ＶＨＩは、保守対象の設備の健全度を示す数値指標であり、値が高いほど健全であり、値が低いほど劣化が進んでいることを示す。ＶＨＩは、製造時が最も高い値を示すもので、製造時の値を１、故障時の値を０として正規化してもよい。ＶＨＩは、設備ごとに算出される値であり、例えば、電柱、開閉器、変圧器では素材や劣化メカニズムが異なるため、それぞれ別のＶＨＩ算出モデルを作成し、ＶＨＩを算出する。 VHI is a numerical index that indicates the soundness of the equipment to be maintained. The higher the value, the better the sound, and the lower the value, the worse the deterioration. The VHI shows the highest value at the time of manufacture, and may be normalized by setting the value at the time of manufacture to 1 and the value at the time of failure to 0. VHI is a value calculated for each facility. For example, since a power pole, a switch, and a transformer have different materials and deterioration mechanisms, different VHI calculation models are created and VHI is calculated.
　記憶部１１６は、加工済みデータ、及び算出されたＶＨＩを格納する。点検順序決定部１１７は、算出されたＶＨＩとＶＨＩ算出に使用したデータの信頼性に基づいて、点検順序を適正化する。適正化された点検順序と、適正化による効果は、出力装置１０４の画面に表示される。 The storage unit 116 stores the processed data and the calculated VHI. The inspection order determination unit 117 optimizes the inspection order based on the calculated VHI and the reliability of the data used for the VHI calculation. The optimized inspection sequence and the effect of the optimization are displayed on the screen of the output device 104.
　図４は、演算装置１０３が現在のＶＨＩを算出する際の、データ加工部１１３、ＶＨＩ計算部１１５及び点検順序決定部１１７が実行する点検順序決定処理のフローチャートである。 FIG. 4 is a flowchart of the inspection order determination processing executed by the data processing unit 113, the VHI calculation unit 115, and the inspection order determination unit 117 when the arithmetic device 103 calculates the current VHI.
　データ加工部１１３は、環境情報データベース１０５と設備保守データベース１０６に格納したデータを分析に適したデータに変換し、関連付けを行うデータ加工処理を実行する（４０１）。データの変換は二種類実施する。一つ目は設備データの変換である。現在のＶＨＩを算出する場合、設備データの変換では、日付に関するデータを現在までの経過日数に変換する。例えば、工事年月日は設備データに記載されている工事年月日を現在までの経過日数に変換する。二つ目はオープンデータの加工である。オープンデータの加工では、まず、オープンデータを分析可能な形式に変換し、各設備に関連付ける。分析可能な形式への変換として、各メッシュにおける各土地利用面積が記載されている土地利用データから各メッシュにおける土地利用割合への変換がある。また、海岸線や工業用地、河川・湖沼海岸線データ、幹線道路データはシェープファイルであり、それぞれの設備が存在する位置を示す。ＶＨＩの算出では設備の劣化に影響する特徴量を入力データとして利用するため、各設備から海岸線、工業用地、河川、湖沼までの距離を算出する。さらに気象データついては、設備が設置されてから現在までの加算値、平均値、最大値、最小値などを算出する。例えば、降水量や降雪量は日々の観測値を累積した月間の加算値に意味があり、気温や風速は日々の観測値の月間の平均値、最大値、最小値等に意味がある。各データを加工後、設備ＩＤをキー項目として設備データと、点検履歴データと、オープンデータとを関連付ける。本実施例では、設備データとの距離が最も近い観測点のオープンデータを関連付ける。以上の加工・算出結果は演算装置１０３の記憶部１１６に保持される。 The data processing unit 113 converts the data stored in the environment information database 105 and the equipment maintenance database 106 into data suitable for analysis, and executes a data processing process for associating (401). Two types of data conversion are implemented. The first is the conversion of equipment data. When calculating the current VHI, in the conversion of facility data, the date-related data is converted into the number of days elapsed up to the present. For example, for the construction date, the construction date described in the equipment data is converted into the number of elapsed days up to the present. The second is the processing of open data. In the processing of open data, first, open data is converted into an analyzable format and associated with each facility. As a conversion to a form that can be analyzed, there is conversion from land use data that describes each land use area in each mesh to a land use ratio in each mesh. The coastline, industrial land, river / lake shoreline data, and main road data are shape files, and indicate the locations where the respective facilities exist. Since the VHI calculation uses the feature amount that affects the deterioration of the equipment as input data, the distance from each equipment to the coastline, industrial land, river, lake is calculated. Furthermore, for meteorological data, additional values, average values, maximum values, minimum values, etc. from the time the equipment is installed to the present are calculated. For example, the amount of precipitation and the amount of snowfall are significant to the monthly added value obtained by accumulating the daily observed values, and the temperature and wind speed are significant to the monthly average value, maximum value, minimum value, etc. of the daily observed values. After processing each data, the equipment data, the inspection history data, and the open data are associated with the equipment ID as a key item. In this embodiment, the open data of the observation point closest to the facility data is associated. The above processing / calculation results are held in the storage unit 116 of the arithmetic device 103.
　ＶＨＩ計算ステップ４０２は、ＶＨＩ算出モデル作成部１１４及びＶＨＩ計算部１１５で実行される。まず、ＶＨＩ算出モデル作成部１１４では過去のデータを使用して事前にＶＨＩ算出モデルを作成する。ここでＶＨＩ算出モデル作成時に使用するデータ項目とモデル作成方法について説明する。ＶＨＩ算出モデル作成時の特徴量（説明変数）は、ステップ４０１で作成するデータと同じ項目を使用し、点検履歴データを目的変数とする。特徴量は、モデル作成時以前の気象データ、大気データ、地理データ、設備データなどである。広範囲にわたって設置される広域設備には個々に設備状態を計測するセンサが設けられないことから、目的変数に設定する点検履歴データは、設備の状態を数値で評価しても、”ＯＫ””ＮＧ”の２値で評価してもよい。数値で設備状態を記録している場合には、モデル作成時の目的変数に点検結果を設定することで、現在の設備状態を数値で予測可能である。 The VHI calculation step 402 is executed by the VHI calculation model creation unit 114 and the VHI calculation unit 115. First, the VHI calculation model creation unit 114 creates a VHI calculation model in advance using past data. Here, the data items used when creating the VHI calculation model and the model creating method will be described. As the characteristic amount (explanatory variable) at the time of creating the VHI calculation model, the same items as the data created at step 401 are used, and the inspection history data is used as the objective variable. The feature amount is weather data, atmospheric data, geographical data, facility data, etc. before the model was created. Wide-area equipment installed over a wide area is not equipped with a sensor that individually measures the equipment status. Therefore, the inspection history data set as the objective variable is "OK", "NG" even if the equipment status is evaluated numerically. You may evaluate by the two values of ". When the equipment status is recorded numerically, the current equipment status can be predicted numerically by setting the inspection result as the objective variable when the model was created.
　しかし、一般的に広域設備の点検結果の多くは、複数の段階で評価されている。”ＯＫ””ＮＧ”の２値で記録されている場合には”ＯＫ””ＮＧ”の２クラスを目的変数として状態を予測するモデルを作成する必要がある。しかし、予測結果が”ＯＫ””ＮＧ”の二値の場合には、”ＮＧ”と判別された設備のうち、どの設備の状態が最も悪いか判定できず、適切な点検順序の決定が困難である。そこで、直接、設備状態を数値で予測するのではなく、ＳＶＭ（Support Vector Machine）で”ＯＫ””ＮＧ”を識別する境界面を作成し、クラスの境界面から各設備データまでの距離をＶＨＩとして利用することによって数値として設備状態を示す方法を採用する。”ＯＫ””ＮＧ”を分けるモデルにおいて境界面から”ＯＫ”側に離れている場合には設備の状態が良く、”ＮＧ”側に離れている場合には設備の状態が悪いことを示す。”ＮＧ”側の境界面からの距離はマイナスをつけてＶＨＩとすることによって、ＶＨＩ値が大きいほど健全度が高く、小さいほど健全度が低く、早急に点検・修理が必要である状態を示す。 However, in general, most inspection results of wide area facilities are evaluated in multiple stages. In the case of being recorded with binary values of "OK" and "NG", it is necessary to create a model for predicting the state by using the two classes of "OK" and "NG" as objective variables. However, when the prediction result is a binary value of “OK” and “NG”, it is difficult to determine which of the equipments judged as “NG” has the worst condition, and it is difficult to determine an appropriate inspection order. Is. Therefore, instead of directly predicting the equipment state numerically, create a boundary surface that identifies "OK" and "NG" with SVM (Support Vector Machine), and calculate the distance from the class boundary surface to each piece of equipment data by VHI. The method of indicating the equipment status as a numerical value is adopted by using as. In the model in which “OK” and “NG” are separated, if the distance from the boundary surface to the “OK” side is good, the condition of the equipment is good, and if it is far from the “NG” side, the condition of the equipment is bad. The distance from the boundary surface on the “NG” side is given a negative value to set it as VHI, and the higher the VHI value, the higher the soundness, and the smaller the VHI value, the lower the soundness, indicating that the condition requires immediate inspection and repair. ..
　なお、２値で設備の状態を評価するＶＨＩ算出方法では、前述した以外の方法を採用できる。また、ＳＶＭなどの方法によって、目的変数の予測に使用する各特徴量の重要度（目的変数に対する寄与の大きさ）をＶＨＩ算出モデル作成時に取得可能である。特徴量の重要度によって、目的変数に大きな影響を与える特徴量を知ることができる。また、点検結果を５段階など複数段階で評価している場合には、推定される各段階の確からしさを用いてＶＨＩを算出できる。複数段階で評価した場合でも、各段階に判定された設備を巡視・点検すべき順序の決定が困難である。このため、複数段階評価の場合にも２段階の”ＯＫ””ＮＧ”評価と同様に環境情報データベース１０５に格納されるデータと設備保守データベース１０６に格納される過去のデータを入力として、設備状態の段階を推定するモデルを作成する。例えば、５段階で設備状態を評価する場合に、段階１は設備の劣化が進んでいる状態を示し、段階５は設備が健全な状態を示す。ある設備は、設置後、段階５から段階１まで状態が徐々に変化すると考えられる。ＳＶＣを算出モデルとして利用したとき、設備状態５と推定される確からしさが高いほど設備状態が良く、設備状態１と推定される確からしさが高いほど設備状態が悪く、劣化が進んでいると判定できる。そこで、ＶＨＩ算出モデルで算出される各劣化段階評価に割り当てられる確からしさを用いてＶＨＩを算出する。 Note that the VHI calculation method that evaluates the state of equipment by two values can adopt methods other than those described above. In addition, the importance of each feature amount used for predicting the target variable (magnitude of contribution to the target variable) can be acquired at the time of creating the VHI calculation model by a method such as SVM. It is possible to know the feature amount that has a large influence on the objective variable by the importance of the feature amount. Further, when the inspection result is evaluated in multiple stages such as five stages, the VHI can be calculated using the estimated certainty of each stage. Even in the case of evaluation in multiple stages, it is difficult to determine the order in which the equipment judged in each stage should be inspected and inspected. Therefore, even in the case of the multi-level evaluation, the data stored in the environment information database 105 and the past data stored in the facility maintenance database 106 are used as inputs in the same manner as in the two-level “OK” “NG” evaluation. Create a model to estimate the stage of. For example, when the equipment state is evaluated in five stages, the stage 1 shows a state where the deterioration of the facility is progressing, and the stage 5 shows a state where the facility is healthy. It is considered that the state of some equipment gradually changes from stage 5 to stage 1 after installation. When SVC is used as a calculation model, it is determined that the higher the probability of being estimated to be equipment state 5, the better the equipment state, and the higher the probability of being estimated to be equipment state 1, the worse the equipment state, and the deterioration is progressing. it can. Therefore, the VHI is calculated using the certainty assigned to each deterioration stage evaluation calculated by the VHI calculation model.
　図５は、点検結果を複数段階で評価する場合に、各劣化段階評価に割り当てられる確からしさの数値を示す劣化段階評価テーブルの例を示す図である。ＶＨＩは劣化段階評価とその確からしさの重みづけ平均で算出する。ＶＨＩ算出式は下記に示す。ここで劣化評価段階ｎと推定される確からしさをｐｎとする。ただし、複数段階で設備の状態を評価する際のＶＨＩ算出方法はこれに限らない。 FIG. 5 is a diagram showing an example of a deterioration stage evaluation table indicating a numerical value of the probability assigned to each deterioration stage evaluation when the inspection result is evaluated in a plurality of stages. VHI is calculated by deterioration stage evaluation and a weighted average of its certainty. The VHI calculation formula is shown below. Here, the probability estimated to be the deterioration evaluation stage n is pn. However, the VHI calculation method for evaluating the state of the equipment in multiple stages is not limited to this.
Figure JPOXMLDOC01-appb-M000001
Figure JPOXMLDOC01-appb-M000001
　演算装置１０３のＶＨＩ計算部１１５は、ステップ４０２のＶＨＩ計算処理を実行する。ステップ４０２のＶＨＩ計算では、ＶＨＩ算出モデル作成部１１４が算出したモデルに、ステップ４０１のデータ加工で作成したデータを入力し、現在のＶＨＩを数値指標として算出する。ＶＨＩ算出時に特徴量の重要度が出力され、演算装置１０３の記憶部１１６に保持する。図１１に保持される重要度を示すテーブルの例を示す。特徴量の重要度は、ステップ４０３の点検順序適正化処理で利用される。各項目の詳細については後述する。 The VHI calculation unit 115 of the arithmetic unit 103 executes the VHI calculation process of step 402. In the VHI calculation of step 402, the data created by the data processing of step 401 is input to the model calculated by the VHI calculation model creation unit 114, and the current VHI is calculated as a numerical index. At the time of VHI calculation, the degree of importance of the feature amount is output and stored in the storage unit 116 of the arithmetic device 103. FIG. 11 shows an example of a table showing the degree of importance held. The importance of the feature amount is used in the inspection order optimization process in step 403. Details of each item will be described later.
　ステップ４０２のＶＨＩ計算処理の実行結果として、各設備のＶＨＩが算出される。各設備のＶＨＩは、図６に示すＶＨＩ出力データとして演算装置１０３の記憶部１１６に保持され、出力装置１０４から出力（例えば、リストとして表示）される。ステップ４０３の点検順序適正化処理では、ステップ４０２のＶＨＩ計算処理で算出されたＶＨＩに基づいて、最適な設備の巡視点検順序を決定する。 The VHI of each facility is calculated as the execution result of the VHI calculation processing in step 402. The VHI of each equipment is held in the storage unit 116 of the arithmetic device 103 as the VHI output data shown in FIG. 6, and is output (for example, displayed as a list) from the output device 104. In the inspection order optimization processing of step 403, the optimum inspection inspection order of the equipment is determined based on the VHI calculated by the VHI calculation processing of step 402.
　図７は、図４のステップ４０３の点検順序適正化処理の詳細な手順のフローチャートである。 FIG. 7 is a flowchart of a detailed procedure of the inspection order optimization process of step 403 of FIG.
　ステップ７０１の点検順序適正化処理では、ステップ４０１のＶＨＩ算出処理の結果として出力されたＶＨＩを値が低い方から順に設備を並べ替え、設備点検順序リストを作成する。 In the inspection order optimization processing in step 701, the equipment is rearranged in order from the one having the lowest VHI output as a result of the VHI calculation processing in step 401 to create an equipment inspection order list.
　次に、ステップ７０２の不確信度算出処理では、モデル作成時に使用した各特徴量の重要度及びデータの品質情報から、各設備に関連付けられるデータの不確信度を算出する。ステップ７０２の処理の詳細については後述する。 Next, in the uncertainty calculation process of step 702, the uncertainty of the data associated with each facility is calculated from the importance of each feature amount used when creating the model and the quality information of the data. Details of the process of step 702 will be described later.
　ステップ７０３の不確信度に基づく設備点検順序並び替え処理では、ステップ７０１で並べ替えた設備点検順序リストをセグメントに分け（例えば、上位から所定件数ずつセグメントに分け）、セグメント内で不確信度に基づいて設備の点検順序を並べ替える。セグメントの分け方としてＶＨＩの値を一定数値ごとに分ける方法や、一年など、所定の期間に点検可能な設備数ごとに分ける方法がある。セグメントを分ける方法は、管理者が入力装置１０１のキーボードやマウスを利用して設定する。設備の巡視、点検の実施にあたり、作業員数及び点検コストは限られているため、一年間に点検可能な設備数は限られる。そこで、設備点検順序リストの上位から順に点検予定年を設定する。 In the equipment inspection order rearrangement processing based on the degree of uncertainty in step 703, the equipment inspection order list rearranged in step 701 is divided into segments (for example, divided into a predetermined number of segments from the top), and the degree of uncertainty within the segment is calculated. Rearrange the inspection order of equipment based on. As a method of dividing the segments, there are a method of dividing the value of VHI by a certain numerical value and a method of dividing by the number of facilities that can be inspected in a predetermined period such as one year. The method of dividing the segment is set by the administrator using the keyboard or mouse of the input device 101. Since the number of workers and inspection costs are limited when conducting inspections and inspections of equipment, the number of equipment that can be inspected in one year is limited. Therefore, scheduled inspection years are set in order from the top of the equipment inspection order list.
　ステップ７０４の将来のＶＨＩ算出処理では、将来のデータに変換した特徴量を図４のステップ４０２で作成したモデルに入力し、将来のＶＨＩを算出する。 In the future VHI calculation process of step 704, the feature amount converted into future data is input to the model created in step 402 of FIG. 4 to calculate the future VHI.
　最後に、ステップ７０５にて点検予定年月のＶＨＩと現在のＶＨＩとの差を算出し、点検予定年月までに著しく設備状態が低下する設備を抽出し、設備劣化が生じる前に点検が完了するように点検順序リストを再度並び替える。将来のＶＨＩ算出処理の詳細は後述する。 Finally, in step 705, the difference between the VHI for the scheduled inspection date and the current VHI is calculated, and the equipment whose equipment condition significantly deteriorates by the scheduled inspection date is extracted, and the inspection is completed before the equipment deterioration occurs. Reorder the inspection order list as you would. Details of the future VHI calculation process will be described later.
　不確信度は、設備とデータ観測局との距離やＶＨＩ算出時の特徴量に使用するオープンデータの品質情報から算出される。データの品質情報とは、データ自体の信頼性を示す値であり、本実施例では、オープンデータの精度（品質情報）や、目的変数として入力される点検結果（劣化評価段階ｎ）の更新頻度を用いる。 Confidence level is calculated from the distance between the equipment and the data observation station and the quality information of the open data used for the features when calculating VHI. The data quality information is a value indicating the reliability of the data itself, and in this embodiment, the accuracy of open data (quality information) and the update frequency of the inspection result (degradation evaluation stage n) input as an objective variable. To use.
　まず、設備に関連付けられた観測局との距離を用いて不確信度を算出する例を説明する。 First, an example of calculating the degree of uncertainty using the distance to the observation station associated with the equipment is explained.
　図８は、ステップ７０２の不確信度算出処理の詳細な手順のフローチャートである。 FIG. 8 is a flowchart of the detailed procedure of the uncertainty calculation processing in step 702.
　まず、図８のステップ８０１で、設備に関連付けられた観測局との距離を算出する。設備と観測局との距離は、設備保守データベース１０６の設備データ１１１に格納されている設備の位置情報、及び環境情報データベース１０５の各データ１０８、１０９、１１０に格納されている観測局の位置情報から算出し、演算装置１０３の記憶部１１６に格納される。 First, in step 801 of FIG. 8, the distance to the observation station associated with the equipment is calculated. The distance between the equipment and the observation station is the location information of the equipment stored in the equipment data 111 of the equipment maintenance database 106, and the location information of the observation station stored in each data 108, 109, 110 of the environment information database 105. And is stored in the storage unit 116 of the arithmetic device 103.
　例えば、図９に示す設備００１に最も近い観測局は観測局１である。設備００１と観測局１間の距離をｄ１１とする。しかし、分析に使用するデータ項目が一つの観測局で全て観測されているとは限らない。例えば、図１０に示すように、設備００１に最も近い観測局１では降水量が観測されていないため、降水量が観測されている観測局のうち、最も距離が近い観測局３と設備００１も関連付ける必要がある。このように一つの設備に対して複数の観測局のデータが関連付けられてもよい。設備に関連付けられた各観測局との距離を記憶部１１６に格納する。このように、一つの設備が１又は複数の観測局と関連付けられ、図８のステップ８０１の処理によって図１２に例示するテーブルが作成される。 For example, the observation station closest to the equipment 001 shown in FIG. 9 is the observation station 1. The distance between the equipment 001 and the observation station 1 is d 11 . However, not all data items used for analysis are observed by one observation station. For example, as shown in FIG. 10, since the observation station 1 closest to the equipment 001 does not observe the precipitation amount, the observation station 3 and the equipment 001 having the shortest distance among the observation stations having the precipitation amount are also observed. Must be associated. In this way, data of a plurality of observation stations may be associated with one piece of equipment. The distance to each observation station associated with the equipment is stored in the storage unit 116. In this way, one piece of equipment is associated with one or a plurality of observation stations, and the table illustrated in FIG. 12 is created by the processing of step 801 in FIG.
　次に、不確信度算出処理（ステップ８０２）では、ステップ８０１で算出された設備と観測局との距離を用いて不確信度を算出する。不確信度は設備と観測局間との距離と関連付けた特徴量の重要度を用いた重みづけ平均によって不確信度Ｒｄ＿１を算出する。 Next, in the uncertainty calculation process (step 802), the uncertainty is calculated using the distance between the facility and the observation station calculated in step 801. For the degree of uncertainty, the degree of uncertainty R d_1 is calculated by a weighted average using the importance of the feature quantity associated with the distance between the equipment and the observation station.
　図１１は、図８のステップ８０２の不確信度算出処理に使用する特徴量、各特徴量の重要度、及びデータ取得元を関連付けたテーブルの例を示す図である。また、図１２は、ステップ８０２の不確信度算出処理に入力される設備に関連付けられた特徴量（観測値）である、観測局、設備－観測局間距離、品質情報を記録するテーブルを示す図である。これらテーブルは記憶部１１６に格納される。 FIG. 11 is a diagram showing an example of a table in which feature amounts used in the uncertainty calculation process of step 802 of FIG. 8, importance of each feature amount, and data acquisition sources are associated. Further, FIG. 12 shows a table recording the observation station, the equipment-observation station distance, and the quality information, which are the feature quantities (observation values) associated with the equipment input to the uncertainty calculation processing in step 802. It is a figure. These tables are stored in the storage unit 116.
　図１１に示すテーブルのデータ取得元カラムには、特徴量が環境情報データベース１０５に記録されている場合には１を、設備保守データベース１０６に記録されている場合には２を記録する。不確信度は、環境情報データベース１０５に格納された観測局で収集されたデータ、及び設備保守データベース１０６に格納されたデータのいずれでも算出可能である。 In the data acquisition source column of the table shown in FIG. 11, 1 is recorded when the characteristic amount is recorded in the environment information database 105, and 2 is recorded when the characteristic amount is recorded in the facility maintenance database 106. The degree of uncertainty can be calculated using either the data collected by the observation station stored in the environment information database 105 or the data stored in the facility maintenance database 106.
　設備－観測局間距離に基づく不確信度を算出する場合には、図１１のテーブルを参照し、データ取得元カラムに”１”が設定された、観測局データを使用した特徴量を抽出する。これによって、例えば、図１２に示すように、データ取得元カラムにフラグ”１”が設定されている特徴量が気温、降水量及び気温の３項目である場合、設備００１の設備－観測局距離に基づく不確信度Ｒｄ＿１を、図１１のテーブルに記録された特徴量の重みと記憶部１１６に格納した設備と観測局との距離を用いて式（２）によって算出する。下式において、ｄ１１は設備００１と気温及び気圧を測定した観測局１との距離、ｄ１３は設備００１と降水量を観測した観測局３との距離である。 When calculating the uncertainty level based on the equipment-observation station distance, refer to the table in FIG. 11 and extract the feature amount using the observation station data with “1” set in the data acquisition source column. .. As a result, for example, as shown in FIG. 12, when the feature quantity for which the flag “1” is set in the data acquisition source column is the three items of temperature, precipitation and temperature, the equipment-observation station distance of the equipment 001. Based on the weight of the feature amount recorded in the table of FIG. 11 and the distance between the equipment and the observation station stored in the storage unit 116, the uncertainty degree R d — 1 based on Eq. In the following formula, d 11 is the distance between the equipment 001 and the observation station 1 that measured the temperature and atmospheric pressure, and d 13 is the distance between the equipment 001 and the observation station 3 that observed the precipitation amount.
Figure JPOXMLDOC01-appb-M000002
Figure JPOXMLDOC01-appb-M000002
　次に、環境情報データベース１０５に格納されるデータ（各観測項目のデータ品質や観測日数）を用いて不確信度を算出する例を説明する。設備００１のＶＨＩ算出に使用したデータの品質情報を用いて不確信度Ｒｑ＿１を算出する場合には、図１２の品質情報カラムに格納したデータ品質情報を数値に変換した値の重要度を用いた重みづけ平均によって不確信度Ｒｑ＿１を算出する。そして、距離に基づく不確信度Ｒｄ＿１及び品質情報に基づく不確信度Ｒｑ＿１から、設備００１の不確信度Ｒ１を下式で算出する。 Next, an example in which the degree of uncertainty is calculated using the data stored in the environment information database 105 (the data quality of each observation item and the number of observation days) will be described. When calculating the non-confidence R Q_1 using quality information of the data used to VHI calculation facility 001, use the severity of a value obtained by converting the numeric data quality information stored in the quality information column of Figure 12 The uncertainty level R q — 1 is calculated by the weighted average. Then, the non-confidence R Q_1 based on non confidence R d_1 and quality information based on the distance, to calculate the non-confidence R1 equipment 001 by the following equation.
Figure JPOXMLDOC01-appb-M000003
Figure JPOXMLDOC01-appb-M000003
　計算に使用する重みｗｄｉｓｔａｎｃｅとｗｑｕａｌｉｔｙは、電力会社のポリシーに従って適切な値を設定するとよい。算出された不確信度は図５のテーブルを参照して劣化段階に変換され、図１４に示す点検順序リストで記憶部１１６に格納する。なお、重みｗｄｉｓｔａｎｃｅとｗｑｕａｌｉｔｙの調整によって、距離を用いることなく、品質情報を用いて不確信度を算出してもよい。 The weights w distance and w quality used in the calculation may be set to appropriate values according to the policy of the electric power company. The calculated uncertainties are converted into deterioration stages with reference to the table of FIG. 5, and stored in the storage unit 116 in the inspection order list shown in FIG. Note that by adjusting the weights w distance and w quality , the uncertainty may be calculated using the quality information without using the distance.
　なお、設備の点検間隔を用いて不確信度を計算してもよい。例えば、点検間隔が長ければ不確信度を大きくし、短ければ（例えば３か月）不確信度を小さくする。これは、点検間隔が５年の設備は、点検後の時間の経過に伴って推定される設備の状態と実際の設備の状態との乖離が大きくなると考えられ、点検間隔が３か月の設備より、不確信度が大きくなるからである。 Note that the degree of uncertainty may be calculated using the equipment inspection interval. For example, if the inspection interval is long, the degree of uncertainty is increased, and if it is short (for example, 3 months), the degree of uncertainty is decreased. This is because the equipment with an inspection interval of 5 years is considered to have a large gap between the estimated equipment status and the actual equipment status with the passage of time after the inspection. This is because the degree of uncertainty increases.
　また、点検情報１１２（設備保守データベース１０６）に記録されている前回の点検年月日からの経過期間が長ければ不確信度を大きくし、短ければ不確信度を小さくしてもよい。 Further, the degree of uncertainty may be increased if the elapsed period from the previous inspection date recorded in the inspection information 112 (equipment maintenance database 106) is long, and may be decreased if the period is short.
　さらに、品質情報として、各観測項目のデータ品質や観測日数、点検間隔、前回の点検からの経過期間を例示したが、設備の種類によって劣化に寄与する観測項目の他の品質情報を使用してもよく、これらのうち、任意の一つ以上を使用すればよい。 Furthermore, as quality information, the data quality of each observation item, the number of observation days, the inspection interval, and the elapsed time since the previous inspection were illustrated, but other quality information of observation items that contribute to deterioration depending on the type of equipment is used. Of course, any one or more of these may be used.
　図１３は、図７のステップ７０３の不確信度に基づく点検順序並べ替え処理の詳細な手順のフローチャートである。 FIG. 13 is a flowchart of the detailed procedure of the inspection order rearrangement process based on the uncertainty in step 703 of FIG.
　ステップ１３０１では、図７のステップ７０１の出力結果である点検順序リストを上位から順に複数セグメントに分ける。セグメントに分ける方法は、ＶＨＩの値ごとに分ける方法や、所定数ずつ分ける方法があり、設備管理ポリシーや目的に適する方法や数値が点検計画立案者によって選択される。 In step 1301, the inspection order list, which is the output result of step 701 in FIG. 7, is divided into a plurality of segments in order from the top. As a method of dividing into segments, there are a method of dividing by VHI value and a method of dividing by a predetermined number, and the inspection planner selects a method and a numerical value suitable for the facility management policy and purpose.
　ステップ１３０２では、図７のステップ７０２で算出した不確信度に基づいて、ステップ１３０１で分けたセグメント内で設備点検順序リストを並べ替える。このとき、ＶＨＩの信頼性が高い設備を優先的に点検する場合には、不確信度が低い設備を上位の点検順に並べる。また、ＶＨＩの値が低いセグメントで、確実に設備を点検したい場合には不確信度が高い設備を上位の点検順に並べる。不確信度によってオープンデータのデータ信頼性を評価可能となる。図１４で示す点検順序リストの設備を不確信度に基づいて並べ替えた後、記憶部１１６に格納する。 At step 1302, the equipment inspection order list is rearranged within the segment divided at step 1301 based on the uncertainty level calculated at step 702 of FIG. 7. At this time, in the case of preferentially inspecting equipment with high VHI reliability, equipment with low uncertainty is arranged in the order of higher inspection. Further, in a segment having a low VHI value, when it is desired to inspect the equipment reliably, the equipment having a high degree of uncertainty is arranged in the order of higher inspection. The degree of uncertainty makes it possible to evaluate the data reliability of open data. The equipment of the inspection order list shown in FIG. 14 is sorted based on the degree of uncertainty, and then stored in the storage unit 116.
　図１５は、図７のステップ７０４の将来のＶＨＩ算出処理の詳細な手順のフローチャートである。 FIG. 15 is a flowchart of detailed procedures of future VHI calculation processing in step 704 of FIG.
　ステップ７０４で算出された将来のＶＨＩに基づいて、ステップ７０５では点検順序リストを並べ替える。配電会社によってポリシーは異なるが、時間を基準にして保全する時間基準保全の場合には数年に一度のサイクルで全ての設備を点検する。例えば、時間基準保全を導入していた場合に設定されている周期をＭ年とする。時間基準保全で設定されている周期は計画立案者がキーボードから入力する。図４のステップ４０２では現時点までのデータを使用して、現時点でのＶＨＩを算出するが、ステップ７０４では将来のＶＨＩを算出するため、Ｍ年後までのデータを作成する必要がある。 In step 705, the inspection order list is rearranged based on the future VHI calculated in step 704. The policy differs depending on the power distribution company, but in the case of time-based maintenance, where maintenance is performed on a time basis, all facilities are inspected once every few years. For example, the cycle set when time-based maintenance is introduced is M years. The planner inputs the cycle set by the time base maintenance from the keyboard. In step 402 of FIG. 4, the data up to the current time is used to calculate the VHI at the current time, but in step 704, the future VHI is calculated, so that it is necessary to create data up to M years later.
　図１５のステップ１５０１では、現在からＭ年後までの各年についてオープンデータを作成する。標高や海岸線からの距離はＭ年後に大きく変化しないと考えられるが、降水量や日照量のＭ年分を加算して合計値を算出する。また、Ｍ年後までの詳細な気象予報の取得は困難であるため、長期の気象シナリオや過去の気象データに基づいて複数のパターンを想定して作成する。例えば、平均的な気候が続くことが想定される場合には過去数年分の降水量や日照量などの平均値を加算して各年分の気象データを算出することによって、Ｍ年後までの各年の分析に適した気象データを取得できる。 In step 1501 of FIG. 15, open data is created for each year from now to M years later. Although it is considered that the altitude and distance from the coastline do not change significantly after M years, the total value is calculated by adding M years worth of precipitation and sunshine. In addition, since it is difficult to obtain detailed weather forecasts up to M years later, multiple patterns are assumed and created based on long-term weather scenarios and past weather data. For example, if it is assumed that the average climate will continue, by adding the average values of precipitation and sunshine for the past several years to calculate the meteorological data for each year, until M years later The weather data suitable for the analysis of each year can be acquired.
　ステップ１５０２では、Ｍ年後までの各年の設備データを作成し、更新する。ステップ１５０２では、設備を設置してからＭ年後までの各年における経過年数を算出する。 In step 1502, equipment data for each year up to M years after is created and updated. In step 1502, the number of years elapsed in each year from the installation of the equipment to M years after is calculated.
　ステップ１５０３では、ＶＨＩ算出モデル作成部１１４が作成したＶＨＩ算出モデルを用いて、ステップ１５０１及びステップ１５０２で作成したデータと、環境情報データベース１０５及び設備保守データベース１０６とから参照する年で変化しないデータを説明変数として、Ｍ年後までの各年のＶＨＩを算出する。算出された各年のＶＨＩは記憶部１１６に格納される。 In step 1503, using the VHI calculation model created by the VHI calculation model creation unit 114, the data created in steps 1501 and 1502 and the data that does not change in the year referenced from the environment information database 105 and the equipment maintenance database 106 are used. As an explanatory variable, the VHI of each year up to M years later is calculated. The calculated VHI for each year is stored in the storage unit 116.
　ステップ１５０４では入力装置１０１で入力された一年に点検可能な設備数に基づいて点検順序リストの上位から順に点検予定年を設定する。 In step 1504, scheduled inspection years are set in order from the top of the inspection sequence list based on the number of facilities that can be inspected in a year and input by the input device 101.
　図１６は、図７のステップ７０５の点検予定年ＶＨＩに基づく並べ替え処理の詳細な手順のフローチャートである。 FIG. 16 is a flowchart of a detailed procedure of the rearrangement process based on the scheduled inspection year VHI in step 705 of FIG.
　並べ替えには、図７のステップ７０４で算出した将来のＶＨＩと図４のステップ４０２で算出した現在のＶＨＩを使用する。故障が近い危険な値を現在のＶＨＩが示していなくても、現在のＶＨＩに基づいて決定された点検予定年までに急激にＶＨＩが低下することがある。そこで、ＶＨＩの著しい悪化が予想される設備は点検順序を入れ替え、点検順序を適正化する。図１６のステップ１６０１では記憶部１１６に格納している現在のＶＨＩの値及び将来のＶＨＩの値を参照し、各設備について点検予定年ＶＨＩと現在のＶＨＩとの差を算出する。ＶＨＩの差を算出後、図１７に示す画面を点検計画策定者に提示する。 For rearrangement, the future VHI calculated in step 704 of FIG. 7 and the current VHI calculated in step 402 of FIG. 4 are used. Even if the current VHI does not indicate a dangerous value close to a failure, the VHI may decrease rapidly by the scheduled inspection year determined based on the current VHI. Therefore, the inspection order is changed for the equipment in which VHI is expected to be significantly deteriorated, and the inspection order is optimized. In step 1601 of FIG. 16, the current VHI value and the future VHI value stored in the storage unit 116 are referred to, and the difference between the scheduled inspection year VHI and the current VHI is calculated for each facility. After the VHI difference is calculated, the screen shown in FIG. 17 is presented to the inspection plan creator.
　以上、全設備の点検順序を適正化する処理について説明したが、本発明の処理によって選択された一部の設備の適切な点検順序を決定できる。 The process for optimizing the inspection order of all equipment has been described above, but an appropriate inspection order for some of the equipment selected by the processing of the present invention can be determined.
　図１７は点検計画立案者がある年に点検が予定されている設備のＶＨＩの変化とＶＨＩの変化に影響を与える特徴量を確認する画面例を示す図である。 FIG. 17 is a diagram showing an example of a screen for the inspection planner to confirm the change in VHI of the equipment scheduled to be inspected in a certain year and the feature amount affecting the change in VHI.
　図１７に示す画面例１７０１は、平均ＶＨＩ経時変化表示領域１７０２、ＶＨＩ差表示領域１７０３、及び設備状態推定に影響する特徴量表示領域１７０４を含む。平均ＶＨＩ経時変化表示領域１７０２には、図７のステップ７０４と図１６のステップ１６０１で算出した、Ｎ年後に点検が予定されている設備の平均ＶＨＩと、現在ＶＨＩとＮ年後のＶＨＩの差が閾値を上回る設備について、平均ＶＨＩの継時変化を示すグラフが表示される。平均ＶＨＩ経時変化表示領域１７０２によると、平均ＶＨＩの改善状況を確認できる。ＶＨＩ差表示領域１７０３には、現在のＶＨＩとＮ年後のＶＨＩとの差が閾値より大きい設備について、設備ＩＤ、現在のＶＨＩ及びＮ年後のＶＨＩの値がリスト形式で表示される。また、特徴量表示領域１７０４には、設備状態の悪化に影響した特徴量がリスト形式で表示される。点検計画立案者は、特徴量表示領域１７０４を確認することによって、対象設備の巡視、点検時の着目点及び劣化発生の対策方法を点検実施者に指示できる。 The screen example 1701 shown in FIG. 17 includes an average VHI temporal change display area 1702, a VHI difference display area 1703, and a feature amount display area 1704 that influences equipment state estimation. In the average VHI temporal change display area 1702, the average VHI of the equipment scheduled to be inspected after N years calculated in step 704 of FIG. 7 and step 1601 of FIG. 16 and the difference between the current VHI and the VHI after N years have passed. A graph showing the change in the average VHI over time is displayed for the equipment where is above the threshold. According to the average VHI temporal change display area 1702, the improvement status of the average VHI can be confirmed. In the VHI difference display area 1703, a facility ID, a current VHI, and a VHI value after N years are displayed in a list format for a facility in which the difference between the current VHI and the VHI after N years is larger than a threshold value. Further, in the feature amount display area 1704, feature amounts that have affected the deterioration of the equipment state are displayed in a list format. By checking the feature amount display area 1704, the inspection planner can instruct the inspection person about the target equipment, the points of interest during inspection, and the countermeasures against deterioration.
　図１６のステップ１６０２では、図７のステップ７０３で不確信度に基づいて並べ替えた結果を複数のセグメントに分割する。セグメントは１年ごとのように点検予定年ごとに分けてもよく、ＶＨＩの値の範囲ごとに分けてもよい。 In step 1602 of FIG. 16, the result of rearrangement based on the degree of uncertainty in step 703 of FIG. 7 is divided into a plurality of segments. The segments may be divided by year of scheduled inspection, such as yearly, or may be divided by range of VHI values.
　図１６のステップ１６０３では、図１６のステップ１６０１で算出されたＶＨＩの差が閾値ｔ１より大きい設備をセグメント内の上位に並べ替える。ステップ１６０３ではセグメント内で並べ替えたが、ＶＨＩの差分が大きい場合には他セグメントに移動させることが適切であるため、ステップ１６０４では各セグメントごとにＭ年後までの各年のＶＨＩ平均値を算出する。ステップ１６０５ではステップ１６０３でセグメント内の上位に並べ替えた設備について、点検予定年のＶＨＩと他のセグメントの点検予定年のＶＨＩ平均値とを比較する。 In step 1603 of FIG. 16, the equipment having the VHI difference calculated in step 1601 of FIG. 16 larger than the threshold value t1 is rearranged to the higher rank in the segment. In step 1603, the data is rearranged within the segment, but when the difference in VHI is large, it is appropriate to move to another segment. Therefore, in step 1604, the VHI average value for each year up to M years later is calculated for each segment. calculate. In step 1605, the VHI for the scheduled inspection year and the average VHI for the scheduled inspection years of other segments are compared for the equipment sorted in the higher order in the segment in step 1603.
　ステップ１６０５の条件に当てはまる場合には、ステップ１６０６に進み、当該レコードが所属するセグメントを変更しない。一方、ステップ１６０５の条件に当てはまらない場合には、ステップ１６０７に進み、平均値が最も近いセグメントに当該レコードを移動する。ステップ１６０８では、点検予定年を移動後のセグメントの点検予定年に更新する。ステップ１６０９では、移動後のセグメント内で点検予定年のＶＨＩ順に設備を並べ替える。 If the condition of step 1605 is satisfied, the process proceeds to step 1606 and the segment to which the record belongs does not change. On the other hand, if the condition of step 1605 is not satisfied, the process proceeds to step 1607, and the record is moved to the segment having the closest average value. In step 1608, the scheduled inspection year is updated to the scheduled inspection year of the segment after movement. In step 1609, the equipment is rearranged in the segment after the movement in the order of VHI in the scheduled inspection year.
　図１８は、図４に示す処理を実行した結果として、点検計画策定者が点検順序適正化の効果を確認するための画面例を示す図である。 FIG. 18 is a diagram showing an example of a screen for the inspection plan creator to confirm the effect of the inspection order optimization as a result of executing the processing shown in FIG.
　図１８に示す画面例１８００は、画面左側のグラフ１８０１と、画面右側のテーブル１８０２とを含む。画面左側のグラフ１８０１では、点検予定年を横軸とし、図７のステップ７０４で算出したＭ年後までの各年のＶＨＩを縦軸として、ある年までに点検が実施されていない設備（点検未実施設備）の平均ＶＨＩを表示する。グラフ１８０１では、ＶＨＩが低い方から順に点検を行った場合と本発明により点検順序を適正化を実施した場合を比較して表示する。点検計画策定者は、本設備保守点検支援システムによる適正化によって、点検予定年が後半の設備についても平均ＶＨＩの悪化を抑制できることを、グラフ１８０１で確認できる。 The screen example 1800 shown in FIG. 18 includes a graph 1801 on the left side of the screen and a table 1802 on the right side of the screen. In the graph 1801 on the left side of the screen, the planned inspection year is the horizontal axis, and the VHI for each year up to M years calculated in step 704 of FIG. 7 is the vertical axis, and the equipment not inspected by a certain year (inspection Display the average VHI of unimplemented equipment. In the graph 1801, the case where the inspection is performed in order from the lowest VHI and the case where the inspection order is optimized according to the present invention are compared and displayed. The inspection plan creator can confirm from the graph 1801 that deterioration of the average VHI can be suppressed even for the equipment in the latter half of the planned inspection year by the optimization by the equipment maintenance and inspection support system.
　また、画面右側のテーブル１８０２には、点検予定年と適正化前後の設備点検順序が表示される。テーブル１８０２によって、点検順序適正化前後では点検を行う設備ＩＤの順序が異なることが確認できる。点検計画策定者は、適正化後の設備ＩＤの順に巡視、点検を実施する点検計画を策定できる。 Further, a table 1802 on the right side of the screen displays the planned inspection year and the equipment inspection order before and after the optimization. It can be confirmed from the table 1802 that the order of equipment IDs to be inspected is different before and after the inspection order is optimized. The inspection plan creator can make an inspection plan in which inspection and inspection are performed in the order of the equipment IDs after the optimization.
　点検計画策定者は、設備状態を基準として適正化された点検順序案を、さらに、設備位置を考慮して点検順序を適正化するシステムに入力してもよい。 The planner of the inspection plan may input the inspection order proposal optimized based on the equipment state into the system for optimizing the inspection order considering the equipment position.
　なお、本実施例では広域設備点検の対象の例として配電設備を示したが、本発明のシステムの適用範囲は、これに限定されず、広域に設備を有する通信、ガス、水道等の点検保守順序の適正化に適用可能である。 In this embodiment, the power distribution equipment is shown as an example of the wide area equipment inspection, but the scope of application of the system of the present invention is not limited to this, and communication and gas having a wide area equipment, inspection and maintenance of gas, water, etc. It is applicable to order optimization.
　以上に説明したように、本発明の実施例の設備保守点検支援システムは、点検順序を決定するための条件を受け付ける入力部（入力装置１０１）と、設備が設置されている環境に関する環境データ（環境情報データベース１０５）と、点検対象の設備の情報及び点検結果を含む設備データ（設備保守データベース１０６）を収集するデータ収集部（データ収集装置１０２）と、前記収集されたデータに基づいて現在及び将来の設備健全度を算出し、前記設備健全度の算出に使用したデータの不確信度を算出し、前記算出された設備健全度及び前記算出された不確信度に基づいて点検順序を決定する演算部（演算装置１０３）と、前記決定された点検順序の結果及び前記決定された点検順序による改善状況を表示する出力部（出力装置１０４）とを備えるので、推定された設備状態及びデータの信頼性に基づいて点検順序を適正化できる。また、点検計画策定者は、設備状態を予測する際に使用したデータの信頼性を考慮して適正化された点検順序の提案を受け、その効果を確認できる。また、点検順序の適正化によって、点検前に発生する設備故障数を抑制できる。 As described above, the equipment maintenance / inspection support system according to the embodiment of the present invention includes an input unit (input device 101) that receives a condition for determining the inspection order, and environmental data ( An environmental information database 105), a data collection unit (data collection device 102) that collects equipment data (equipment maintenance database 106) including information on the equipment to be inspected and inspection results, and the current and current data based on the collected data. The future equipment soundness is calculated, the uncertainty level of the data used to calculate the equipment soundness degree is calculated, and the inspection order is determined based on the calculated equipment soundness degree and the calculated uncertainty level. Since the calculation unit (calculation device 103) and the output unit (output device 104) that displays the result of the determined inspection order and the improvement status by the determined inspection order are provided, the estimated equipment state and data The inspection sequence can be optimized based on reliability. Further, the inspection plan creator can receive the proposal of the inspection sequence optimized in consideration of the reliability of the data used when predicting the equipment state, and confirm the effect. Further, by optimizing the inspection sequence, it is possible to suppress the number of equipment failures that occur before the inspection.
　また、データ収集部１０２は、前記環境データ１０５及び前記設備データ１０６を所定のタイミングで自動的に収集するので、情報の更新タイミングを知らなくても、最新の情報に基づいて点検順序を決定できる。 Further, since the data collection unit 102 automatically collects the environmental data 105 and the equipment data 106 at a predetermined timing, the inspection order can be determined based on the latest information without knowing the update timing of the information. .
　また、演算部１０３は、収集された環境データ１０５と設備データ１０６とを関連付け、分析用データに変換するデータ加工部１１３と、前記加工された分析用データから前記設備健全度を算出するモデルを作成するＶＨＩ算出モデル作成部１１４と、前記作成されたモデルを用いて、前記分析用データから設備健全度を算出するＶＨＩ計算部１１５と、前記設備健全度の算出に使用したデータの不確信度を算出し、前記算出された設備健全度及び前記算出された不確信度に基づいて点検順序を決定する点検順序決定部１１７とを有するので、推定された設備状態及びデータの信頼性に基づいて点検順序を適正化できる。 In addition, the calculation unit 103 associates the collected environment data 105 with the equipment data 106 and converts the data into an analysis data, and a model for calculating the equipment soundness from the processed analysis data. A VHI calculation model creation unit 114 to be created, a VHI calculation unit 115 that calculates equipment soundness from the analysis data using the created model, and an uncertainty level of data used to calculate the equipment soundness And an inspection order determination unit 117 that determines an inspection order based on the calculated equipment soundness and the calculated uncertainty level. Therefore, based on the estimated equipment state and the reliability of the data. The inspection order can be optimized.
　また、ＶＨＩ算出モデル作成部１１４は、前記作成されたモデルを用いて算出される設備健全度への、前記モデルに特徴量として入力される各データの寄与の大きさを表す重要度を算出するので、設備状態の悪化に影響したデータが分かり、対象設備の巡視、点検時の着目点及び劣化発生の対策方法を検討できる。 In addition, the VHI calculation model creation unit 114 calculates the degree of importance of the contribution of each data input as a feature amount to the model to the equipment soundness calculated using the created model. Therefore, it is possible to understand the data that has affected the deterioration of the equipment condition, and to examine the target equipment, the points of interest at the time of inspection, and the countermeasures against deterioration.
　また、点検順序決定部１１７は、前記算出された設備健全度が悪い設備を上位の点検順序に並べ替える第１並べ替え処理７０１と、前記不確信度を算出する不確信度算出処理７０２と、前記算出された不確信度に基づいて、設備の点検順序を並べ替える第２並べ替え処理７０３と、将来の設備健全度を算出する将来ＶＨＩ算出処理７０４と、前記算出された将来の設備健全度に基づいて、設備の点検順序を並べ替える第３並べ替え処理７０５とを実行するので、適正な点検順序を作成できる。 In addition, the inspection order determination unit 117, a first rearrangement processing 701 that rearranges the equipment having the calculated poor equipment soundness into a higher inspection order, and an uncertainty calculation processing 702 that calculates the uncertainty. A second rearrangement process 703 for rearranging the inspection order of the facilities, a future VHI calculation process 704 for calculating a future facility soundness, and the calculated future facility soundness based on the calculated uncertainty. Since the third rearrangement process 705 for rearranging the inspection order of the equipment is executed based on the above, the proper inspection order can be created.
　また、点検順序決定部１１７は、前記不確信度算出処理７０２において、前記モデルに入力される各データの品質及び前記算出された重要度に基づいて、前記不確信度を算出するので、データの寄与度を考慮した不確信度を算出でき、適正な点検順序を作成できる。 In addition, the inspection order determination unit 117 calculates the uncertainty level based on the quality of each data input to the model and the calculated importance level in the uncertainty level calculation processing 702. The degree of uncertainty can be calculated considering the contribution, and an appropriate inspection order can be created.
　また、点検順序決定部１１７は、前記不確信度算出処理７０２において、前記環境データに含まれる観測値の重要度に基づいて前記不確信度を算出するので、環境データに含まれる各観測値の寄与度を考慮した不確信度を算出でき、適正な点検順序を作成できる。 Further, since the inspection order determination unit 117 calculates the uncertainty in the uncertainty calculation processing 702 based on the importance of the observation included in the environmental data, the inspection order determination unit 117 calculates the uncertainty of each observation included in the environmental data. The degree of uncertainty can be calculated considering the contribution, and an appropriate inspection order can be created.
　また、点検順序決定部１１７は、前記不確信度算出処理７０２において、前記設備データ１０６に含まれる設備の位置情報及び前記環境データ１０５に含まれる観測局の位置情報を用いて算出された観測局と前記設備との距離に基づいて前記不確信度を算出するので、距離による観測値のズレを考慮した不確信度を算出でき、適正度な点検順序を作成できる。 In addition, the inspection order determination unit 117, in the uncertainty calculation process 702, the observation station calculated using the position information of the equipment included in the equipment data 106 and the position information of the observation station included in the environment data 105. Since the degree of uncertainty is calculated based on the distance between the equipment and the facility, the degree of uncertainty can be calculated in consideration of the deviation of the observed values due to the distance, and an appropriate inspection order can be created.
　また、点検順序決定部１１７は、前記不確信度算出処理７０２において、前記設備データ１０６に含まれる点検結果の点検間隔から前記データの品質を算出するので、点検間隔の長短を考慮した不確信度を算出でき、適正な点検順序を作成できる。 In addition, since the inspection order determination unit 117 calculates the quality of the data from the inspection interval of the inspection result included in the equipment data 106 in the uncertainty calculation process 702, the degree of uncertainty in consideration of the length of the inspection interval. Can be calculated and an appropriate inspection sequence can be created.
　また、点検順序決定部１１７は、前記第２並べ替え処理７０３において、分割されたセグメント内で、前記算出された不確信度に基づいて設備の点検順序を並べ替えるので、不確信度を考慮して適正な点検順序を作成できる。 In addition, the inspection order determination unit 117 rearranges the inspection order of the equipment in the divided segments based on the calculated uncertainties in the second rearrangement process 703, and therefore considers the uncertainties. The proper inspection sequence can be created.
　また、点検順序決定部１１７は、前記将来ＶＨＩ算出処理７０４において、現在から所定の保全周期が終了するまでの各年の環境データを作成し（１５０１）、現在から前記保全周期が終了するまでの各年の設備データを作成し（１５０２）、前記作成された各年の環境データ及び前記作成された各年の設備データを用いて将来の設備健全度を算出し（１５０３）、 前記算出された将来の設備健全度に基づいて点検予定年を設定する（１５０４）ので、将来の設備健全度を正確に算出でき、適正度な点検順序を作成できる。 Further, the inspection order determination unit 117, in the future VHI calculation processing 704, creates environmental data for each year from the present to the end of the predetermined maintenance cycle (1501), and from the present to the end of the maintenance cycle. Facility data for each year is created (1502), future facility soundness is calculated using the created environment data for each year and the created facility data for each year (1503), Since the scheduled inspection year is set based on the future facility soundness (1504), the future facility soundness can be accurately calculated and an appropriate inspection sequence can be created.
　また、点検順序決定部１１７は、前記第３並べ替え処理７０５において、一年に点検実施可能な設備数に基づいて前記設備の点検予定年を設定し、各設備について前記算出された現在の設備健全度と前記算出された点検予定年の設備健全度との差を算出し（１６０１）、所定の順序に並べられた設備をセグメントに分割し（１６０２）、前記設備健全度の差が所定の閾値より大きい設備を前記セグメント内の上位に並べ替え（１６０３）、前記各セグメントにおける設備健全度の平均を算出し（１６０４）、設備が所属するセグメントの点検予定年の設備健全度の平均値が設備点検予定年の設備健全度に最も近いかを判定し（１６０５）、設備が所属するセグメントの点検予定年のＶＨＩ平均値が設備点検予定年のＶＨＩに最も近いものではない場合、平均値が最も近いセグメントの点検予定年に設備の点検予定年を更新し（１６０８）、セグメント内で設備健全度が悪い順に設備を並べ替える（１６０９）ので、将来の設備健全度を考慮した、適正度な点検順序を作成できる。 In addition, the inspection order determination unit 117 sets the scheduled inspection year of the facility based on the number of facilities that can be inspected in one year in the third rearrangement process 705, and the calculated current facility for each facility. The difference between the soundness and the calculated soundness of the facility for the planned inspection year is calculated (1601), the equipment arranged in a predetermined order is divided into segments (1602), and the difference in the soundness of the equipment is predetermined. The equipment larger than the threshold value is rearranged to the higher rank in the segment (1603), the average of the equipment soundness of each segment is calculated (1604), and the average value of the equipment soundness of the scheduled inspection year of the segment to which the equipment belongs is It is judged whether or not the facility soundness is closest to the facility inspection year (1605), and if the VHI average value of the scheduled inspection year of the segment to which the facility belongs is not the closest to the VHI of the facility inspection scheduled year, the average value is determined. The scheduled inspection year of the equipment is updated to the closest scheduled inspection year (1608), and the equipment is sorted in the segment in ascending order of the soundness of the equipment (1609). Therefore, it is appropriate to consider the future soundness of the equipment. You can create an inspection sequence.
　また、出力部１０４は、前記点検順序を決定する前後において、設備の点検時期ごとの設備健全度の平均値を示すグラフと、前記点検順序を決定した後の点検順序のリストとを表示する画面データを出力するので、点検順序の適正化の効果を分かりやすく提示できる。 Further, the output unit 104 is a screen that displays a graph showing an average value of the equipment soundness for each inspection time of the equipment before and after the inspection order is determined, and a list of the inspection order after the inspection order is determined. Since data is output, the effect of optimizing the inspection sequence can be presented in an easy-to-understand manner.
　なお、本発明は前述した実施例に限定されるものではなく、添付した特許請求の範囲の趣旨内における様々な変形例及び同等の構成が含まれる。例えば、前述した実施例は本発明を分かりやすく説明するために詳細に説明したものであり、必ずしも説明した全ての構成を備えるものに本発明は限定されない。また、ある実施例の構成の一部を他の実施例の構成に置き換えてもよい。また、ある実施例の構成に他の実施例の構成を加えてもよい。また、各実施例の構成の一部について、他の構成の追加・削除・置換をしてもよい。 The present invention is not limited to the above-described embodiments, but includes various modifications and equivalent configurations within the scope of the appended claims. For example, the above-described embodiments have been described in detail in order to explain the present invention in an easy-to-understand manner, and the present invention is not necessarily limited to those having all the configurations described. Further, part of the configuration of one embodiment may be replaced with the configuration of another embodiment. Further, the configuration of another embodiment may be added to the configuration of one embodiment. Further, a part of the configuration of each embodiment may be added / deleted / replaced with another configuration.
　また、前述した各構成、機能、処理部、処理手段等は、それらの一部又は全部を、例えば集積回路で設計する等により、ハードウェアで実現してもよく、プロセッサがそれぞれの機能を実現するプログラムを解釈し実行することにより、ソフトウェアで実現してもよい。 Further, each of the above-mentioned configurations, functions, processing units, processing means, etc. may be realized by hardware, for example, by designing a part or all of them with an integrated circuit, and a processor realizes each function. It may be realized by software by interpreting and executing the program.
　各機能を実現するプログラム、テーブル、ファイル等の情報は、メモリ、ハードディスク、ＳＳＤ（Ｓｏｌｉｄ　Ｓｔａｔｅ　Ｄｒｉｖｅ）等の記憶装置、又は、ＩＣカード、ＳＤカード、ＤＶＤ等の記録媒体に格納することができる。 Information such as programs, tables, and files that realize each function can be stored in a memory, a hard disk, a storage device such as SSD (Solid State Drive), or a recording medium such as an IC card, SD card, or DVD.
　また、制御線や情報線は説明上必要と考えられるものを示しており、実装上必要な全ての制御線や情報線を示しているとは限らない。実際には、ほとんど全ての構成が相互に接続されていると考えてよい。 Also, the control lines and information lines are shown to be necessary for explanation, and not all the control lines and information lines necessary for implementation are shown. In reality, it can be considered that almost all configurations are connected to each other.

Claims (14)

  1. 　設備の保守業務における点検順序を決定する設備保守点検支援システムであって、
    　点検順序を決定するための条件を受け付ける入力部と、
    　設備が設置されている環境に関する環境データと、点検対象の設備の情報及び点検結果を含む設備データを収集するデータ収集部と、
    　前記収集されたデータに基づいて現在及び将来の設備健全度を算出し、前記設備健全度の算出に使用したデータの不確信度を算出し、前記算出された設備健全度及び前記算出された不確信度に基づいて点検順序を決定する演算部と、
    　前記決定された点検順序の結果及び前記決定された点検順序による改善状況を表示する出力部とを備えることを特徴とする設備保守点検支援システム。     A facility maintenance inspection support system that determines the inspection sequence in equipment maintenance work,
    An input unit that accepts conditions for determining the inspection order,
    A data collection unit that collects environmental data about the environment in which the equipment is installed, and equipment data including information on the equipment to be inspected and inspection results,
    The present and future equipment soundness is calculated based on the collected data, the uncertainty level of the data used for the calculation of the equipment soundness is calculated, and the calculated equipment soundness and the calculated uncertainties are calculated. A calculation unit that determines the inspection order based on the certainty factor,
    An equipment maintenance / inspection support system, comprising: an output unit that displays a result of the determined inspection order and an improvement status according to the determined inspection order.
  2. 　請求項１に記載の設備保守点検支援システムであって、
    　前記データ収集部は、前記環境データ及び前記設備データを所定のタイミングで自動的に収集することを特徴とする設備保守点検支援システム。     The equipment maintenance inspection support system according to claim 1,
    The facility maintenance and inspection support system, wherein the data collection unit automatically collects the environmental data and the facility data at a predetermined timing.
  3. 　請求項１に記載の設備保守点検支援システムであって、
    　前記演算部は、
    　前記収集された環境データと設備データとを関連付け、分析用データに加工するデータ加工部と、
    　前記加工された分析用データから前記設備健全度を算出するモデルを作成するＶＨＩ算出モデル作成部と、
    　前記作成されたモデルを用いて、前記分析用データから設備健全度を算出するＶＨＩ計算部と、
    　前記設備健全度の算出に使用したデータの不確信度を算出し、前記算出された設備健全度及び前記算出された不確信度に基づいて点検順序を決定する点検順序決定部とを有することを特徴とする設備保守点検支援システム。     The equipment maintenance inspection support system according to claim 1,
    The arithmetic unit is
    A data processing unit for associating the collected environmental data and equipment data with each other and processing the data for analysis,
    A VHI calculation model creation unit that creates a model for calculating the facility soundness from the processed analysis data;
    A VHI calculator that calculates equipment soundness from the analysis data using the created model;
    Calculating an uncertain degree of the data used to calculate the equipment soundness, and having an inspection order determining unit that determines an inspection order based on the calculated equipment soundness and the calculated uncertainty. Characteristic equipment maintenance inspection support system.
  4. 　請求項３に記載の設備保守点検支援システムであって、
    　前記ＶＨＩ算出モデル作成部は、前記作成されたモデルを用いて算出される設備健全度への、前記モデルに特徴量として入力される各データの寄与の大きさを表す重要度を算出することを特徴とする設備保守点検支援システム。     The equipment maintenance and inspection support system according to claim 3,
    The VHI calculation model creation unit calculates a degree of importance that represents a size of contribution of each data input as a feature amount to the model to the equipment soundness calculated using the created model. Characteristic equipment maintenance inspection support system.
  5. 　請求項４に記載の設備保守点検支援システムであって、
    　前記点検順序決定部は、
    　前記算出された設備健全度が悪い設備を上位の点検順序に並べ替える第１並べ替え処理と、
    　前記不確信度を算出する不確信度算出処理と、
    　前記算出された不確信度に基づいて、設備の点検順序を並べ替える第２並べ替え処理と、
    　将来の設備健全度を算出する将来ＶＨＩ算出処理と、
    　前記算出された将来の設備健全度に基づいて、設備の点検順序を並べ替える第３並べ替え処理とを実行することを特徴とする設備保守点検支援システム。     The equipment maintenance inspection support system according to claim 4,
    The inspection order determination unit,
    A first rearrangement process for rearranging the facilities with the calculated poor equipment health into a higher inspection order;
    An uncertainty calculation process for calculating the uncertainty,
    A second rearrangement process for rearranging the inspection order of the equipment based on the calculated uncertainty.
    Future VHI calculation processing for calculating future facility soundness,
    A facility maintenance and inspection support system, which executes a third rearrangement process for rearranging the facility inspection order based on the calculated future facility soundness.
  6. 　請求項５に記載の設備保守点検支援システムであって、
    　前記点検順序決定部は、前記不確信度算出処理において、前記モデルに入力される各データの品質及び前記算出された重要度に基づいて、前記不確信度を算出することを特徴とする設備保守点検支援システム。     The equipment maintenance inspection support system according to claim 5,
    The facility maintenance, wherein the inspection order determination unit calculates the uncertainty in the uncertainty calculation process based on the quality of each data input to the model and the calculated importance. Inspection support system.
  7. 　請求項６に記載の設備保守点検支援システムであって、
    　前記点検順序決定部は、前記不確信度算出処理において、前記環境データに含まれる観測値の重要度に基づいて前記不確信度を算出することを特徴とする設備保守点検支援システム。     The equipment maintenance inspection support system according to claim 6,
    The facility maintenance and inspection support system, wherein the inspection order determination unit calculates the uncertainty in the uncertainty calculation process based on the importance of an observed value included in the environmental data.
  8. 　請求項６に記載の設備保守点検支援システムであって、
    　前記環境データは、データを観測した観測局の位置情報を含み、
    　前記点検順序決定部は、前記不確信度算出処理において、
    　前記設備データに含まれる前記設備の位置情報及び前記環境データに含まれる前記観測局の位置情報を用いて、当該観測局と当該設備との距離を算出し、
    　前記算出された距離に基づいて前記不確信度を算出することを特徴とする設備保守点検支援システム。     The equipment maintenance inspection support system according to claim 6,
    The environmental data includes position information of the observation station that observed the data,
    The inspection order determination unit, in the uncertainty calculation process,
    Using the location information of the equipment included in the equipment data and the location information of the observation station included in the environmental data, calculate the distance between the observation station and the equipment,
    An equipment maintenance and inspection support system, wherein the degree of uncertainty is calculated based on the calculated distance.
  9. 　請求項６に記載の設備保守点検支援システムであって、
    　前記点検順序決定部は、前記不確信度算出処理において、前記設備データに含まれる点検日時に基づいて前記データの品質を算出することを特徴とする設備保守点検支援システム。     The equipment maintenance inspection support system according to claim 6,
    The facility maintenance and inspection support system, wherein the inspection order determination unit calculates the quality of the data based on the inspection date and time included in the facility data in the uncertainty calculation process.
  10. 　請求項５に記載の設備保守点検支援システムであって、
    　前記点検順序決定部は、前記第２並べ替え処理において、
    　所定の順序に並べられた設備をセグメントに分割し、
    　前記分割された各セグメント内で、前記算出された不確信度に基づいて設備の点検順序を並べ替えることを特徴とする設備保守点検支援システム。     The equipment maintenance inspection support system according to claim 5,
    The inspection order determination unit, in the second rearrangement process,
    Divide the equipment arranged in a predetermined order into segments,
    An equipment maintenance and inspection support system, wherein the equipment inspection order is rearranged in each of the divided segments based on the calculated uncertainty.
  11. 　請求項５に記載の設備保守点検支援システムであって、
    　前記点検順序決定部は、前記将来ＶＨＩ算出処理において、
    　現在から所定の保全周期が終了するまでの各年の環境データを作成し、
    　現在から前記保全周期が終了するまでの各年の設備データを作成し、
    　前記作成された各年の環境データ及び前記作成された各年の設備データを用いて将来の設備健全度を算出し、
      前記算出された将来の設備健全度に基づいて点検予定年を設定することを特徴とする設備保守点検支援システム。     The equipment maintenance inspection support system according to claim 5,
    The inspection order determination unit, in the future VHI calculation process,
    Create environmental data for each year from the present until the end of the prescribed maintenance cycle,
    Create equipment data for each year from the present to the end of the maintenance cycle,
    Calculate future facility soundness using the created environmental data of each year and the created facility data of each year,
    An equipment maintenance and inspection support system, characterized in that a scheduled inspection year is set based on the calculated future equipment soundness.
  12. 　請求項５に記載の設備保守点検支援システムであって、
    　前記点検順序決定部は、前記第３並べ替え処理において、
    　一年に点検実施可能な設備数に基づいて前記設備の点検予定年を設定し、
    　各設備について前記算出された現在の設備健全度と前記算出された点検予定年の設備健全度との差を算出し、
    　所定の順序に並べられた設備をセグメントに分割し、
    　前記設備健全度の差が所定の閾値より大きい設備を前記セグメント内の上位に並べ替え、
    　前記各セグメントにおける設備健全度の平均を算出し、
    　設備が所属するセグメントの点検予定年の設備健全度の平均値が設備点検予定年の設備健全度に最も近いかを判定し、
    　設備が所属するセグメントの点検予定年のＶＨＩ平均値が設備点検予定年のＶＨＩに最も近いものではない場合、平均値が最も近いセグメントの点検予定年に設備の点検予定年を更新し、セグメント内で設備健全度が悪い順に設備を並べ替えることを特徴とする設備保守点検支援システム。     The equipment maintenance inspection support system according to claim 5,
    The inspection order determination unit, in the third rearrangement process,
    Set the scheduled year of inspection of the equipment based on the number of equipment that can be inspected in one year,
    Calculate the difference between the calculated current equipment soundness for each piece of equipment and the calculated equipment soundness for the planned inspection year,
    Divide the equipment arranged in a predetermined order into segments,
    Sorting the equipment in which the difference in the equipment soundness is larger than a predetermined threshold value to a higher rank in the segment,
    Calculate the average equipment health in each segment,
    Determine whether the average value of the facility soundness of the scheduled inspection year of the segment to which the facility belongs is closest to the facility soundness of the planned facility inspection year,
    If the VHI average value of the scheduled inspection year of the segment to which the equipment belongs is not the closest to the VHI of the planned equipment inspection year, update the scheduled inspection year of the equipment to the scheduled inspection year of the segment with the closest average value, and then An equipment maintenance and inspection support system that sorts equipment in order of poor equipment health.
  13. 　請求項１に記載の設備保守点検支援システムであって、
    　前記出力部は、
    　前記点検順序を決定する前後において、設備の点検時期ごとの設備健全度の平均値を示すグラフと、
    　前記点検順序を決定した後の点検順序のリストとを表示する画面データを出力することを特徴とする設備保守点検支援システム。     The equipment maintenance inspection support system according to claim 1,
    The output unit is
    Before and after determining the inspection order, a graph showing the average value of the equipment soundness for each inspection time of the equipment,
    A facility maintenance and inspection support system, which outputs screen data displaying a list of inspection sequences after the inspection sequence is determined.
  14. 　計算機が設備の保守業務における点検順序を決定する設備保守点検支援方法であって、
    　前記計算機は、
    　所定の処理を実行する演算装置と、前記演算装置に接続された記憶デバイスと、前記演算装置に接続された通信インターフェースとを有し、
    　前記設備保守点検支援方法は、
    　前記演算装置が、点検順序を決定するための条件を受け付ける入力手順と、
    　前記演算装置が、設備が設置されている環境に関する環境データと、点検対象の設備の情報及び点検結果を含む設備データを収集するデータ収集手順と、
    　前記演算装置が、前記収集されたデータに基づいて現在及び将来の設備健全度を算出し、前記設備健全度の算出に使用したデータの不確信度を算出し、前記算出された設備健全度及び前記算出された不確信度に基づいて点検順序を決定する演算手順と、
    　前記演算装置が、決定された点検順序の結果及び前記決定した点検順序による改善状況を表示する出力手順とを含むことを特徴とする設備保守点検支援方法。
          A facility maintenance inspection support method in which a computer determines an inspection sequence in facility maintenance work,
    The calculator is
    An arithmetic unit for executing a predetermined process, a storage device connected to the arithmetic unit, and a communication interface connected to the arithmetic unit,
    The equipment maintenance inspection support method is
    An input procedure in which the arithmetic unit receives a condition for determining an inspection sequence,
    A data collection procedure in which the computing device collects environment data relating to the environment in which the equipment is installed, and equipment data including information of the equipment to be inspected and inspection results,
    The computing device calculates current and future equipment soundness based on the collected data, calculates the uncertainty of the data used to calculate the equipment soundness, and the calculated equipment soundness and A calculation procedure for determining an inspection order based on the calculated uncertainty.
    The facility maintenance and inspection support method, wherein the arithmetic unit includes an output procedure for displaying a result of the determined inspection order and an improvement situation according to the determined inspection order.
PCT/JP2018/043037 2018-11-21 2018-11-21 Facility maintenance inspection assisting system and order of inspection determination method WO2020105151A1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/JP2018/043037 WO2020105151A1 (en) 2018-11-21 2018-11-21 Facility maintenance inspection assisting system and order of inspection determination method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2018/043037 WO2020105151A1 (en) 2018-11-21 2018-11-21 Facility maintenance inspection assisting system and order of inspection determination method

Publications (1)

Publication Number Publication Date
WO2020105151A1 true WO2020105151A1 (en) 2020-05-28

Family

ID=70774709

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2018/043037 WO2020105151A1 (en) 2018-11-21 2018-11-21 Facility maintenance inspection assisting system and order of inspection determination method

Country Status (1)

Country Link
WO (1) WO2020105151A1 (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2022107240A1 (en) * 2020-11-18 2022-05-27 日本電信電話株式会社 Deterioration estimation device, deterioration estimation method, and program

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2002304213A (en) * 2001-04-06 2002-10-18 Kansai Electric Power Co Inc:The Equipment deterioration rate estimating system
JP2010073121A (en) * 2008-09-22 2010-04-02 Hitachi Plant Technologies Ltd Repair work schedule preparation method and repair work schedule preparation system for plant equipment
JP2010097392A (en) * 2008-10-16 2010-04-30 Chugoku Electric Power Co Inc:The Facility deterioration prediction system and facility deterioration prediction method
US20140156225A1 (en) * 2012-11-19 2014-06-05 Abb Technology Ag Assessment of power system equipment for equipment maintenance and/or risk mitigation
JP2014529795A (en) * 2011-08-22 2014-11-13 ローベルト ボッシュ ゲゼルシャフト ミット ベシュレンクテル ハフツング How to create control unit functions
JP2015010927A (en) * 2013-06-28 2015-01-19 Kddi株式会社 Observation value processing device, observation value processing method, and observation value processing program
JP2016224539A (en) * 2015-05-27 2016-12-28 日本電信電話株式会社 Management method and management apparatus
JP2017002537A (en) * 2015-06-09 2017-01-05 株式会社東芝 Device and method for providing road inspection information
JP2018010523A (en) * 2016-07-14 2018-01-18 株式会社日立製作所 Facility maintenance schedule creation system and facility maintenance schedule creating method

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2002304213A (en) * 2001-04-06 2002-10-18 Kansai Electric Power Co Inc:The Equipment deterioration rate estimating system
JP2010073121A (en) * 2008-09-22 2010-04-02 Hitachi Plant Technologies Ltd Repair work schedule preparation method and repair work schedule preparation system for plant equipment
JP2010097392A (en) * 2008-10-16 2010-04-30 Chugoku Electric Power Co Inc:The Facility deterioration prediction system and facility deterioration prediction method
JP2014529795A (en) * 2011-08-22 2014-11-13 ローベルト ボッシュ ゲゼルシャフト ミット ベシュレンクテル ハフツング How to create control unit functions
US20140156225A1 (en) * 2012-11-19 2014-06-05 Abb Technology Ag Assessment of power system equipment for equipment maintenance and/or risk mitigation
JP2015010927A (en) * 2013-06-28 2015-01-19 Kddi株式会社 Observation value processing device, observation value processing method, and observation value processing program
JP2016224539A (en) * 2015-05-27 2016-12-28 日本電信電話株式会社 Management method and management apparatus
JP2017002537A (en) * 2015-06-09 2017-01-05 株式会社東芝 Device and method for providing road inspection information
JP2018010523A (en) * 2016-07-14 2018-01-18 株式会社日立製作所 Facility maintenance schedule creation system and facility maintenance schedule creating method

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
KITAYAMA, MASASHI: "Asset management for social infrastructure facilities", SYSTEMS, CONTROL AND INFORMATION, vol. 51, no. 7, 15 July 2007 (2007-07-15), pages 8 - 13, XP009521325, DOI: 10.11509/isciesci.51.7_300 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2022107240A1 (en) * 2020-11-18 2022-05-27 日本電信電話株式会社 Deterioration estimation device, deterioration estimation method, and program

Similar Documents

Publication Publication Date Title
CN108375715B (en) Power distribution network line fault risk day prediction method and system
CN109543906B (en) Atmospheric visibility prediction method and equipment
CN107194139B (en) Atmospheric pollution source grading method and computing equipment
CN106321368B (en) Marine wind electric field wake losses measurement method based on operation blower SCADA data
CN111143932A (en) Bridge health state assessment method, device, system and equipment
KR101827908B1 (en) Ocean weather analysis device and method using thereof
CN104182594A (en) Method for drawing power system wind area graph
CN113779760B (en) Power-statistics combined season climate prediction method based on predictable climate mode
CN105488316A (en) Air quality prediction system and method
WO2019225064A1 (en) Weather prediction device, weather prediction method, and wind-power-generation output estimation device
Perkins et al. CMIP3 ensemble climate projections over the western tropical Pacific based on model skill
Guan et al. Development of verification methodology for extreme weather forecasts
CN110097205A (en) A kind of building load prediction weather forecast data preprocessing method
Lucio-Eceiza et al. Quality control of surface wind observations in northeastern North America. Part II: Measurement errors
JP2020134300A (en) Prediction method, prediction program and information processing apparatus
TWI546762B (en) Wind power generation equipment of the stress estimation device and wind power equipment, the stress estimation method, wind power generation system
Georgieva et al. Evaluating the performance of WRF-CMAQ air quality modelling system in Bulgaria by means of the DELTA tool
CN113516406B (en) High-speed rail line rainfall measurement point arrangement method based on real-time observation and analysis
WO2020105151A1 (en) Facility maintenance inspection assisting system and order of inspection determination method
JP2005121474A (en) Apparatus for analyzing index distribution of atmospheric substance
Bean et al. Predicting Utah ground snow loads with PRISM
CN117172554A (en) Icing disaster risk prediction method, device, equipment and storage medium
CN102236746A (en) Wind resource simulated estimation method for region without wind measurement records
CN112345972A (en) Power failure event-based power distribution network line transformation relation abnormity diagnosis method, device and system
Bannayan et al. Predicting realizations of daily weather data for climate forecasts using the non‐parametric nearest‐neighbour re‐sampling technique

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18940979

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18940979

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: JP