A performance evaluation method and system based on duty record system for substation operation and maintenance

Through the multi-dimensional analysis of the duty record system for substation operation and maintenance and the application of deep learning models, the problem of inability to evaluate the performance of substation operation and maintenance team members in the existing technology is solved, and the scientific evaluation of substation operation and maintenance operations is realized. manage.

CN113487152BActive Publication Date: 2024-11-26STATE GRID SHANDONG ELECTRIC POWER CO JINING CITY RENCHENG DISTRICT POWER SUPPLY CO +2
View PDF 10 Cites 0 Cited by

Patent Information

Application Number
CN202110712906.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-06-25
Publication Date
2024-11-26
Estimated Expiration
2041-06-25

AI Technical Summary

Technical Problem

The existing technology cannot effectively evaluate the accident handling effect of substation operation and maintenance team members and whether the equipment inspection and inspection work meets the standards, and lacks performance evaluation methods for substation operation and maintenance operations.

Method used

By conducting multi-dimensional analysis of the data of the duty record system for substation operation and maintenance, and using a deep learning system to build a performance appraisal model, extract event-related information, calculate performance evaluation indicators, and perform performance appraisal of substation operation and maintenance team members.

Benefits of technology

It has achieved scientific evaluation of the performance of routine and unconventional matters of substation operation and maintenance team members, provided an operation and maintenance operation evaluation that is closer to reality, and improved the accuracy and effectiveness of operation and maintenance management.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113487152B_ABST
    Figure CN113487152B_ABST
Patent Text Reader

Abstract

The present invention discloses a performance appraisal method based on a duty record system for substation operation and maintenance. According to the industry characteristics of substation operation and maintenance operations, a multi-dimensional analysis is first performed on the data in the duty record system for substation operation and maintenance. Then, a deep learning system is used to construct a deep learning model. Through the use of the deep learning model, the performance appraisal status of routine matters and the performance appraisal status of unconventional matters of substation operation and maintenance team members in the month to be appraised are realized. In the deep learning model, the inspection of unconventional matters after the routine matters of the month to be appraised are used to reflect the processing effect of routine matters in the month to be appraised. The inspection of routine matters after the unconventional matters of the month to be appraised are used to reflect the processing effect of unconventional matters in the month to be appraised. The training effect of the deep learning model can be closer to the actual substation operation and maintenance operations.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of power systems, and in particular to a performance assessment method and system based on a duty record system for substation operation and maintenance. Background Art

[0002] Substation operation and maintenance is a term in the power industry, specifically referring to the operation and maintenance of substations. Based on the needs of operation and maintenance, switching operations, accident handling, equipment inspections and civilized production management of unmanned substations, combined with geographical location, power supply area and traffic conditions, substation operation and maintenance teams are set up to efficiently and reasonably manage substations with few or no personnel on duty.

[0003] At present, in patent CN207473653U, the evaluation system of substation operation and maintenance performance, which determines the position of the substation patrol personnel carrying the handheld terminal when collecting operation and maintenance information in real time through the positioning device connected to the handheld terminal, and then transmits the operation and maintenance information and positioning information to the substation operation and maintenance server of the patrol center through wireless communication equipment and wireless network for evaluation, so as to realize real-time dynamic evaluation of substation operation and maintenance performance. However, the evaluation system can only grasp the positioning information and working hours of the substation operation and maintenance team members, and has no evaluation means for the final effect of accident handling in the substation operation and maintenance operation. At the same time, there is no effective evaluation indicator for whether the inspection work of the substation operation and maintenance team members in the routine equipment inspection meets the standards. Summary of the invention

[0004] In view of the shortcomings of the prior art, the first purpose of the present invention is to provide a performance appraisal method based on a duty record system for substation operation and maintenance, wherein event-related information of substation maintenance team members is entered into the duty record system for substation operation and maintenance, and multi-dimensional analysis and element extraction are performed on the data of the duty record system for substation operation and maintenance, and then training is performed using a deep learning system to derive performance appraisal evaluation indicators based on the duty record system for substation operation and maintenance. The performance appraisal evaluation indicators are used to conduct performance appraisal on various substation operation and maintenance operations of the substation operation and maintenance team members.

[0005] The second purpose of the present invention is to provide a performance appraisal system based on the duty record system for substation operation and maintenance. The appraisal system uses a deep learning system to train the data of previous substation operation and maintenance duty record systems, and then uses the obtained performance appraisal evaluation indicators based on the substation operation and maintenance duty record system as evaluation indicators for the performance appraisal of the system.

[0006] In order to achieve the above object, the present invention adopts the following technical solution:

[0007] In a first aspect, the present invention provides a performance evaluation method based on a duty record system for substation operation and maintenance, comprising:

[0008] Extract data from the duty record system used for substation operation and maintenance;

[0009] Conduct multi-dimensional analysis on the extracted duty record system data for substation operation and maintenance;

[0010] Import the data after multi-dimensional analysis into the deep learning system, build a deep learning model, use the deep learning model for training, and then derive performance evaluation indicators based on the duty record system for substation operation and maintenance;

[0011] The performance appraisal evaluation indicators are used to conduct performance appraisal on various substation operation and maintenance tasks of the substation operation and maintenance team members.

[0012] The data extraction items include: the location of the incident, the event that occurred, the time point of the fault event alarm, the employee number of the substation operation and maintenance team member, the time point when the substation operation and maintenance team member arrived at the incident location, and the time point when the incident processing was completed.

[0013] The multi-dimensional analysis includes: dividing the data extracted from the duty record system for substation operation and maintenance into historical reference data, data to be assessed, evaluation data, and backup data according to time periods.

[0014] The multi-dimensional analysis also includes: dividing the historical reference data, data to be assessed, and evaluation data into historical routine matters data, historical non-routine matters data, routine matters data to be assessed, non-routine matters data to be assessed, evaluated routine matters data, and evaluated non-routine matters data according to matter categories.

[0015] The item categories are set as routine items based on the work characteristics of substation operation and maintenance, such as operation and maintenance, switching operations, equipment inspections, etc. that require regular operations, while various sudden accident handling and other temporary operations are set as non-routine items.

[0016] As a further technical solution, building a deep learning model includes:

[0017] (1) Develop performance evaluation indicators for routine matters based on the time when substation operation and maintenance team members arrive at the incident site, the time when the incident is handled, and the degree of completion of routine matters;

[0018] (2) referring to the performance evaluation indicators of routine items data and the performance evaluation indicators of non-routine items data, respectively calculate the performance evaluation indicator values ​​of historical routine items data, the performance evaluation indicator values ​​of historical non-routine items data, the performance evaluation indicator values ​​of routine items data to be assessed, the performance evaluation indicator values ​​of non-routine items data to be assessed, the performance evaluation indicator values ​​of routine items data for assessment, and the performance evaluation indicator values ​​of non-routine items data for assessment;

[0019] (3) using the performance evaluation index value of the historical routine item data and the performance evaluation index value of the evaluation non-routine item data to perform a weighted average calculation and obtain a first performance evaluation index value;

[0020] (4) comparing the first performance evaluation index value with the performance evaluation index value of the routine items data to be evaluated, and determining the routine items performance evaluation status of the substation operation and maintenance team members;

[0021] (5) using the performance evaluation index value of the historical non-routine items data and the performance evaluation index value of the evaluation routine items data to perform a weighted average calculation and obtain a second performance evaluation index value;

[0022] (6) Compare the second performance evaluation index value with the performance evaluation index value of the non-routine items to be evaluated to determine the non-routine items performance evaluation status of the substation operation and maintenance team members.

[0023] The performance appraisal status of routine matters and the performance appraisal status of non-routine matters of the substation operation and maintenance team members in the month to be assessed obtained in step (4) and step (6) are used to obtain the final performance appraisal status of the substation operation and maintenance team members in the month to be assessed through a weighted average algorithm.

[0024] In the second aspect, the present invention provides a performance appraisal system based on a duty record system for substation operation and maintenance, which is used for the performance appraisal method based on a duty record system for substation operation and maintenance described in this application, including, in order and layer by layer: a duty record system for substation operation and maintenance, a data analysis module, a deep learning system, and a performance appraisal module.

[0025] The substation operation and maintenance duty record system is used to provide relevant data for performance appraisal.

[0026] The data analysis module is used to perform multi-dimensional analysis on the relevant data provided by the duty record system for substation operation and maintenance.

[0027] The deep learning system is used to construct relevant performance appraisal evaluation indicators for data after multi-dimensional analysis.

[0028] The performance appraisal module conducts a final performance appraisal of the substation operation and maintenance team members in the month to be appraised based on the relevant performance appraisal evaluation indicators constructed by the deep learning system.

[0029] Beneficial effects of the present invention:

[0030] (1) The method described in the present invention does not adopt the technical solution of comparing employees in the conventional employee performance appraisal method. Instead, based on the industry characteristics of substation operation and maintenance operations, the method first performs a multi-dimensional analysis on the data in the substation operation and maintenance duty record system. Then, a deep learning system is used to construct a deep learning model. Through the use of the deep learning model, the performance appraisal status of routine matters and non-routine matters of the substation operation and maintenance team members in the month to be appraised is realized.

[0031] (2) In the deep learning model described in the present invention, the inspection of non-routine items after the routine items of the month to be assessed are used to reflect the processing effect of routine items in the month to be assessed; the inspection of routine items after the non-routine items of the month to be assessed are used to reflect the processing effect of non-routine items in the month to be assessed; so that the training effect of the deep learning model can be closer to the actual substation operation and maintenance operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The drawings in the specification, which constitute a part of the present application, are used to provide further understanding of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute improper limitations on the present application.

[0033] Figure 1 It is a schematic diagram of the process of multi-dimensional analysis of data in the duty record system for substation operation and maintenance in the embodiment described in the present application;

[0034] Figure 2 It is a structural diagram of the deep learning model in the embodiment described in this application. DETAILED DESCRIPTION

[0035] It should be noted that the following detailed descriptions are illustrative and are intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present application belongs.

[0036] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present application. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0037] Embodiment 1:

[0038] The present application is described in detail below with reference to the accompanying drawings and specific implementation methods:

[0039] like Figure 1-2 As shown, this embodiment provides a performance evaluation method based on a duty record system for substation operation and maintenance, including:

[0040] Extract data from the duty record system used for substation operation and maintenance.

[0041] The data extracted include: the location of the incident, what happened, the time of the fault event alarm, the employee number of the substation operation and maintenance team members, the time when the substation operation and maintenance team members arrived at the location of the incident, and the time when the incident was handled.

[0042] Conduct multi-dimensional analysis on the extracted duty record system data for substation operation and maintenance.

[0043] The data after multi-dimensional analysis is imported into the deep learning system to build a deep learning model, which is then trained to derive performance appraisal evaluation indicators based on the duty record system for substation operation and maintenance.

[0044] This performance appraisal evaluation indicator is used to conduct performance appraisal on various substation operation and maintenance tasks of substation operation and maintenance team members.

[0045] The multi-dimensional analysis includes:

[0046] 1: The data extracted from the duty record system for substation operation and maintenance is divided into historical reference data, data to be assessed, evaluation data, and backup data according to time periods.

[0047] In this embodiment, the month is used as a recording unit for the assessment period. Generally, the current time is used as the starting point, and the month two months ago is selected as the month to be assessed. The data of the month to be assessed is the data to be assessed, the data within two years before the month to be assessed is set as historical reference data, the data one month after the month to be assessed is the evaluation data, and the data in other stages are backup data.

[0048] 2: Based on the characteristics of substation operation and maintenance, the above-mentioned item categories set operations such as operation and maintenance, switching operations, equipment inspections, etc. that require regular operations as routine items, while various sudden accident handling and other temporary operations are set as non-routine items.

[0049] According to the classification of the above-mentioned matter categories, the historical reference data, data to be assessed, and evaluation data are divided into historical routine matter data, historical non-routine matter data, routine matter data to be assessed, non-routine matter data to be assessed, evaluated routine matter data, and evaluated non-routine matter data according to the matter categories.

[0050] Building a deep learning model involves:

[0051] 1: Develop performance evaluation indicators for routine matters data based on the time when substation operation and maintenance team members arrive at the incident site, the time when the incident is handled, and the completion rate of routine matters.

[0052] Performance evaluation indicators for non-routine event data are formulated based on the time point of fault event alarm, the time point when the substation operation and maintenance team members arrive at the event site, and the time point when the event is handled.

[0053] For ease of understanding, assuming that in the routine affairs data, based on the time when the substation operation and maintenance team members arrived at the incident site and the time when the incident was handled, we concluded that the average processing time for routine affairs was 3.5 hours, and among the 320 routine affairs that needed to be completed, only 316 were completed, then the completion rate of routine affairs is: 316÷320=0.9875.

[0054] The performance evaluation index of routine matters data is 3.5 / 0.9875.

[0055] 2: Referring to the performance evaluation indicators of routine matters data and the performance evaluation indicators of non-routine matters data, calculate the performance evaluation indicator values ​​of historical routine matters data, the performance evaluation indicator values ​​of historical non-routine matters data, the performance evaluation indicator values ​​of routine matters data to be assessed, the performance evaluation indicator values ​​of non-routine matters data to be assessed, the performance evaluation indicator values ​​of assessed routine matters data, and the performance evaluation indicator values ​​of assessed non-routine matters data respectively.

[0056] 3: In reality, the results of routine matters processing in the month to be evaluated need to be tested by subsequent non-routine matters to reflect the processing effect. Therefore, the performance evaluation index values ​​of historical routine matters data and the performance evaluation index values ​​of non-routine matters data are used for weighted average calculation to reflect the reasonable performance evaluation index values ​​of the routine matters data to be evaluated and obtain the first performance evaluation index value.

[0057] 4: Compare the first performance evaluation index value obtained after weighted average calculation with the performance evaluation index value of the routine matters data to be evaluated, and then judge the routine matters performance evaluation status of the substation operation and maintenance team members based on the comparison.

[0058] 5: In reality, the results of handling non-routine items in the month to be evaluated need to be tested by subsequent routine items to reflect the processing effect. Therefore, the performance evaluation index values ​​of historical non-routine item data and the performance evaluation index values ​​of routine item data are used for weighted average calculation to reflect the reasonable performance evaluation index values ​​of the non-routine item data to be evaluated and obtain the second performance evaluation index value.

[0059] 6: Compare the second performance evaluation index value obtained after weighted average calculation with the performance evaluation index value of the non-routine matters data to be evaluated, and then judge the non-routine matters performance evaluation status of the substation operation and maintenance team members based on the comparison.

[0060] Finally, by using the trained deep learning model and inputting the employee number of the substation operation and maintenance team member, the performance appraisal status of routine matters and non-routine matters of the substation operation and maintenance team member in the month to be assessed can be obtained. Through the weighted average algorithm, the final performance appraisal status of the substation operation and maintenance team member in the month to be assessed can be obtained.

[0061] Embodiment 2:

[0062] This embodiment provides a performance appraisal system based on a duty record system for substation operation and maintenance, which is used for the performance appraisal method based on a duty record system for substation operation and maintenance described in Example 1 of the present application, including, in order and layer by layer: a duty record system for substation operation and maintenance, a data analysis module, a deep learning system, and a performance appraisal module.

[0063] The substation operation and maintenance duty record system is used to provide relevant data for performance appraisal.

[0064] The data analysis module is used to perform multi-dimensional analysis on the relevant data provided by the duty record system for substation operation and maintenance.

[0065] The deep learning system is used to construct relevant performance appraisal evaluation indicators for data after multi-dimensional analysis.

[0066] The performance appraisal module conducts a final performance appraisal of the substation operation and maintenance team members in the month to be appraised based on the relevant performance appraisal evaluation indicators constructed by the deep learning system.

[0067] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A performance evaluation method based on a duty record system for substation operation and maintenance, characterized in that: include: Extract data from the duty record system used for substation operation and maintenance; Conduct multi-dimensional analysis on the extracted duty record system data for substation operation and maintenance; Import the data after multi-dimensional analysis into the deep learning system, build a deep learning model, use the deep learning model for training, and then derive performance evaluation indicators based on the duty record system for substation operation and maintenance; Using the performance appraisal evaluation indicators, the performance of each substation operation and maintenance task of the substation operation and maintenance team members is evaluated; The data extraction items include: the location of the incident, the event that occurred, the time of the fault event alarm, the employee number of the substation operation and maintenance team member, the time when the substation operation and maintenance team member arrived at the incident location, and the time when the incident processing was completed; The data extracted from the duty record system for substation operation and maintenance is divided into historical reference data, data to be assessed, evaluation data, and backup data according to time periods; The multi-dimensional analysis further includes: dividing the historical reference data, data to be assessed, and assessment data into historical routine matters data, historical non-routine matters data, routine matters data to be assessed, non-routine matters data to be assessed, assessment routine matters data, and assessment non-routine matters data according to the matters categories; It is characterized in that building a deep learning model includes: (1) According to the time when the substation operation and maintenance team members arrived at the incident site, the time when the incident was handled, and the completion rate of routine matters, formulate performance evaluation indicators for routine matters data; according to the time when the fault event alarm was triggered, the time when the substation operation and maintenance team members arrived at the incident site, and the time when the incident was handled; formulate performance evaluation indicators for non-routine matters data; (2) referring to the performance evaluation indicators of routine items data and the performance evaluation indicators of non-routine items data, respectively calculate the performance evaluation indicator values ​​of historical routine items data, the performance evaluation indicator values ​​of historical non-routine items data, the performance evaluation indicator values ​​of routine items data to be assessed, the performance evaluation indicator values ​​of non-routine items data to be assessed, the performance evaluation indicator values ​​of routine items data for assessment, and the performance evaluation indicator values ​​of non-routine items data for assessment; (3) using the performance evaluation index value of the historical routine item data and the performance evaluation index value of the evaluation non-routine item data to perform a weighted average calculation and obtain a first performance evaluation index value; (4) comparing the first performance evaluation index value with the performance evaluation index value of the routine items data to be evaluated, and determining the routine items performance evaluation status of the substation operation and maintenance team members; (5) using the performance evaluation index value of the historical non-routine items data and the performance evaluation index value of the evaluation routine items data to perform a weighted average calculation and obtain a second performance evaluation index value; (6) Compare the second performance evaluation index value with the performance evaluation index value of the non-routine items data to be evaluated, and determine the non-routine items performance evaluation status of the substation operation and maintenance team members; Input the employee number of the substation operation and maintenance team member, and use the weighted average algorithm to calculate the performance appraisal status of routine matters and the performance appraisal status of non-routine matters of the substation operation and maintenance team member in the month to be assessed, and then obtain the final performance appraisal status of the substation operation and maintenance team member in the month to be assessed; By testing the routine matters after handling the routine matters in the month to be assessed, the effect of handling the routine matters in the month to be assessed can be reflected; by testing the routine matters after handling the non-routine matters in the month to be assessed, the effect of handling the non-routine matters in the month to be assessed can be reflected; making the training effect of the deep learning model closer to the actual substation operation and maintenance operations.

2. The performance evaluation method based on the duty record system for substation operation and maintenance according to claim 1 is characterized in that: The item categories are set as routine items based on the work characteristics of substation operation and maintenance, such as operation and maintenance, switching operations, and equipment inspection operations that require regular operations, while various sudden accident handling and other temporary operations are set as non-routine items.

3. A performance evaluation system based on a duty record system for substation operation and maintenance, using the performance evaluation method based on a duty record system for substation operation and maintenance as claimed in claim 1, characterized in that: It includes the following modules in order: duty record system for substation operation and maintenance, data analysis module, deep learning system and performance appraisal module.

4. The performance appraisal system based on the duty record system for substation operation and maintenance according to claim 3 is characterized in that: The duty record system for substation operation and maintenance is used to provide relevant data for performance appraisal; The data analysis module is used to perform multi-dimensional analysis on the relevant data provided by the duty record system for substation operation and maintenance.

5. The performance evaluation system based on the duty record system for substation operation and maintenance according to claim 3 is characterized in that: The deep learning system is used to construct relevant performance evaluation indicators for the data after multi-dimensional analysis; The performance appraisal module conducts a final performance appraisal of the substation operation and maintenance team members in the month to be appraised based on the relevant performance appraisal evaluation indicators constructed by the deep learning system.

Citation Information

Patent Citations

  • Evaluation system of transformer substation's fortune dimension performance

    CN207473653U

  • Skilled talent evaluation method based on factor analysis and BP neural networks

    CN105590175A

  • Work order data-based employee performance evaluation system and method

    CN106485421A

  • Large power enterprise performance distribution monitoring and analysis system

    CN107369001A

  • Method for establishing whole-staff performance assessment information system and system

    CN108304987A