CN115063048A - Intelligent management system for rail transit power supply operation and maintenance - Google Patents
Intelligent management system for rail transit power supply operation and maintenance Download PDFInfo
- Publication number
- CN115063048A CN115063048A CN202210977835.7A CN202210977835A CN115063048A CN 115063048 A CN115063048 A CN 115063048A CN 202210977835 A CN202210977835 A CN 202210977835A CN 115063048 A CN115063048 A CN 115063048A
- Authority
- CN
- China
- Prior art keywords
- management module
- management
- power supply
- equipment
- unit
- Prior art date
- Legal status (The legal status 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 status listed.)
- Pending
Links
- 238000012423 maintenance Methods 0.000 title claims abstract description 36
- 238000007726 management method Methods 0.000 claims description 153
- 238000012545 processing Methods 0.000 claims description 38
- 230000007547 defect Effects 0.000 claims description 27
- 238000012544 monitoring process Methods 0.000 claims description 25
- 238000013528 artificial neural network Methods 0.000 claims description 23
- 210000002569 neuron Anatomy 0.000 claims description 20
- 238000000034 method Methods 0.000 claims description 19
- 238000004364 calculation method Methods 0.000 claims description 11
- 238000009826 distribution Methods 0.000 claims description 10
- 230000006870 function Effects 0.000 claims description 10
- 238000007689 inspection Methods 0.000 claims description 7
- 230000006399 behavior Effects 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 claims description 4
- 230000005540 biological transmission Effects 0.000 claims description 3
- 238000013500 data storage Methods 0.000 claims description 3
- 238000011161 development Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 description 12
- 238000004422 calculation algorithm Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 5
- 238000010801 machine learning Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000003062 neural network model Methods 0.000 description 3
- 238000012550 audit Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 206010033799 Paralysis Diseases 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 238000013529 biological neural network Methods 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000013439 planning Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/40—Business processes related to the transportation industry
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Marketing (AREA)
- Software Systems (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Entrepreneurship & Innovation (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Primary Health Care (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Public Health (AREA)
- Molecular Biology (AREA)
- Medical Informatics (AREA)
- Computational Linguistics (AREA)
- Water Supply & Treatment (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Life Sciences & Earth Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Power Sources (AREA)
Abstract
The invention discloses an intelligent management system for power supply, operation and maintenance of rail transit, which comprises an equipment management module, a safety management module, a load management module and an intelligent decision module, wherein the equipment management module, the safety management module and the load management module are classified through the intelligent decision module, the priority of faults is decided after the fault grades fed back by the equipment management module, the safety management module and the load management module are combined with the self grades of the equipment management module, the safety management module and the load management module, then instructions are issued to operation and maintenance personnel in sequence according to the priority division, the management system carries out multi-end management on power supply equipment, information equipment software and information equipment hardware and issues the instructions in sequence according to the corresponding fault grades in the multi-end management, so that the fault with the highest risk is processed in priority, and the normal operation of the rail transit power supply system is ensured, and the operation risk of the rail transit power supply system is reduced.
Description
Technical Field
The invention relates to the technical field of power supply operation and maintenance management, in particular to an intelligent management system for rail transit power supply operation and maintenance.
Background
Urban rail transit is a vehicle transportation system which adopts a rail structure for bearing and guiding, and is a public transportation mode of conveying passenger flow of a considerable scale in a train or single vehicle mode by arranging a fully-closed or partially-closed special rail line according to the requirements of the overall planning of urban traffic.
The safe operation of the rail transit is not separated from a safe, standard and reliable power supply system, the power supply system is blood of rail transit transportation and is a core system, once the power supply system breaks down or is interrupted, the power supply system not only can cause paralysis of urban rail transit transportation, but also can endanger life safety of passengers, and brings huge pressure to ground wire public transport, thereby causing adverse effects on social stability and urban image.
The prior art has the following defects: when the existing rail transit power supply management system carries out multi-end management, the management system can only make a decision according to the sending time of a fault and then send an instruction, when the multi-end simultaneously breaks down, the fault with a large danger coefficient can be processed after the fault with a small danger coefficient, and the processing mode greatly improves the operation risk of the rail transit power supply system, so that the intelligent management system for rail transit power supply operation and maintenance is needed to solve the problems.
Disclosure of Invention
The invention aims to provide an intelligent management system for rail transit power supply operation and maintenance, which aims to solve the defects in the background technology.
In order to achieve the above purpose, the invention provides the following technical scheme: an intelligent management system for operation and maintenance of rail transit power supply comprises:
a device management module: the power supply equipment is used for overhauling, maintaining and managing the power supply equipment in an inspection way;
a safety management module: a device for recording and storing management information;
a load management module: the system comprises a data processing unit, a data processing unit and a data processing unit, wherein the data processing unit is used for acquiring and managing performance resource load data of an information device;
an intelligent decision module: the method comprises the steps of classifying an equipment management module, a safety management module and a load management module, combining fault grades fed back by the equipment management module, the safety management module and the load management module with the management module grades, deciding the priority of the fault, and issuing an instruction to operation and maintenance personnel according to the priority division.
Preferably, the intelligent decision module includes an intelligent processing unit, and the processing logic of the intelligent processing unit is:
(1) setting module security level as follows: the device management module is in a third level, the safety management module is in a second level, and the load management module is in a first level;
(2) classification of failure classes A, B, C, D, E, F;
and the priority of the management module self level is greater than the priority of the fault level.
Preferably, the equipment management module includes electric wire netting monitoring unit, maintenance unit, state management unit and patrols and examines the unit, and wherein, monitoring unit is used for monitoring power supply unit's current transmission information, and when patrolling and examining the unit and detecting that the periphery takes place the operation trouble inside and outside the power supply unit, do the maintenance processing to equipment by the maintenance unit, state management unit is used for the running state of management equipment to the information of storage equipment.
Preferably, the grid monitoring unit adopts a neural network for predicting the defects of the power supply equipment, and the neurons of the neural network are defined as:
in the above formula, the neuron NP is a multivariate function, and the operation result Mout is obtained by performing the operation through the input parameter Mi.
Preferably, the security management module includes a network protection unit, a network access management unit and an operation maintenance unit, the network protection unit is configured to perform protection processing on a network, the network access management unit gives a corresponding right to a user according to a network access key, and the operation maintenance unit ensures normal operation of the application.
Preferably, the network access management unit includes user management, authority management and log management, the user management performs access control on system users, the authority management defines different system resource access ranges for users with different authorities, and the log management records operation behaviors of all users of the system.
Preferably, the neuron calculation formula of the neural network is as follows:
in the above formula, parametersRespectively representing the operating voltage, current, duration, severity level of last defect, occurrence time and defect type of the device,weight parameter representing input value, weight parameterAnd the value range of the output value is [0,1]]The input parameters are processed by a normalization method, and the output result represents the probability value of the defect of the equipment.
Preferably, the hierarchical structure of the management system includes an infrastructure layer, a data layer, a platform layer, and a user layer, wherein the infrastructure layer includes system-implemented hardware devices; the data layer comprises various data information in system operation; the platform layer comprises various service processing logics of system users; the user layer comprises a client browser and interacts with each application of the system.
Preferably, the hardware device comprises a server, a data storage and network hardware; the data information comprises an operation library, a database, a distribution network professional graph and a basic database; the service processing logic comprises application development and a GIS graphical platform which completes distribution network graphic topology analysis and distribution network display.
Preferably, the load management module includes a core monitoring unit, a memory processing unit and a disk management unit, wherein the core monitoring unit is configured to monitor a load condition of a core processor of the information device, the memory processing unit monitors a remaining amount of a memory, and the disk management unit periodically cleans a disk.
Preferably, the network protection unit comprises a firewall, a role control and a permission assignment, wherein,
preferably, the firewall: in order to ensure the safety of the management information system, an independent application server and a database server are respectively established, the two servers are distributed in different network segments, and the existing risk data is rejected through a firewall;
preferably, the role controls: according to different requirements, access users are divided into two categories of ordinary users and administrators, so that when a system user accesses a database, strict role control measures are required to ensure that the access of database resources is limited;
preferably, the right assignment: the method comprises the steps of giving access limits of different system data resources according to different user roles, dividing different roles according to different functions of each user, giving different authorities according to the roles of the different roles, ensuring the one-to-one correspondence of the roles and the authorities, preventing potential risks that the authorities are changed when the roles are changed or the roles are not changed, setting validity periods for the authorities of the roles, automatically losing the authorities after the validity periods are exceeded, resetting, and ensuring the safety guarantee capability of a database through regular checking and dynamic control.
Preferably, the network access management unit includes user management, authority management and log management functions, the network access management unit performs access control on system users, defines different system resource access ranges for users with different authorities, simultaneously performs detailed record on operation behaviors of all users of the system, provides data basis for system security audit, verifies the legality of user identity, matches the user name and password input by the user with information in a database, if the user name and password are consistent with the information, the user can enter the system, otherwise, the system prompts login failure information, the resources which can be accessed by the users with different authorities after entering the system are different, and therefore, the viewed interfaces are also different
In the technical scheme, the invention provides the following technical effects and advantages:
1. the management system carries out multi-terminal management on the power supply equipment, the information equipment software and the information equipment hardware and sequentially issues instructions according to the corresponding fault grades in the multi-terminal management, so that the fault with the largest danger is processed preferentially, the normal operation of the rail transit power supply system is favorably ensured, and the operation risk of the rail transit power supply system is reduced;
2. the power grid monitoring unit of the invention is based on neural network neuron defect prediction algorithm, and respectively uses the operation voltage, current, duration, the severity level of the last defect, occurrence time and defect type of the input equipment to enable the output result to represent the probability value of the occurrence of the defect of the equipment.
Drawings
In order to more clearly illustrate the embodiments of the present application or technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments described in the present invention, and other drawings can be obtained by those skilled in the art according to the drawings.
FIG. 1 is a block diagram of a circuit of the present invention.
FIG. 2 is a system architecture diagram of the present invention.
Fig. 3 is a schematic diagram of a network topology according to the present invention.
FIG. 4 is a flow chart of role control and authority assignment in accordance with the present invention.
FIG. 5 is a flowchart illustrating a user login process according to the present invention.
FIG. 6 is a flowchart illustrating the operation and maintenance management of the device management module according to the present invention.
FIG. 7 is a diagram of an E-R data model of a database according to the present invention.
FIG. 8 is a schematic diagram of a neural network of the present invention.
FIG. 9 is a flow chart of a defect prediction algorithm of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It will be understood that when an element is referred to as being "secured to" another element, it can be directly on the other element or intervening elements may also be present. When an element is referred to as being "connected" to another element, it can be directly connected to the other element or intervening elements may also be present.
Example 1
Referring to fig. 1, the intelligent management system for rail transit power supply operation and maintenance in this embodiment includes an equipment management module, a security management module, a load management module and an intelligent decision module,
wherein,
the equipment management module carries out maintenance, maintenance and routing inspection management on the power supply equipment according to the daily service category;
the safety management module is used for recording and storing and managing the firewall state, the communication port state and the public network inbound traffic information of the information equipment;
the load management module acquires performance resource load data of each information device under an intranet environment through an SNMP protocol, and performs classified storage and visual display of load conditions according to load types;
the intelligent decision module grades the equipment management module, the safety management module and the load management module, after fault grades fed back by the equipment management module, the safety management module and the load management module are combined with the self grades of the equipment management module, the safety management module and the load management module, the priority of faults is decided, then, the faults are divided according to the priority, and instructions are sequentially issued to operation and maintenance personnel.
The load management module comprises a core monitoring unit, a memory processing unit and a disk management unit, wherein the core monitoring unit is used for monitoring the load condition of a core processor of the information equipment, the phenomenon that the core processor is overloaded and crashed is avoided, the memory processing unit monitors the residual amount of the memory, and the disk management unit regularly cleans the disk, so that the normal operation of the information equipment is guaranteed.
The intelligent decision module comprises an intelligent processing unit, and the processing logic of the intelligent processing unit is as follows: setting module security level as follows: the device management module is in a third level, the safety management module is in a second level, and the load management module is in a first level, wherein the more the number of levels is, the higher the level of the management module is;
dividing the fault grades into A, B, C, D, E, F, wherein the fault grades are low as the grades go backwards, namely A is more than B, more than C, more than D, more than E and more than F;
wherein, each level of the management module corresponds to three levels of fault, for example: if the equipment fault level monitored by the equipment management module is E, the fault level of the safety management module is B, and the fault level of the load management module is D, the priority sequence is as follows: the fault grade of the safety management module is greater than the fault grade of the equipment monitoring module and greater than the fault grade of the load management module;
if the equipment fault level monitored by the equipment management module is C and the fault level of the safety management module is A, the level of the management module is taken as the priority, namely the equipment fault level monitored by the equipment management module is greater than the fault level of the safety management module.
In the actual use process, the device management module is responsible for managing and monitoring the power supply device, the safety management module is responsible for managing and monitoring the operating software on the computer, and the load management module is responsible for managing and monitoring the data packet switching device (such as a switch).
Example 2
Referring to fig. 2, the management system is designed in a layered structure, and mainly includes an infrastructure layer, a data layer, a platform layer, and a user layer, where the infrastructure layer mainly covers hardware devices for system implementation and implementation, including devices such as a server, a data storage, and network hardware, which are basic parts for system implementation;
the data layer mainly covers various data information in the operation process of the system, mainly comprises information such as an operation library, a database, distribution network professional figures, a basic database and the like, and provides data support for the realization of the system;
the platform layer mainly covers various service processing logics of system users, such as application development and a GIS graphical platform for completing distribution network graphic topology analysis and distribution network display;
the user layer mainly interacts with each application of the system through a client browser, various data requests are initiated in the browser, and results are returned to the user through server processing and processing, and the user layer mainly covers user interaction behaviors.
Referring to fig. 3, the management system mainly operates in an internal lan, and meanwhile, needs of a user to log in from the outside are also considered, and an internal network (Web server cluster) and an external network (user cluster) of the system are isolated by using a firewall in a structural design of a network topology of the management system, so that the system is protected from being exposed to the external network, and security of the system is ensured.
The user client browser, the server application and the database are respectively deployed on different logic layers, data circulation is carried out through an internal operation mechanism, the user client browser mainly provides an interactive interface between a user and the system application, the user initiates various data requests through the browser, the data requests are analyzed, processed and processed through a server application program, a processing result is returned to the user, the processing result is displayed to the user in the form of a graph, a report form and the like on the browser, the system database is accessed and operated through middleware such as ODBC and the like, and reliable data support is provided for stable operation of the system.
Example 3
Referring to fig. 1, the device management module includes a power grid monitoring unit, an overhaul unit, a state management unit and an inspection unit, wherein the monitoring unit is configured to monitor current transmission information of the power supply device, when the inspection unit detects that an operation failure occurs on the periphery of the power supply device, the overhaul unit performs an overhaul process on the device, and the state management unit is configured to manage an operation state of the device and store information of the device;
referring to fig. 6, the device management module mainly records information of device type, device usage, and the like, and a manager can record all information of the device in a system in a detailed and classified manner, so as to facilitate rapid maintenance of the device.
Referring to fig. 7, according to the management content of the device management module, relationships between various types of data are effectively managed through a database design, so as to support better implementation of the device management module, in this embodiment, a database table mainly includes a manager information table and a power supply device information table, and the manager information table is as follows:
the administrator information table is the most basic data table of the system, and because a system administrator has special authority, the legality and uniqueness of the administrator information need to be ensured, the administrator information mainly comprises an administrator job number, a user name, a password and a real name, and meanwhile, the department and the position number of the administrator and the date registered in the system need to be recorded.
The power supply apparatus information table is as follows:
the electrical equipment information table is the table with the most quantity in the system, and the system needs to be input to each equipment information one by one, because the equipment is of a great variety and numerous, the key commonality information needs to be extracted from each distribution network equipment, so that managers can carry out unified standard management to the equipment, and the electrical equipment information table mainly comprises: the system comprises key information such as equipment name numbers, equipment factory numbers, equipment manufacturing units, equipment models, rated voltages, currents, position information, installer information, running states and the like.
Example 4
Referring to fig. 1, the security management module includes a network protection unit, a network access management unit, and an operation maintenance unit, where the network protection unit is configured to perform protection processing on a network to prevent data leakage and data loss caused by hacking on the network, the network access management unit gives a corresponding right to a user according to a network access key, and the operation maintenance unit ensures normal operation of an application, mainly to prevent the application from being stuck or crashed;
the network protection unit includes a firewall, role control, and authority assignment, wherein,
(1) firewall: in order to ensure the safety of the management information system, an independent application server and a database server are respectively established, the two servers are distributed in different network segments, and the data with risks are rejected outside the network segments through a firewall;
referring to fig. 4, (2) role control: according to different requirements, access users are divided into two categories, namely ordinary users and administrators, so that when a system user accesses a database, strict role control measures are required to ensure that the access of database resources is limited;
please refer to fig. 4, (3) right assignment: the method comprises the steps of giving access limits of different system data resources according to different user roles, dividing different roles according to different functions of each user, giving different authorities according to the roles of the different roles, ensuring the one-to-one correspondence of the roles and the authorities, preventing potential risks that the authorities are changed when the roles are changed or the roles are not changed, setting validity periods for the authorities of the roles, automatically losing the authorities after the validity periods are exceeded, resetting, and ensuring the safety guarantee capability of a database through regular checking and dynamic control.
Referring to fig. 5, the network access management unit includes user management, authority management, and log management functions, and the network access management unit performs access control on a system user, defines different system resource access ranges for users with different authorities, and simultaneously performs detailed recording on operation behaviors of all users of the system, provides a data basis for system security audit, verifies the validity of a user identity, matches the user name and password input by the user with information in a database, if the user name and password are consistent with the information in the database, the user identity is successfully verified, the user can enter the system, otherwise, the system prompts login failure information, and the resources that users with different authorities can access after entering the system are different, so the viewed interfaces are also different.
Example 5
Referring to fig. 8, the grid monitoring unit employs a neural network for predicting the defects of the power supply device, the neural network defines a series of neuron objects to form a complex neural network, and performs self-learning by using a large amount of historical data in a manner similar to that of a biological neural network, and in this process, algorithm parameters are continuously adjusted to finally achieve a neural network model for practical application, wherein the neurons are defined as follows:
the neural network is an operation hierarchical structure composed of a large number of neurons, and comprises 1 input layer, a plurality of intermediate layers and 1 output layer.
The input layer is the original data directly used for calculation, the intermediate layer receives the calculation result of the neuron of the input layer, the input data of the output layer is obtained in a layer-by-layer calculation mode, and finally the calculation result of the neural network model is obtained according to the calculation result of the neuron of the output layer.
In this embodiment, the neuron calculation formula is as follows:
in the above formula, parametersRespectively representing the operating voltage, current, duration, severity level of last defect, occurrence time and defect type of the device,weight parameter representing input value, weight parameterAnd the value range of the output value is [0,1]]The input parameters are processed by a normalization method, and the output result represents the probability value of the defect of the equipment.
Referring to fig. 9, in the function F, the corresponding defect occurrence probability is obtained mainly according to the input device operation parameters, and then the number of the middle layers of the neural network is set to 5 (the same as the input data amount of the neurons) according to the neuron definition, and meanwhile, the number of the neurons in the input layers and the middle layers is set to 5 according to the number of the input data of the neurons, so as to obtain a neural network with a 5 × 5 structure.
The specific processing logic is as follows:
(1) defining a prediction error, wherein the error value is set to be 0.01 percent, namely 10000 pieces of equipment operation data are processed, and the maximum defect error quantity obtained by judgment can only appear for 1 time;
(2) the function corresponding to each neuron is initialized with input parameter values, the initialized specific numerical values adopt random numbers, namely, the random number calculation interface of the NET platform is adopted to obtain parameter values of 6 [0,1] intervals without considering specific analysis and prediction requirements, and the parameter values are dynamically checked and updated in the self-learning process of the neural network.
The neural network object adopts a corresponding 5 multiplied by 5 two-dimensional array for expression, the array elements are function references corresponding to the neural network object, the two-dimensional array is used for subsequent historical data analysis and learning processing, namely known historical data of defects of the power equipment are used as input signals for machine learning of the neural network, the quantity of the historical data is directly related to the accuracy and the availability of a calculation model obtained by final learning of the neural network, and generally, the larger the scale of the historical data is, the higher the accuracy of the obtained neural network model is;
in the actual use process, the number of the selected historical data is 10000, namely a calculation model of the neural network is obtained after 10000 times of simulation operation and machine learning;
in addition, in the subsequent application process, the weight parameters of the neuron object functions are continuously checked and updated according to the actual application condition of the neural network algorithm model.
In addition, in the neural network, the lower the preset model error value is, the larger the size of the history data required for machine learning is.
Meanwhile, the prediction error of the algorithm can be manually adjusted, so that the problem that the machine learning cannot be converged due to overhigh error condition setting or the final learning result cannot meet the actual application requirement due to loose error condition setting is avoided;
the power grid monitoring unit is based on a neural network neuron defect prediction algorithm, the operation voltage, the current, the duration, the severity level of the last defect, the occurrence time and the defect type of the input equipment are respectively used, so that the output result represents the probability value of the defect occurrence of the equipment, the power supply equipment in the power grid is monitored through the defect prediction algorithm, and the safety risk existing in the operation process of the power supply equipment is favorably reduced.
It is noted that, in this document, relational terms such as first and second, and the like, if any, are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. The utility model provides a track traffic power supply operation and maintenance uses intelligent management system which characterized in that includes:
a device management module: the power supply equipment is used for overhauling, maintaining and managing the power supply equipment in an inspection way;
a safety management module: a device for recording and storing management information;
a load management module: the system comprises a data processing unit, a data processing unit and a data processing unit, wherein the data processing unit is used for acquiring and managing performance resource load data of an information device;
an intelligent decision module: the method comprises the steps of classifying an equipment management module, a safety management module and a load management module, combining fault grades fed back by the equipment management module, the safety management module and the load management module with the management module grades, deciding the priority of the fault, and issuing an instruction to operation and maintenance personnel according to the priority division.
2. The intelligent management system for rail transit power supply operation and maintenance according to claim 1, wherein: the intelligent decision module comprises an intelligent processing unit, and the processing logic of the intelligent processing unit is as follows:
(1) setting module security level as follows: the device management module is in a third level, the safety management module is in a second level, and the load management module is in a first level;
(2) classification of failure classes A, B, C, D, E, F;
and the priority of the management module self level is greater than the priority of the fault level.
3. The intelligent management system for rail transit power supply operation and maintenance according to claim 1 or 2, characterized in that: the equipment management module comprises a power grid monitoring unit, an overhauling unit, a state management unit and an inspection unit, wherein the monitoring unit is used for monitoring current transmission information of the power supply equipment, when the inspection unit detects that the periphery of the power supply equipment has operation faults, the overhauling unit is used for overhauling the equipment, and the state management unit is used for managing the operation state of the equipment and storing the information of the equipment.
4. The intelligent management system for rail transit power supply operation and maintenance according to claim 3, wherein: the grid monitoring unit adopts a neural network for predicting the defects of the power supply equipment, and the neurons of the neural network are defined as follows:
in the above formula, the neuron NP is a multivariate function, and the operation result Mout is obtained by performing the operation through the input parameter Mi.
5. The intelligent management system for rail transit power supply operation and maintenance according to claim 1 or 2, characterized in that: the security management module comprises a network protection unit, a network access management unit and an operation maintenance unit, wherein the network protection unit is used for protecting the network, the network access management unit gives corresponding authority to a user according to a network access key, and the operation maintenance unit ensures normal operation of the application.
6. The intelligent management system for rail transit power supply operation and maintenance according to claim 5, wherein: the network access management unit comprises user management, authority management and log management, wherein the user management is used for carrying out access control on system users, the authority management is used for defining different system resource access ranges for users with different authorities, and the log management is used for recording operation behaviors of all users of the system.
7. The intelligent management system for rail transit power supply operation and maintenance according to claim 4, wherein: the neuron calculation formula of the neural network is as follows:
in the above formula, parametersRespectively representing the operating voltage, current, duration, severity level of last defect, occurrence time and defect type of the device,weight parameter representing input value, weight parameterAnd the value range of the output value is [0,1]]The input parameters are processed by a normalization method, and the output result represents the probability value of the defect of the equipment.
8. The intelligent management system for rail transit power supply operation and maintenance according to claim 1, wherein: the hierarchical structure of the management system comprises an infrastructure layer, a data layer, a platform layer and a user layer, wherein the infrastructure layer comprises hardware equipment for system implementation; the data layer comprises various data information in system operation; the platform layer comprises various service processing logics of system users; the user layer comprises a client browser and interacts with each application of the system.
9. The intelligent management system for rail transit power supply operation and maintenance according to claim 8, wherein: the hardware equipment comprises a server, a data storage and network hardware; the data information comprises an operation library, a database, a distribution network professional graph and a basic database; the service processing logic comprises application development and a GIS graphical platform which completes distribution network graphic topology analysis and distribution network display.
10. The intelligent management system for rail transit power supply operation and maintenance according to claim 9, wherein: the load management module comprises a core monitoring unit, a memory processing unit and a disk management unit, wherein the core monitoring unit is used for monitoring the load condition of a core processor of the information equipment, the memory processing unit monitors the residual amount of the memory, and the disk management unit regularly cleans the disk.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210977835.7A CN115063048A (en) | 2022-08-16 | 2022-08-16 | Intelligent management system for rail transit power supply operation and maintenance |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210977835.7A CN115063048A (en) | 2022-08-16 | 2022-08-16 | Intelligent management system for rail transit power supply operation and maintenance |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115063048A true CN115063048A (en) | 2022-09-16 |
Family
ID=83207857
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210977835.7A Pending CN115063048A (en) | 2022-08-16 | 2022-08-16 | Intelligent management system for rail transit power supply operation and maintenance |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115063048A (en) |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101110155A (en) * | 2007-08-27 | 2008-01-23 | 北京交通大学 | Built-in intelligent fault diagnosing device based on data inosculating pattern recognition and method thereof |
CN101209714A (en) * | 2006-12-28 | 2008-07-02 | 上海轨道交通设备发展有限公司 | Track traffic synthetic monitoring system and method |
CN101783578A (en) * | 2010-02-03 | 2010-07-21 | 北京奥福瑞科技有限公司 | Intelligent online detection optimizing management control method of high-frequency switch power supply and device thereof |
CN101789596A (en) * | 2009-01-22 | 2010-07-28 | 四川华雁信息产业股份有限公司 | Automatic detection method of power grid failure |
CN104409123A (en) * | 2014-11-15 | 2015-03-11 | 北京广利核***工程有限公司 | Priority management system of nuclear power plant |
CN104964387A (en) * | 2015-06-12 | 2015-10-07 | 石家庄国祥运输设备有限公司 | Method for recording and selecting fault information of rail transit vehicle air conditioning equipment |
CN109086889A (en) * | 2018-09-30 | 2018-12-25 | 广东电网有限责任公司 | Terminal fault diagnostic method neural network based, device and system |
CN109472381A (en) * | 2017-12-28 | 2019-03-15 | 国网浙江省电力公司嘉兴供电公司 | A kind of guarantor's electric equipment upkeep operation optimization method |
CN110675070A (en) * | 2019-09-26 | 2020-01-10 | 上海博辕信息技术服务有限公司 | Intelligent microgrid device criticality analysis method |
CN111382786A (en) * | 2020-03-04 | 2020-07-07 | 中国工商银行股份有限公司 | Fault processing method and device for equipment, computer system and storage medium |
CN113848417A (en) * | 2021-08-09 | 2021-12-28 | 上海应用技术大学 | Rail transit power supply equipment fault prediction method and device |
-
2022
- 2022-08-16 CN CN202210977835.7A patent/CN115063048A/en active Pending
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101209714A (en) * | 2006-12-28 | 2008-07-02 | 上海轨道交通设备发展有限公司 | Track traffic synthetic monitoring system and method |
CN101110155A (en) * | 2007-08-27 | 2008-01-23 | 北京交通大学 | Built-in intelligent fault diagnosing device based on data inosculating pattern recognition and method thereof |
CN101789596A (en) * | 2009-01-22 | 2010-07-28 | 四川华雁信息产业股份有限公司 | Automatic detection method of power grid failure |
CN101783578A (en) * | 2010-02-03 | 2010-07-21 | 北京奥福瑞科技有限公司 | Intelligent online detection optimizing management control method of high-frequency switch power supply and device thereof |
CN104409123A (en) * | 2014-11-15 | 2015-03-11 | 北京广利核***工程有限公司 | Priority management system of nuclear power plant |
CN104964387A (en) * | 2015-06-12 | 2015-10-07 | 石家庄国祥运输设备有限公司 | Method for recording and selecting fault information of rail transit vehicle air conditioning equipment |
CN109472381A (en) * | 2017-12-28 | 2019-03-15 | 国网浙江省电力公司嘉兴供电公司 | A kind of guarantor's electric equipment upkeep operation optimization method |
CN109086889A (en) * | 2018-09-30 | 2018-12-25 | 广东电网有限责任公司 | Terminal fault diagnostic method neural network based, device and system |
CN110675070A (en) * | 2019-09-26 | 2020-01-10 | 上海博辕信息技术服务有限公司 | Intelligent microgrid device criticality analysis method |
CN111382786A (en) * | 2020-03-04 | 2020-07-07 | 中国工商银行股份有限公司 | Fault processing method and device for equipment, computer system and storage medium |
CN113848417A (en) * | 2021-08-09 | 2021-12-28 | 上海应用技术大学 | Rail transit power supply equipment fault prediction method and device |
Non-Patent Citations (1)
Title |
---|
朱莉: "基于大数据云平台的智慧城市轨道交通运维管理一体化体系", 《百家论坛》 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11565734B2 (en) | Weak-current unified system for rail transit | |
CN112102111B (en) | Intelligent processing system for power plant data | |
CN106709580B (en) | Transformer substation secondary system operation and maintenance cloud platform | |
CN110717665B (en) | System and method for fault identification and trend analysis based on scheduling control system | |
CN114584405B (en) | Electric power terminal safety protection method and system | |
RU2583703C2 (en) | Malicious attack detection and analysis | |
CN107220775B (en) | Active power distribution network multi-view cooperative vulnerability assessment method considering information system effect | |
US20150286949A1 (en) | Problem analysis and priority determination based on fuzzy expert systems | |
CN106165345A (en) | Mark is for dissolving the failture evacuation option of network failure | |
CN105867347B (en) | Cross-space cascading fault detection method based on machine learning technology | |
CN107730647A (en) | A kind of smart mobile phone cruising inspection system and its method for inspecting based on SCADA | |
CN112291266B (en) | Data processing method, device, server and storage medium | |
CN112291264B (en) | Security control method, device, server and storage medium | |
CN111934954A (en) | Broadband detection method and device, electronic equipment and storage medium | |
CN115033450A (en) | Bayesian cluster monitoring early warning analysis method based on distribution | |
CN113301040B (en) | Firewall strategy optimization method, device, equipment and storage medium | |
CN115063048A (en) | Intelligent management system for rail transit power supply operation and maintenance | |
CN116149954A (en) | Intelligent operation and maintenance system and method for server | |
CN114997574A (en) | Power distribution station area elastic resource management method and device based on service middling station | |
CN114520763A (en) | Design method for overall architecture of intelligent comprehensive operation and maintenance system | |
CN113472068A (en) | Island microgrid remote operation and maintenance method, system and storage medium | |
Qiu et al. | Design Mechanism of Power Outage Perception Prediction Model Based on Big Data Technology | |
CN108566288A (en) | A kind of computer network cloud activation system | |
TWI789003B (en) | Service anomaly detection and alerting method, apparatus using the same, storage media for storing the same, and computer software program for generating service anomaly alert | |
Li et al. | Research and Design of Power Equipment Operation and Maintenance System Based on Big Data Technology |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220916 |
|
RJ01 | Rejection of invention patent application after publication |