CN108083044B - Elevator on-demand maintenance system and method based on big data analysis - Google Patents
Elevator on-demand maintenance system and method based on big data analysis Download PDFInfo
- Publication number
- CN108083044B CN108083044B CN201711168356.6A CN201711168356A CN108083044B CN 108083044 B CN108083044 B CN 108083044B CN 201711168356 A CN201711168356 A CN 201711168356A CN 108083044 B CN108083044 B CN 108083044B
- Authority
- CN
- China
- Prior art keywords
- data
- elevator
- maintenance
- analysis
- fault
- 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.)
- Active
Links
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
- B66B5/00—Applications of checking, fault-correcting, or safety devices in elevators
- B66B5/0087—Devices facilitating maintenance, repair or inspection tasks
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
- B66B5/00—Applications of checking, fault-correcting, or safety devices in elevators
- B66B5/0006—Monitoring devices or performance analysers
- B66B5/0018—Devices monitoring the operating condition of the elevator system
- B66B5/0025—Devices monitoring the operating condition of the elevator system for maintenance or repair
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/22—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06Q10/20—Administration of product repair or maintenance
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Engineering & Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Databases & Information Systems (AREA)
- Quality & Reliability (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Indicating And Signalling Devices For Elevators (AREA)
- Maintenance And Inspection Apparatuses For Elevators (AREA)
Abstract
The invention provides an elevator maintenance system on demand based on big data analysis, which comprises a data source, a data access module and a data processing module, wherein the data access module acquires data from the data source, analyzes and distributes the data, and the data processing module receives the data distributed by the data access module, stores, models and analyzes the data; the data access module comprises a data analysis unit, a data cleaning unit and a data distribution unit. The invention further provides an elevator maintenance-on-demand method based on the big data analysis. According to the elevator maintenance method, elevator data related to maintenance and protection and elevator safe operation fault data acquired by the Internet of things equipment are utilized, and the fault condition in the daily use process of the elevator, the online condition of the Internet of things equipment and the like are combined, so that a daily maintenance mode of Internet of things and maintenance is implemented according to the elevator safe operation risk requirement, a quantitative index mathematical model of maintenance of the elevator according to risk and condition is established, and data support is provided for maintenance and protection innovation.
Description
Technical Field
The invention relates to the technical field of elevator maintenance, in particular to a model and a system for analyzing and predicting maintenance requirements based on big data of an elevator internet of things.
Background
In recent years, the domestic economy is suddenly and fiercely advanced, a city enters a rapid construction period of a high-rise building, an elevator is also developed in a blowout mode as an important vertical transportation means for the entrance and exit of the high-rise building, meanwhile, with the high-speed increase of the number of the elevators, the market demand of elevator maintenance is high, the phenomena of man-machine mismatching, vicious competition, unreal and bad maintenance work occur in the traditional maintenance mode, and great threats are generated on the safety and reliability of elevator maintenance.
At present, there are also researches on elevator maintenance, for example, chinese patent application CN201410609531.0, which discloses a method for calculating elevator maintenance time, and the elevator maintenance time is planned by a half-month protection calculation mode or a combination of annual protection, half-year protection, quarterly protection and half-month protection.
The technical scheme has the following defects: the elevator maintenance plan is arranged mainly by means of unified time calculation, the management is extensive, fine management cannot be performed on a single elevator, and the phenomenon that resources are arranged for maintenance and the occupied maintenance and protection resources are very short due to the fact that the elevator has good running condition and is good in quality or is used infrequently is caused; the elevator safety risk is high, early warning cannot be timely made, a fault may occur before a conventional maintenance plan arrives, and meanwhile, due to extensive management of maintenance resources, the elevator with high fault risk cannot acquire enough maintenance resources.
Disclosure of Invention
The invention provides an elevator maintenance-on-demand system based on big data analysis, which is used for collecting a large amount of elevator operation parameter data based on an internet of things data collection technology, combining elevator historical maintenance data and fault data, using a big data technology analysis technology to realize elevator maintenance prediction, and adjusting a traditional maintenance-on-time mode into an elevator operation risk and operation state maintenance-on-demand mode.
Therefore, the invention adopts the following technical scheme: an elevator maintenance system on demand based on big data analysis comprises a data source, a data access module and a data processing module, wherein the data access module acquires data from the data source, analyzes and distributes the data, and the data processing module receives the data distributed by the data access module, stores, models and analyzes the data; the data in the data source comprises elevator basic data, elevator operation data, elevator fault data and elevator maintenance data; the data access module comprises a data analysis unit, a data cleaning unit and a data distribution unit, wherein the data analysis unit acquires relevant data from a data source, the relevant data is sent to the data cleaning unit after being analyzed, and the data cleaned by the data cleaning unit is sent to the data processing module by the data distribution unit for corresponding processing.
Further, in the data source, the elevator basic data comprises an elevator brand, an elevator model and an elevator commissioning date, the elevator operation data comprises an elevator operation speed, an elevator operation temperature, an elevator operation frequency and an elevator vibration amplitude, the elevator fault data comprises an elevator fault type and a fault occurrence time, and the elevator maintenance data comprises an elevator maintenance date and maintenance condition feedback.
Furthermore, in the data access module, the data analysis unit realizes data access collection management according to a unified communication protocol and a unified data standard through a unified data transmission inlet, the data cleaning unit defines a cleaning rule to filter dirty data and realize preliminary data quality management, and the data distribution unit sends the accessed and cleaned data to the data processing module for storage and analysis.
Furthermore, in the data processing module, a data storage unit stores mass data for analysis and use, a data modeling unit establishes an elevator fault prediction model through analysis of historical data and can perform self-learning of the model, and a prediction analysis unit accesses relevant data of elevator operation within a certain time, substitutes the data into the model for calculation and outputs an elevator maintenance estimated date.
The invention also provides an elevator maintenance-on-demand method based on big data analysis, which adopts the system and comprises two processes of real-time online early warning analysis and offline maintenance date evaluation, wherein the offline maintenance date evaluation is based on the result of the real-time online early warning analysis or the intermediate result, the real-time online early warning analysis gives an alarm aiming at the emergency and informs the maintainers of carrying out maintenance inspection, and the method specifically comprises the following steps:
a1, data preparation: accessing elevator operation data in real time, pulling historical data of normal operation of the elevator in a certain period of time before, collecting data items including elevator operation speed, elevator operation acceleration, elevator car temperature and elevator vibration amplitude, and inputting the collected data items into an outlier detection model according to the brand and model of the elevator in a classified manner;
a2, early warning detection: carrying out risk prediction by introducing the analyzed data into a fault risk early warning model through analyzing local outliers generated by comparing real-time data with historical data, and outputting a risk coefficient through calculation by the fault risk early warning model;
a3, data storage: respectively storing the data into an outlier database according to whether the data belong to outliers, storing the data belonging to the outliers into the outlier database, and storing the data not belonging to the outliers into a non-outlier database;
the offline maintenance date evaluation is used for maintenance reminding before a fault occurs, and the method specifically comprises the following steps:
b1, obtaining elevator fault data, and obtaining an average value of maintenance interval periods according to requirements according to the interval periods of average fault occurrence of the elevator brand and model statistics;
b2, counting the average value of the elevator running risk coefficients obtained by the real-time online early warning analysis process in the interval period of a near period of time, and sequencing from high to low;
and B3, according to the magnitude of the risk coefficient, on the basis of maintaining the interval period mean value as required, combining the maintenance resource to prolong or shorten the maintenance period for a single elevator, wherein the elevator with a high risk coefficient suitably shortens the maintenance period, and the elevator with a low risk coefficient suitably prolongs the maintenance period.
Further, the early warning detection in step a2 further includes confirmation of a risk coefficient, specifically: after the risk coefficients are output by the fault risk prediction model, the prediction analysis unit obtains implementation risk coefficients within 5 minutes, the real-time risk coefficients are subjected to mean processing, and if the mean of the real-time risk coefficients is larger than a threshold value, fault early warning is output.
Further, in the early warning detection step of step a2, the local outlier detection model based on density compares the real-time data with the historical data to obtain an outlier database, and the local outlier detection model based on density describes the degree of separation between the data sample and other samples by using various statistical, distance, and density quantization indexes through a local anomaly factor algorithm, so as to determine the degree of abnormality of the data and distinguish outliers from non-outliers.
Further, the specific algorithm of the failure risk prediction model in step a2 is:
(1.1) carrying out weighted average calculation on the local outlier factors of the elevator running speed, the elevator running acceleration, the elevator running temperature and the vibration amplitude according to the formula 1;
in the formula 1, the compound is shown in the specification,
wherein x1.. cndot, xn is an observation variable, w1... wn is a weight value;
observed variables x1.. times, xn are calculated from a density-based local outlier detection model;
(1.2) acquiring a time point of failure through elevator failure data;
(1.3) acquiring data within 1 hour before the time point from the cluster database;
and (1.4) carrying out proportion analysis on the data within 1 hour to obtain the corresponding data item weight.
Further, the threshold value compared with the real-time risk coefficient is obtained by a risk coefficient threshold value measurement model, and the specific algorithm of the risk coefficient threshold value measurement model is as follows:
(2.1) acquiring a time point of failure through elevator failure data;
(2.2) obtaining data 1 hour before the time point from the outlier database and the non-outlier database;
(2.3) bringing the obtained data into a fault analysis and prediction model to obtain fault risk coefficients within 5 minutes before the fault occurs, and taking the minimum value of the coefficients as a risk threshold value;
and (2.4) correcting and optimizing the threshold value through continuous fault detection.
The invention has the beneficial effects that: according to the elevator maintenance method, the elevator data related to maintenance and protection collected by the equipment of the Internet of things and the elevator safe operation fault data are utilized, and the daily maintenance mode of the Internet of things and maintenance is implemented according to the elevator safe operation risk requirement by combining the fault condition in the daily use process of the elevator, the online condition of the equipment of the Internet of things and the like, namely, for the elevator with high safety performance and low fault analysis, equipment inspection and maintenance are carried out by elevator manufacturing enterprises through remote monitoring, and the found fault is timely repaired, maintenance personnel are timely arranged by a maintenance company to go to the door for maintenance and protection aiming at the elevator with low safety performance and high fault risk, maintenance based on time and projects is converted into maintenance based on the equipment condition or based on the risk, a quantitative index mathematical model for maintenance of the elevator according to the risk and the condition is preliminarily established, and data support is provided for the maintenance and reform.
Drawings
FIG. 1 is a system block diagram of the present invention.
Fig. 2 is a flow chart of a real-time analysis early warning process.
FIG. 3 is a schematic diagram of a local outlier detection model.
FIG. 4 is a flow chart of offline maintenance date evaluation.
Detailed Description
The following detailed description of the embodiments of the present invention is provided with reference to the accompanying drawings, and it should be noted that the examples are only for the purpose of clearly illustrating the technical solutions of the present invention, and are not intended to limit the present invention.
Embodiment 1, an elevator on-demand maintenance system based on big data analysis.
As shown in fig. 1, the data access module obtains data from a data source, analyzes and distributes the data, and the data processing module receives the data distributed by the data access module, stores, models and analyzes the data; the data in the data source comprises elevator basic data, elevator operation data, elevator fault data and elevator maintenance data; the data access module comprises a data analysis unit, a data cleaning unit and a data distribution unit, wherein the data analysis unit acquires relevant data from a data source, the relevant data is sent to the data cleaning unit after being analyzed, and the data cleaned by the data cleaning unit is sent to the data processing module by the data distribution unit for corresponding processing.
In the data source, the elevator basic data comprises an elevator brand, an elevator model and an elevator commissioning date, the elevator operation data comprises an elevator operation speed, an elevator operation temperature, an elevator operation frequency and an elevator vibration amplitude, the elevator fault data comprises an elevator fault type and a fault occurrence time, and the elevator maintenance data comprises an elevator maintenance date and maintenance condition feedback.
In the data access module, a data analysis unit realizes data access collection management according to a unified communication protocol and a unified data standard through a unified data transmission inlet, a data cleaning unit defines a cleaning rule, dirty data are filtered, preliminary data quality management is realized, and a data distribution unit sends the accessed and cleaned data to a data processing module for storage and analysis.
In the data processing module, a data storage unit stores mass data for analysis and use, a data modeling unit establishes an elevator fault prediction model through analysis of historical data and can perform self-learning of the model, and a prediction analysis unit accesses relevant data of elevator operation within a certain time, substitutes the relevant data into the model for calculation and outputs an elevator maintenance prediction date.
Embodiment 2, an elevator maintenance on demand method based on big data analysis.
As shown in fig. 2, the method of this embodiment is based on the system of embodiment 1, and includes two core processes, one of which is a real-time online early warning analysis process, performs anomaly detection on real-time accessed operation data and historical data, focuses on and alarms the anomaly data, and the operation and maintenance unit goes to the site to perform maintenance and inspection after receiving the alarm; the second process is an off-line maintenance date evaluation process, a mathematical formula is established according to elevator fault data, maintenance data and elevator operation data, and dates required for maintenance of a single elevator are evaluated, and the two processes are respectively explained below.
And (I) carrying out real-time online early warning analysis process.
The real-time analysis early warning process mainly aims at the sudden abnormal situation, gives an alarm in time, arranges maintenance personnel for maintenance and inspection, and prevents accidents in the past, and a specific processing flow chart is shown in the following figure 2.
The real-time analysis early-warning process mainly comprises three major stages, namely, a data preparation stage in which steps 1.1 to 1.4 identified in fig. 2 belong, a fault early-warning detection stage in which steps 2.1 to 2.6 belong, and a data storage stage in which steps 3.1 to 3.4 belong.
Specifically, in the data preparation phase, data are mainly prepared for subsequent model analysis, including elevator running state data accessed in real time and pulling historical data of normal running of the elevator in the last 1 hour (pulled from a non-cluster database). The data items comprise elevator running speed, running acceleration data, car temperature data and vibration amplitude data, and the data are input into the density-based outlier detection model in an elevator brand and model classification mode after being collected.
The outlier detection model based on the density mainly utilizes various statistical, distance and density quantization indexes to describe the separation degree of a data sample and other samples, and further judges the abnormal degree of the data, as shown in fig. 3, the overall distance, the density and the dispersion condition of points of a C1 set are uniform and consistent through visual and intuitive feeling, and the points can be considered as a same cluster; for the points in the C2 set, which can also be considered as a cluster, the points o1 and o2 are relatively isolated, and are the outliers or discrete points that we want to analyze. The Outlier detection model based on the density realizes the identification of the outliers of a set with different density dispersion situations, such as C1 and C2, through a Local Outlier Factor algorithm (LOF), the algorithm is general and efficient, and the method can adapt to the identification of abnormal state data of elevator operation.
Lof the algorithm is formulated as follows:LOFk(p)=∑o∈Nk(p)lrdk(o)lrdk(p)|Nk(p)|=∑o∈Nk(p) lrdk(o)|Nk(p)|/lrdk(p)
lof the algorithm outputs the local outlier factor for P points by the formula (LOFk(p)) If, ifLOFk(p)The closer to 1, the more the density of the neighborhood points of p is, the more the p possibly belongs to the same cluster with the neighborhood; if the ratio is less than 1, the density of p is higher than that of the neighborhood points, and p is a dense point; if this ratio is greater than 1, it indicates that the density of p is less than its neighborhood point density, and p is more likely to be an outlier.
The LOF algorithm is mature in various programming languages such as java and python, the invention only utilizes the mature algorithm, so detailed algorithm derivation is not needed, and it is a conventional technical means for a person skilled in the art to know the algorithm and be capable of utilizing the algorithm to carry out derivation.
In the fault early warning detection stage, local outliers generated by comparing real-time data with historical data are analyzed, the analyzed data are brought into a fault risk early warning model to carry out risk prediction, and the model outputs a risk coefficient through calculation. The single high-risk event may be caused by some factors such as error data, the fault risk cannot be directly confirmed, and the accurate judgment can be made only when the high-risk event occurs for a certain period of time, so that the real-time data risk coefficient of the latest 5 minutes needs to be obtained, the mean value of the real-time data risk coefficient needs to be processed, and if the mean value is greater than a threshold value (obtained by calculation of a risk coefficient threshold value measurement model), fault early warning is output.
The fault risk prediction model mainly obtains an overall data outlier coefficient through a weighted average algorithm of local outlier factors of the elevator running speed, the elevator running acceleration, the elevator temperature and the elevator vibration amplitude, the overall data outlier coefficient is called a risk coefficient, and whether to send an alarm or not is determined by the size of the risk coefficient. The weighting formula is as follows:
where x1, … …, xn are observed variables and w1, … …, wn are weight values. The formula is brought into a fault risk prediction model, wherein four x are respectively an elevator running speed local outlier factor x1, a running acceleration local outlier factor x2, a temperature local outlier factor x3, a vibration amplitude outlier factor x4 and four weighted values are also present, and the four x are respectively an elevator running speed local outlier factor accounting for a risk coefficient weight w1, an elevator running acceleration local outlier factor accounting for a risk coefficient weight w2, a temperature local outlier factor accounting for a risk coefficient weight w3 and a vibration amplitude local outlier factor accounting for a risk coefficient weight w 4.
In the formula x1... x4 is calculated by a "density-based local outlier detection model", and the weight needs to be obtained by correlation analysis for historical fault conditions, which is specifically performed as follows:
(1) and acquiring the time point of the fault through the elevator fault data.
(2) Data from the "outlier database" was obtained 1 hour prior to this time point.
(3) And (3) carrying out proportion analysis on the data to obtain the weight of the corresponding data item, wherein if the total number of the elevator running speed outlier data accounts for 15% of the total number of the outlier data, the elevator running speed local outlier factor accounts for 0.15 of the weight w1 of the risk coefficient.
The risk coefficient threshold value measuring and calculating model outputs risk coefficients through off-line analysis, is a set of model for learning evidences through historical fault data, and comprises the following specific implementation steps:
(1) and acquiring the time point of the fault through the elevator fault data.
(2) The data 1 hour before this time point is obtained from the "outlier database" and the "non-outlier database".
(3) And substituting the obtained data into a fault analysis and prediction model to obtain fault risk coefficients 5 minutes before the fault occurs, and taking the minimum value of the coefficients as a risk threshold.
(4) And subsequently, the threshold value is adjusted and optimized through continuously detecting the fault early warning accuracy.
And (II) performing an offline maintenance date evaluation process.
The real-time prior analysis early warning process is mainly used for solving maintenance reminding before sudden failure, but normalized maintenance work (estimating the maintenance period according to the maintenance date by the model) still needs to be carried out, on one hand, the real-time prior analysis early warning process is used for collecting more maintenance and elevator failure data for model learning and optimization, on the other hand, the real-time analysis early warning process also solves the maintenance check of a scene which is not covered by the real-time analysis early warning process, a new failure scene or a data rule discovered in the normal maintenance process is continuously optimized into the real-time analysis early warning process, the normal maintenance can be analyzed off line according to the obtained data, and the specific process is shown in fig. 4.
(1) And obtaining elevator fault data, and counting the average fault occurrence interval period according to the brand and the model of the elevator to be used as an average value of maintenance interval periods according to requirements.
(2) And counting the average value of the elevator running risk coefficients in the nearest interval period, and carrying out sequencing operation from high to low.
(3) Aiming at a single elevator, based on the risk coefficient and on the basis of maintaining the interval period mean value as required, the maintenance resource is combined to prolong or shorten the period, the elevator with high risk coefficient properly shortens the maintenance period, and the elevator with low risk coefficient properly prolongs the maintenance period.
Claims (5)
1. A maintenance method of an elevator according to needs based on big data analysis is characterized in that the method applies an elevator maintenance system according to needs based on big data analysis, the system comprises a data source, a data access module and a data processing module, the data access module obtains data from the data source and analyzes and distributes the data, and the data processing module receives the data distributed by the data access module and stores, models and analyzes the data; the data in the data source comprises elevator basic data, elevator operation data, elevator fault data and elevator maintenance data; the data access module comprises a data analysis unit, a data cleaning unit and a data distribution unit, wherein the data analysis unit acquires relevant data from a data source, the relevant data is transmitted to the data cleaning unit after being analyzed, and the data cleaned by the data cleaning unit is transmitted to the data processing module by the data distribution unit for corresponding processing; respectively storing the data into an outlier database or a non-outlier database according to whether the data belong to outlier data, storing the data belonging to the outlier into the outlier database, and storing the data not belonging to the outlier into the non-outlier database; in the data source, the elevator basic data comprises an elevator brand, an elevator model and an elevator commissioning date, the elevator operation data comprises an elevator operation speed, an elevator operation temperature, an elevator operation frequency and an elevator vibration amplitude, the elevator fault data comprises an elevator fault type and a fault occurrence time, and the elevator maintenance data comprises an elevator maintenance date and maintenance condition feedback; in the data access module, a data analysis unit realizes data access collection management according to a unified communication protocol and a unified data standard through a unified data transmission inlet, a data cleaning unit defines a cleaning rule, dirty data are filtered, preliminary data quality management is realized, and a data distribution unit sends the accessed and cleaned data to a data processing module for storage and analysis; in the data processing module, a data storage unit stores mass data for analysis and use, a data modeling unit establishes an elevator fault prediction model through analysis of historical data and can perform self-learning of the model, and a prediction analysis unit is accessed into relevant data of elevator operation within a certain time, substituted into the model for calculation and outputs an elevator maintenance estimated date;
the method comprises two processes of real-time online early warning analysis and offline maintenance date evaluation, wherein the offline maintenance date evaluation is based on the result or the intermediate result of the real-time online early warning analysis, the real-time online early warning analysis gives an alarm aiming at the emergency situation and informs a maintainer of maintenance inspection, and the method specifically comprises the following steps of:
a1, data preparation: accessing elevator operation data in real time, pulling historical data of normal operation of the elevator in a certain period of time before, collecting data items including elevator operation speed, elevator operation acceleration, elevator car temperature and elevator vibration amplitude, and inputting the collected data items into an outlier detection model according to the brand and model of the elevator in a classified manner;
a2, early warning detection: carrying out risk prediction by introducing the analyzed data into a fault risk early warning model through analyzing local outliers generated by comparing real-time data with historical data, and outputting a risk coefficient through calculation by the fault risk early warning model;
a3, data storage: respectively storing the data into an outlier database and a non-outlier database according to whether the data belong to outlier data, storing the data belonging to the outlier into the outlier database, and storing the data not belonging to the outlier into the non-outlier database;
the off-line maintenance date evaluation is used for maintenance reminding before a fault occurs, and specifically comprises the following steps
The method comprises the following steps:
b1, obtaining elevator fault data, and obtaining an average value of maintenance interval periods according to requirements according to the interval periods of average fault occurrence of the elevator brand and model statistics;
b2, counting the average value of the elevator running risk coefficients obtained by the real-time online early warning analysis process in the interval period of a near period of time, and sequencing from high to low;
and B3, according to the magnitude of the risk coefficient, on the basis of maintaining the interval period mean value as required, combining the maintenance resource to prolong or shorten the maintenance period for a single elevator, wherein the elevator with a high risk coefficient suitably shortens the maintenance period, and the elevator with a low risk coefficient suitably prolongs the maintenance period.
2. The on-demand maintenance method for the elevator based on the big data analysis as claimed in claim 1, wherein the early warning detection in the step a2 further comprises the confirmation of risk factors, specifically: after the risk coefficients are output by the fault risk prediction model, the prediction analysis unit obtains implementation risk coefficients within 5 minutes, the real-time risk coefficients are subjected to mean processing, and if the mean of the real-time risk coefficients is larger than a threshold value, fault early warning is output.
3. The on-demand maintenance method for the elevator based on the big data analysis as claimed in claim 2, wherein in the early warning detection step of step a2, the real-time data and the historical data are compared by a local outlier detection model based on density to obtain an outlier database, and the local outlier detection model based on density describes the degree of separation between the data sample and other samples by various statistical, distance and density quantization indexes through a local abnormal factor algorithm, so as to determine the abnormal degree of the data and distinguish the outliers from the non-outliers.
4. The on-demand maintenance method for the elevator based on the big data analysis as claimed in claim 3, wherein the specific algorithm of the failure risk prediction model in the step A2 is as follows:
(1.1) carrying out weighted average calculation on the local outlier factors of the elevator running speed, the elevator running acceleration, the elevator running temperature and the vibration amplitude according to the formula 1;
in the formula 1, the compound is shown in the specification,
wherein x1.. cndot, xn is an observation variable, w1... wn is a weight value;
an observation variable x1,.. times, xn is calculated from a density-based local outlier detection model
To;
(1.2) acquiring a time point of failure through elevator failure data;
(1.3) acquiring data within 1 hour before the time point from the cluster database;
and (1.4) carrying out proportion analysis on the data within 1 hour to obtain the corresponding data item weight.
5. The elevator maintenance-on-demand method based on big data analysis as claimed in claim 3, wherein the threshold value compared with the real-time risk coefficient is obtained by a risk coefficient threshold value calculation model, and the specific algorithm of the risk coefficient threshold value calculation model is as follows:
(2.1) acquiring a time point of failure through elevator failure data;
(2.2) obtaining data 1 hour before the time point from the outlier database and the non-outlier database;
(2.3) bringing the obtained data into a fault analysis and prediction model to obtain fault risk coefficients within 5 minutes before the fault occurs, and taking the minimum value of the coefficients as a risk threshold value;
and (2.4) correcting and optimizing the threshold value through continuous fault detection.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711168356.6A CN108083044B (en) | 2017-11-21 | 2017-11-21 | Elevator on-demand maintenance system and method based on big data analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711168356.6A CN108083044B (en) | 2017-11-21 | 2017-11-21 | Elevator on-demand maintenance system and method based on big data analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108083044A CN108083044A (en) | 2018-05-29 |
| CN108083044B true CN108083044B (en) | 2019-12-24 |
Family
ID=62172854
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711168356.6A Active CN108083044B (en) | 2017-11-21 | 2017-11-21 | Elevator on-demand maintenance system and method based on big data analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108083044B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022195335A1 (en) * | 2021-03-19 | 2022-09-22 | Killakathu Ramanathan Babu | System and method for controlling multidirectional operation of an elevator |
Families Citing this family (40)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108584598B (en) * | 2018-03-16 | 2020-09-15 | 广州市金度信息科技有限公司 | Elevator fault automatic analysis and early warning method, storage medium and intelligent terminal |
| SG11202012606TA (en) | 2018-07-19 | 2021-02-25 | Inventio Ag | Method and device for monitoring a state of a passenger transport system using a digital double |
| CA3105141A1 (en) * | 2018-07-19 | 2020-01-23 | Inventio Ag | Method and device for monitoring a passenger transport system using a detection device and a digital double |
| CN109165818B (en) * | 2018-08-02 | 2022-02-08 | 国网湖北省电力有限公司电力科学研究院 | Negative point calculation method for risk assessment of electrical equipment |
| CN110817628A (en) * | 2018-08-08 | 2020-02-21 | 北京感瞰科技有限公司 | Intelligent fault diagnosis method, device and system for elevator |
| CN109110608A (en) * | 2018-10-25 | 2019-01-01 | 歌拉瑞电梯股份有限公司 | A kind of elevator faults prediction technique based on big data study |
| CN109896384B (en) * | 2019-02-26 | 2021-09-28 | 北京市特种设备检测中心 | Traction elevator health state characteristic parameter extraction method based on big data analysis |
| CN110077928A (en) * | 2019-04-13 | 2019-08-02 | 浙江城际特种设备检测有限公司 | A kind of method of elevator detection |
| US11993480B2 (en) | 2019-04-30 | 2024-05-28 | Otis Elevator Company | Elevator shaft distributed health level with mechanic feed back condition based monitoring |
| CN110155840B (en) * | 2019-05-22 | 2021-05-14 | 安徽奥里奥克科技股份有限公司 | Elevator data acquisition management system |
| CN110271929A (en) * | 2019-06-14 | 2019-09-24 | 山东科技大学 | A kind of city elevator maintenance QA system based on big data driving |
| CN110436291B (en) * | 2019-07-03 | 2020-12-15 | 北京中铁电梯工程有限公司 | Maintenance system for real-time operation of elevator |
| CN110371815B (en) * | 2019-07-04 | 2021-02-26 | 安徽中科福瑞科技有限公司 | Elevator maintenance system on demand based on Internet of things |
| CN112633617A (en) * | 2019-09-24 | 2021-04-09 | 北京国双科技有限公司 | Maintenance strategy generation method and device, computer equipment and readable storage medium |
| US11993488B2 (en) | 2019-09-27 | 2024-05-28 | Otis Elevator Company | Processing service requests in a conveyance system |
| CN110687851A (en) * | 2019-10-31 | 2020-01-14 | 广东安可云科技有限公司 | Terminal operation monitoring system and method |
| CN110844731A (en) * | 2019-11-15 | 2020-02-28 | 上海市特种设备监督检验技术研究院 | Elevator function safety real-time monitoring system and method |
| CN111027934A (en) * | 2019-12-10 | 2020-04-17 | 深圳市通用互联科技有限责任公司 | Elevator maintenance task data processing method and device, computer equipment and storage medium |
| CN111243250B (en) * | 2019-12-25 | 2022-05-27 | 东软集团股份有限公司 | Maintenance early warning method, device and equipment based on alarm data |
| CN111392539B (en) * | 2020-03-25 | 2021-08-20 | 虏克电梯有限公司 | Elevator fault early warning device |
| CN111240306A (en) * | 2020-04-26 | 2020-06-05 | 南京市产品质量监督检验院 | Self-adaptive distribution transformer fault diagnosis system and diagnosis method thereof |
| CN111252641A (en) * | 2020-04-28 | 2020-06-09 | 广东梯云科技有限公司 | Elevator maintenance-on-demand intelligent management system and management method thereof |
| CN111611546B (en) * | 2020-05-18 | 2023-06-20 | 南京市特种设备安全监督检验研究院 | Elevator on-demand maintenance work quality evaluation method based on Internet of things data extraction and calculation |
| CN111559680A (en) * | 2020-05-25 | 2020-08-21 | 陕西省特种设备检验检测研究院 | Elevator intelligent inspection method based on big data |
| CN111874775A (en) * | 2020-06-12 | 2020-11-03 | 朱凯 | Elevator safety monitoring system based on big data |
| CN111717753A (en) * | 2020-06-29 | 2020-09-29 | 浙江新再灵科技股份有限公司 | Self-adaptive elevator fault early warning system and method based on multi-dimensional fault characteristics |
| CN111994749A (en) * | 2020-08-14 | 2020-11-27 | 揭阳市聆讯软件有限公司 | Elevator intelligent supervision and on-demand maintenance system and method based on PHM technology |
| CN114314228A (en) * | 2020-09-29 | 2022-04-12 | 思维实创(哈尔滨)科技有限公司 | Calculation method of elevator maintenance period model based on big data |
| CN112390105B (en) * | 2020-10-28 | 2022-09-16 | 日立楼宇技术（广州）有限公司 | Elevator operation detection method and device, computer equipment and storage medium |
| CN112811275B (en) * | 2020-12-30 | 2022-05-20 | 重庆厚齐科技有限公司 | Elevator maintenance-on-demand period measuring and calculating system and method based on Internet of things |
| CN112830357B (en) * | 2020-12-30 | 2022-05-17 | 重庆厚齐科技有限公司 | System and method for measuring and calculating elevator health value based on Internet of things and big data |
| CN112830358B (en) * | 2020-12-30 | 2022-05-20 | 重庆厚齐科技有限公司 | System and method for predicting elevator maintenance cycle on demand by machine learning |
| CN112777442A (en) * | 2021-02-03 | 2021-05-11 | 浙江新再灵科技股份有限公司 | Elevator safety region risk prediction method based on Internet of things big data |
| CN113071966A (en) * | 2021-04-26 | 2021-07-06 | 平安国际智慧城市科技股份有限公司 | Elevator fault prediction method, device, equipment and storage medium |
| CN113233275B (en) * | 2021-04-27 | 2022-07-29 | 重庆青云电梯安装工程有限公司 | Automatic matching system for target elevator and scattered maintenance personnel |
| CN113213296B (en) * | 2021-04-27 | 2022-07-29 | 重庆青云电梯安装工程有限公司 | Automatic matching method for target elevator and scattered maintenance personnel |
| CN115001943B (en) * | 2022-05-27 | 2024-03-22 | 深圳小湃科技有限公司 | Equipment fault identification method, equipment and storage medium based on big data |
| CN114671314B (en) * | 2022-05-30 | 2022-08-16 | 凯尔菱电（山东）电梯有限公司 | Safety monitoring method for elevator |
| CN115231410A (en) * | 2022-07-22 | 2022-10-25 | 成都市旭永升机电设备有限公司 | Elevator periodic maintenance, monitoring and management cloud system based on intellectualization |
| CN115258867A (en) * | 2022-08-12 | 2022-11-01 | 杭州电子科技大学 | Elevator maintenance system and method according to needs |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102923538A (en) * | 2012-07-06 | 2013-02-13 | 天津大学 | Elevator health management and maintenance system based on Internet of things and collection and assessment method |
| CN104973475A (en) * | 2015-05-19 | 2015-10-14 | 绍兴市特种设备检测院 | Method for monitoring elevator quality safety index |
| CN105712140A (en) * | 2014-12-05 | 2016-06-29 | 华夏视清数字技术(北京)有限公司 | Monitoring and early-warning device and method |
| CN105731209A (en) * | 2016-03-17 | 2016-07-06 | 天津大学 | Intelligent prediction, diagnosis and maintenance method for elevator faults on basis of Internet of Things |
| CN106144819A (en) * | 2016-07-19 | 2016-11-23 | 广州日滨科技发展有限公司 | The pre-diagnostic method of elevator and device |
| CN106672733A (en) * | 2016-12-02 | 2017-05-17 | 常州大学 | Elevator failure analysis and early warning system based on micro-cloud intelligent terminal and method thereof |
| CN107037062A (en) * | 2017-05-17 | 2017-08-11 | 中天射频电缆有限公司 | Coaxial cable material microwave property is monitored on-line and diagnostic device and method |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102289585B (en) * | 2011-08-15 | 2014-06-18 | 重庆大学 | Real-time monitoring method for energy consumption of public building based on data mining |
| CN102360378A (en) * | 2011-10-10 | 2012-02-22 | 南京大学 | Outlier detection method for time-series data |
| CN104135074B (en) * | 2014-07-31 | 2016-02-17 | 上海交通大学 | Based on the Ultra-high Voltage Substations device temperature monitoring alarm method of outlier detection |
| CN104462819A (en) * | 2014-12-09 | 2015-03-25 | 国网四川省电力公司信息通信公司 | Local outlier detection method based on density clustering |
-
2017
- 2017-11-21 CN CN201711168356.6A patent/CN108083044B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102923538A (en) * | 2012-07-06 | 2013-02-13 | 天津大学 | Elevator health management and maintenance system based on Internet of things and collection and assessment method |
| CN105712140A (en) * | 2014-12-05 | 2016-06-29 | 华夏视清数字技术(北京)有限公司 | Monitoring and early-warning device and method |
| CN104973475A (en) * | 2015-05-19 | 2015-10-14 | 绍兴市特种设备检测院 | Method for monitoring elevator quality safety index |
| CN105731209A (en) * | 2016-03-17 | 2016-07-06 | 天津大学 | Intelligent prediction, diagnosis and maintenance method for elevator faults on basis of Internet of Things |
| CN106144819A (en) * | 2016-07-19 | 2016-11-23 | 广州日滨科技发展有限公司 | The pre-diagnostic method of elevator and device |
| CN106672733A (en) * | 2016-12-02 | 2017-05-17 | 常州大学 | Elevator failure analysis and early warning system based on micro-cloud intelligent terminal and method thereof |
| CN107037062A (en) * | 2017-05-17 | 2017-08-11 | 中天射频电缆有限公司 | Coaxial cable material microwave property is monitored on-line and diagnostic device and method |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022195335A1 (en) * | 2021-03-19 | 2022-09-22 | Killakathu Ramanathan Babu | System and method for controlling multidirectional operation of an elevator |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108083044A (en) | 2018-05-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108083044B (en) | Elevator on-demand maintenance system and method based on big data analysis | |
| CN113255795B (en) | Equipment state monitoring method based on multi-index cluster analysis | |
| CN103793854B (en) | The overhead transmission line operation risk informatization evaluation method that Multiple Combination is optimized | |
| CN109544399B (en) | Power transmission equipment state evaluation method and device based on multi-source heterogeneous data | |
| CN109491339B (en) | Big data-based substation equipment running state early warning system | |
| CN105930629B (en) | A kind of on-line fault diagnosis method based on magnanimity service data | |
| CN111444169A (en) | Transformer substation electrical equipment state monitoring and diagnosis system and method | |
| CN113036913B (en) | Method and device for monitoring state of comprehensive energy equipment | |
| CN112884325A (en) | Method and system for application analysis and health condition evaluation of customer station equipment | |
| CN109711664B (en) | Power transmission and transformation equipment health assessment system based on big data | |
| CN111080074B (en) | System service security situation element obtaining method based on network multi-feature association | |
| CN110209999A (en) | A kind of mobile unit failure trend prediction method | |
| CN106649755A (en) | Threshold self-adaption setting abnormity detection method for multi-dimensional real-time power transformation device data | |
| CN115650006B (en) | Elevator safety monitoring and early warning method and system based on big data | |
| CN113627735A (en) | Early warning method and system for safety risk of engineering construction project | |
| CN115511367B (en) | Intelligent quality management system of production line | |
| CN117689214A (en) | Dynamic safety assessment method for energy router of flexible direct-current traction power supply system | |
| CN116991130A (en) | Intelligent automatic control system and method for petrochemical production | |
| CN107239835A (en) | Build the method and system that oil gas ground produces different kinds of process flow differentiation grade O＆M | |
| CN115841739A (en) | Equipment management tracking method and system based on Internet of things | |
| CN111806516A (en) | Health management device and method for intelligent train monitoring and operation and maintenance | |
| CN103679547B (en) | Optimization method for missed steps of relay protection | |
| CN110989042A (en) | Intelligent prediction method for highway fog-clustering risk | |
| CN114912678A (en) | Online automatic detection and early warning method and system for abnormal operation of power grid regulation and control | |
| CN106325258B (en) | Relay protection device state evaluation method based on online monitoring information |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20180529 Assignee: Jiangsu xinzailing Intelligent Technology Co., Ltd Assignor: ZHEJIANG XINZAILING TECHNOLOGY Co.,Ltd. Contract record no.: X2020980000583 Denomination of invention: Elevator as-required maintenance system and method based on big data analysis Granted publication date: 20191224 License type: Common License Record date: 20200311 |
|
| EE01 | Entry into force of recordation of patent licensing contract | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A method of elevator maintenance system based on big data Effective date of registration: 20220419 Granted publication date: 20191224 Pledgee: CITIC Bank Limited by Share Ltd. Hangzhou Xiaoshan branch Pledgor: ZHEJIANG XINZAILING TECHNOLOGY Co.,Ltd. Registration number: Y2022330000551 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right |