Equipment state evaluation method and system based on fuzzy comprehensive evaluation
Through the equipment status evaluation method based on fuzzy comprehensive evaluation, the problem of low accuracy in the status prediction of substation equipment is solved, and more efficient and accurate equipment status monitoring is achieved, reducing costs.
Patent Information
- Application Number
- CN202411558093.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-04
- Publication Date
- 2025-02-14
AI Technical Summary
In the prior art, the prediction accuracy of the state of the substation device is affected by data transmission and processing delays, resulting in high costs and inaccurate prediction.
Using the device state evaluation method based on fuzzy comprehensive evaluation, the device state data with the state label to be tested and the abnormal state label are obtained, and the preset device state prediction model is input, the variance is calculated to obtain the membership matrix, and the weight vector is synthesized to obtain the Comprehensive evaluation results.
It effectively solves the problem of accuracy in the state prediction of substation equipment, conducts comprehensive analysis through fuzzy comprehensive evaluation, and timely discovers potential problems, reducing the complexity and cost of data processing.
Smart Images
Figure CN119443958A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of equipment status evaluation, and in particular to an equipment status evaluation method and system based on fuzzy comprehensive evaluation. Background Art
[0002] Distribution equipment plays an important role in the distribution network. The normal operation of distribution equipment is related to the reliable and stable operation of the distribution system. The role of status evaluation is to correctly judge the operating status of the equipment. It is the first step in the implementation of status maintenance, which can ensure the reliability of equipment operation and reduce maintenance costs.
[0003] The existing substation system evaluates the status of substation equipment by using sensors to monitor the operating status of substation equipment in real time, such as temperature, vibration, oil level, current and other parameters. This results in high costs for equipment status monitoring technology, and delays in data transmission and processing may affect the accuracy of prediction of substation equipment status. Summary of the invention
[0004] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a device status assessment method and system based on fuzzy comprehensive evaluation, which solves the problem of prediction accuracy of substation equipment status through the device status assessment method based on fuzzy comprehensive evaluation.
[0005] To achieve the above object, the present invention provides the following technical solutions: A device state assessment method based on fuzzy comprehensive evaluation includes the following steps: obtaining device state data with a state label to be tested and an abnormal state label added; inputting the device state data with the state label to be tested and the abnormal state label into a preset device state prediction model to obtain first device prediction data and second device prediction data; calculating the variance of the first device prediction data and the second device prediction data to obtain a membership matrix; synthesizing the membership matrix with a weight vector to obtain a comprehensive evaluation result.
[0006] In a preferred embodiment, the first prediction data of the device and the second prediction data of the device are obtained by the following method: the obtained device status data with the state label to be tested is cleaned and used as the first prediction data of the device; the obtained device status data with the abnormal state label is quantized based on a quantization function and used as the second prediction data of the device.
[0007] In a preferred embodiment, the membership matrix is obtained by the following method: ratioing the variance of the first prediction data of the device and the variance of the second prediction data of the device; obtaining the first-level fuzzy evaluation factor and taking the minimum quantitative data below a preset threshold screened out from the second prediction data of the device as the second-level fuzzy evaluation factor; calculating the mean square error of the first-level fuzzy evaluation factor and the second-level fuzzy evaluation factor to obtain the membership matrix.
[0008] In a preferred embodiment, the membership matrix and the preset weight vector are synthesized to obtain a comprehensive evaluation result, specifically: the second-level fuzzy evaluation factors are graded to obtain the membership of the membership matrix elements, and a fuzzy membership matrix is obtained; the fuzzy membership matrix is multiplied by the preset weight vector to obtain a comprehensive evaluation result.
[0009] In a preferred embodiment, the second-level fuzzy evaluation factors are classified into: the second-level fuzzy evaluation factors are divided into severe abnormality and slight abnormality; the value range of the second-level fuzzy evaluation factors of severe abnormality is ; The numerical range of the second-level fuzzy evaluation factor of the slight abnormal state is ; According to the numerical range of the second-level fuzzy evaluation factors of each level, determine the element membership of the first prediction data of the device in the membership matrix.
[0010] A system for equipment status evaluation method based on fuzzy comprehensive evaluation, characterized by comprising a data acquisition module, an equipment status early warning analysis module, a fuzzy comprehensive evaluation module, and a prediction result module: Data acquisition module: used to acquire device status data with test status tags and abnormal status tags added; Equipment status early warning analysis module: used for inputting the equipment status data with the to-be-tested status label and the abnormal status label into a preset equipment status prediction model to obtain the first equipment prediction data and the second equipment prediction data; Fuzzy comprehensive evaluation module: used to calculate the variance of the first prediction data of the device and the second prediction data of the device to obtain the membership matrix; Prediction result module: used to synthesize the membership matrix and the weight vector to obtain a comprehensive evaluation result.
[0011] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. Through a device status assessment method based on fuzzy comprehensive evaluation, the problem of prediction accuracy of substation equipment status in the prior art is effectively solved.
[0012] 2. By combining the state labels to be tested and the abnormal state labels, a fuzzy comprehensive evaluation method is used to comprehensively analyze the equipment status, thereby realizing the timely discovery of potential problems.
[0013] 3. By using quantization functions to process abnormal state labels, data processing is made simpler and more effective, thereby enhancing the adaptability of the model. BRIEF DESCRIPTION OF THE DRAWINGS
[0014] Figure 1 A schematic diagram of the structure of a device status assessment method based on fuzzy comprehensive evaluation provided in an embodiment of the present application; Figure 2 It is a structural schematic diagram of the equipment status evaluation system based on fuzzy comprehensive evaluation of the present invention; DETAILED DESCRIPTION The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0015] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "include..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.
[0016] Embodiment 1, Figure 1 The present invention provides a device status evaluation method based on fuzzy comprehensive evaluation, comprising the following steps: A method and system for evaluating equipment status based on fuzzy comprehensive evaluation, characterized in that it comprises the following steps: Obtain device status data with a to-be-tested status tag and an abnormal status tag added; Inputting the device state data with the to-be-tested state label and the abnormal state label into a preset device state prediction model to obtain first device prediction data and second device prediction data; Calculate the variance of the first prediction data of the device and the second prediction data of the device to obtain a membership matrix; The membership matrix and the weight vector are synthesized to obtain the comprehensive evaluation result.
[0017] The test state tag is added to the device state data when it is assumed that the device state reflected by the device state data is the test state, and the abnormal state tag is added to the device when it is assumed that the device state reflected by the device state data is the abnormal state.
[0018] The method for obtaining the first prediction data of the device and the second prediction data of the device is as follows: Clean the acquired device status data with the status tag to be tested as the first prediction data of the device; The acquired device state data with abnormal state labels is quantized based on a quantization function and used as the second prediction data of the device.
[0019] The first prediction data of the device is defined as follows:
[0020] Where: First prediction data for the device, is the state parameter of the i-th substation equipment, and n is the total number of substation equipment with status tags to be tested.
[0021] The second prediction data of the device is defined as follows:
[0022] Where: The second prediction data for the device, is the state parameter of the jth substation with abnormal status, and m is the total number of substations with abnormal status labels.
[0023] The cleaning process of the acquired device status data with the status tag to be tested comprises the following steps: Extract key data from the acquired equipment status data with the status tag to be tested, and enter it into the system according to the preset format; Correct the data standard time point for the successfully entered device status data with the status tag to be tested; The attribute format, field content, and data set size range of the first prediction data of the device after detection processing.
[0024] Cleaning the device status data with the status tag to be tested has the following importance: Improve data quality: The cleaning process can remove noise and redundant data, thereby removing erroneous, duplicate or irrelevant data points, thereby improving the overall quality of the dataset; Ensure data consistency: Standardize data formats: Different devices or systems may use different status representations. The formats (such as timestamp format, status code, etc.) can be unified during the cleaning process to ensure data consistency; Improve analysis accuracy: High-quality data is the basis for building accurate prediction models, and cleaned data can improve the predictive ability of the model.
[0025] The acquired device status data with abnormal status tags is quantized based on a quantization function, and the quantization function is defined as follows:
[0026] Where: y is the quantization function, is the state parameter of the j-th abnormal substation equipment in the second prediction data of the equipment, and w is the quantization coefficient.
[0027] A quantization function is a mathematical mapping used to convert continuous values or high-precision data into discrete values or low-precision data. This conversion can reduce the complexity of the data and reduce storage requirements while still retaining the useful features of the data. When processing device status data with abnormal status labels, the role of the quantization function is mainly reflected in the following aspects: Simplify data processing: By quantizing complex, continuous state data into discrete values, the subsequent data analysis and processing steps can be simplified and the computational complexity can be reduced; Anomaly detection: In a dataset with abnormal state labels, the quantization function can help identify and distinguish normal and abnormal states. The distribution characteristics of the quantified data are more obvious, which helps to formulate corresponding detection algorithms. Improved prediction accuracy: Quantization can improve the prediction performance of machine learning models by removing noise and redundant information from the data. By using quantized data as input, the model can more effectively identify patterns and trends; Facilitates feature extraction: During the quantization process, features can be extracted by selecting an appropriate quantization method (such as uniform quantization or non-uniform quantization), thereby providing more effective information for subsequent prediction models.
[0028] The calculation formula for calculating the variance of the first prediction data of the device and the second prediction data of the device is as follows:
[0029] Where: is the variance of the first predicted data of the device, is the variance of the second prediction data of the device, is the state parameter of the jth abnormal substation, m is the total number of substations with abnormal state labels, is the state parameter of the i-th substation equipment, n is the total number of substation equipment with the state label to be tested, is the average value.
[0030] The membership matrix is obtained as follows: Ratio the variance of the first prediction data of the device to the variance of the second prediction data of the device; obtain the first-level fuzzy evaluation factor; The minimum quantitative data below the preset threshold screened out from the second prediction data of the device is used as the second-level fuzzy evaluation factor; The mean square error of the first-level fuzzy evaluation factors and the second-level fuzzy evaluation factors is calculated to obtain the membership matrix.
[0031] The first-level fuzzy evaluation factors are defined as follows:
[0032] The membership matrix is calculated as follows:
[0033] Where: E is the membership matrix, is the jth fuzzy evaluation factor, and k is the number of evaluation factors.
[0034] The first-level fuzzy evaluation factors are defined as follows:
[0035] Where: is the variance of the first predicted data of the device, is the variance of the second prediction data of the device, It should be noted that the use of the minimum quantitative data below the preset threshold screened out from the second prediction data of the device as the second-level fuzzy evaluation factor has the following significance: By setting a threshold, the data below the value can be considered as abnormal or abnormal. Such data usually represent equipment failure or abnormal operation. Therefore, they are taken into consideration in the fuzzy evaluation, which helps to improve the accuracy and effectiveness of the evaluation. Using data below the threshold as the second-level fuzzy evaluation factor helps to form a more detailed membership matrix, making subsequent analysis and decision-making more scientific. By focusing on the analysis of this part of the data, enterprises or organizations can develop more effective maintenance strategies and improvement plans, reduce equipment failure rates, and improve overall operating efficiency; In fuzzy control or evaluation, the construction of membership function often depends on specific evaluation indicators. By introducing data below the preset threshold, a more comprehensive and accurate membership function can be formed.
[0036] The membership matrix is synthesized with the preset weight vector to obtain a comprehensive evaluation result, which is specifically: The second-level fuzzy evaluation factors are graded to obtain the element membership of the membership matrix, thereby obtaining a fuzzy membership matrix; The fuzzy membership matrix is multiplied by the preset weight vector to obtain a comprehensive evaluation result.
[0037] In fuzzy evaluation methods, it is a common approach to conduct comprehensive evaluation by constructing a membership matrix and presetting weight vectors.
[0038] The second-level fuzzy evaluation factors are classified into severe abnormality and slight abnormality; The numerical range of the second-level fuzzy evaluation factor of severe abnormal state is ; The numerical range of the second-level fuzzy evaluation factor of the slight abnormal state is ; According to the numerical range of the second-level fuzzy evaluation factor of each level, the absolute value of the difference of the first prediction data of the device in the membership matrix is determined, and the element membership of the membership matrix is obtained, and the fuzzy membership matrix is composed of the element membership of the membership matrix.
[0039] It should be noted that the fuzzy evaluation is to determine the membership of each factor indicator in the influencing factor set in the comment set, establish a fuzzy relationship from the influencing factor set to the equipment status data, and thus derive the membership matrix.
[0040] The comprehensive evaluation results are obtained as follows:
[0041] Where: Z is the comprehensive evaluation result, is the fuzzy membership matrix, is the preset weight vector.
[0042] It should be noted that the state of the device with the state label to be tested is measured by the value of the comprehensive evaluation result, wherein the preset weight vector is a matrix with n rows and a single column, and n is the number of rows of the fuzzy membership matrix.
[0043] Fuzzy evaluation is an evaluation method based on fuzzy mathematics theory, which is used to deal with uncertainty and fuzziness. It expresses the characteristics, attributes and indicators of the evaluation objects in the form of fuzzy numbers, thereby achieving a comprehensive evaluation of these objects. This method is particularly suitable for situations that cannot be described with precise numbers, and is commonly used in the fields of social sciences, management, environmental science, etc.
[0044] The basic principles of fuzzy evaluation are as follows: Fuzzy set: The basis of fuzzy evaluation is fuzzy set theory. Fuzzy set represents the membership of an object as a range rather than a specific value. Each element has a membership in the range of [0,1], indicating its "degree" in the set.
[0045] Membership function: Each fuzzy set has a corresponding membership function that is used to define the membership of the elements. These functions can be in the form of triangle, trapezoid, etc., depending on the application scenario and requirements.
[0046] Fuzzy comprehensive evaluation: By combining the fuzzy values of various evaluation indicators, an overall evaluation is formed. Usually, the weighted average method is used to take the importance of different indicators into account.
[0047] Fuzzy evaluation provides an effective method for solving complex problems. By dealing with fuzziness and uncertainty, it makes the evaluation more flexible and in line with the actual situation. With the development of fuzzy mathematics theory, the application field of fuzzy evaluation is also expanding, providing valuable support for various industries.
[0048] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.
[0049] Embodiment 2, Figure 2 The present invention provides a system for an equipment status evaluation method based on fuzzy comprehensive evaluation, including a data acquisition module, an equipment status early warning analysis module, a fuzzy comprehensive evaluation module, and a prediction result module: Data acquisition module: used to acquire device status data with test status tags and abnormal status tags added; Equipment status early warning analysis module: used for inputting the equipment status data with the to-be-tested status label and the abnormal status label into a preset equipment status prediction model to obtain the first equipment prediction data and the second equipment prediction data; Fuzzy comprehensive evaluation module: used to calculate the variance of the first prediction data of the device and the second prediction data of the device to obtain the membership matrix; Prediction result module: used to synthesize the membership matrix and the weight vector to obtain a comprehensive evaluation result.
[0050] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product.
[0051] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.
[0052] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.
[0053] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
[0054] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.
Claims
1. A method and system for evaluating equipment status based on fuzzy comprehensive evaluation, characterized in that: The steps include: Obtain device status data with a to-be-tested status tag and an abnormal status tag added; Inputting the device state data with the to-be-tested state label and the abnormal state label into a preset device state prediction model to obtain first device prediction data and second device prediction data; Calculate the variance of the first prediction data of the device and the second prediction data of the device to obtain a membership matrix; The membership matrix and the weight vector are synthesized to obtain the comprehensive evaluation result.
2. The device status assessment method based on fuzzy comprehensive evaluation as claimed in claim 1, characterized in that: The method for obtaining the first prediction data of the device and the second prediction data of the device is as follows: Clean the acquired device status data with the status tag to be tested as the first prediction data of the device; The acquired device state data with abnormal state labels is quantized based on a quantization function and used as the second prediction data of the device.
3. The device status assessment method based on fuzzy comprehensive evaluation as claimed in claim 2, characterized in that: The calculation formula for calculating the variance of the first prediction data of the device and the second prediction data of the device is as follows: Where: is the variance of the first predicted data of the device, is the variance of the second prediction data of the device, is the state parameter of the jth abnormal substation, m is the total number of substations with abnormal state labels, is the state parameter of the i-th substation equipment, n is the total number of substation equipment with the state label to be tested, is the average value.
4. The device status assessment method based on fuzzy comprehensive evaluation as claimed in claim 3 is characterized by: The membership matrix is obtained as follows: Ratio the variance of the first prediction data of the device to the variance of the second prediction data of the device; obtain the first-level fuzzy evaluation factor; The minimum quantitative data below the preset threshold screened out from the second prediction data of the device is used as the second-level fuzzy evaluation factor; The mean square error of the first-level fuzzy evaluation factors and the second-level fuzzy evaluation factors is calculated to obtain the membership matrix.
5. The device status assessment method based on fuzzy comprehensive evaluation as claimed in claim 4, characterized in that: The membership matrix is synthesized with the preset weight vector to obtain a comprehensive evaluation result, which is specifically: The second-level fuzzy evaluation factors are graded to obtain the membership degrees of the membership matrix elements, thereby obtaining a fuzzy membership matrix; The fuzzy membership matrix is multiplied by the preset weight vector to obtain a comprehensive evaluation result.
6. The device status assessment method based on fuzzy comprehensive evaluation as claimed in claim 5, characterized in that: Said The quantization function is defined as follows: Where: y is the quantization function, is the state parameter of the j-th abnormal substation equipment in the second prediction data of the equipment, and w is the quantization coefficient.
7. The device status assessment method based on fuzzy comprehensive evaluation as claimed in claim 6, characterized in that: The membership matrix is calculated as follows: Where: E is the membership matrix, is the jth fuzzy evaluation factor, and k is the total number of evaluation factors.
8. The device status assessment method based on fuzzy comprehensive evaluation as claimed in claim 7, characterized in that: The second-level fuzzy evaluation factors are classified as follows: The second-level fuzzy evaluation factors are divided into severe abnormal state and slight abnormal state; the value range of the second-level fuzzy evaluation factors of severe abnormal state is ; The numerical range of the second-level fuzzy evaluation factor of the slight abnormal state is ; According to the numerical range of the second-level fuzzy evaluation factors of each level, determine the element membership of the first prediction data of the device in the membership matrix.
9. The device status assessment method based on fuzzy comprehensive evaluation as claimed in claim 8, characterized in that: The comprehensive evaluation results are obtained as follows: Where: Z is the comprehensive evaluation result, is the fuzzy membership matrix, is the preset weight vector.
10. A system using the equipment status assessment method based on fuzzy comprehensive evaluation as claimed in any one of claims 1 to 9, characterized in that: Including data acquisition module, equipment status early warning analysis module, fuzzy comprehensive evaluation module, and prediction result module: Data acquisition module: used to acquire device status data with test status tags and abnormal status tags added; Equipment status early warning analysis module: used for inputting the equipment status data with the to-be-tested status label and the abnormal status label into a preset equipment status prediction model to obtain the first equipment prediction data and the second equipment prediction data; Fuzzy comprehensive evaluation module: used to calculate the variance of the first prediction data of the device and the second prediction data of the device to obtain the membership matrix; Prediction result module: used to synthesize the membership matrix and the weight vector to obtain a comprehensive evaluation result.