CN116894165B - Cable aging state assessment method based on data analysis - Google Patents
Cable aging state assessment method based on data analysis Download PDFInfo
- Publication number
- CN116894165B CN116894165B CN202311160592.9A CN202311160592A CN116894165B CN 116894165 B CN116894165 B CN 116894165B CN 202311160592 A CN202311160592 A CN 202311160592A CN 116894165 B CN116894165 B CN 116894165B
- Authority
- CN
- China
- Prior art keywords
- cable
- parameter indexes
- principal component
- state parameter
- sample
- 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
- 230000032683 aging Effects 0.000 title claims abstract description 50
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000007405 data analysis Methods 0.000 title claims abstract description 11
- 238000011156 evaluation Methods 0.000 claims abstract description 11
- 238000000513 principal component analysis Methods 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 10
- 238000000605 extraction Methods 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 9
- 238000004422 calculation algorithm Methods 0.000 claims description 8
- 230000002860 competitive effect Effects 0.000 claims description 8
- 230000004927 fusion Effects 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000005070 sampling Methods 0.000 claims description 6
- 238000012614 Monte-Carlo sampling Methods 0.000 claims description 4
- 238000003066 decision tree Methods 0.000 claims description 4
- 238000007637 random forest analysis Methods 0.000 claims description 4
- 238000013077 scoring method Methods 0.000 claims description 4
- 238000012706 support-vector machine Methods 0.000 claims description 4
- 239000004020 conductor Substances 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 230000003044 adaptive effect Effects 0.000 claims description 2
- 239000000284 extract Substances 0.000 abstract description 2
- 238000012423 maintenance Methods 0.000 abstract description 2
- 238000009413 insulation Methods 0.000 description 5
- 238000010223 real-time analysis Methods 0.000 description 5
- 239000000126 substance Substances 0.000 description 5
- 238000012847 principal component analysis method Methods 0.000 description 3
- 239000000463 material Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000002427 irreversible effect Effects 0.000 description 1
- 230000007257 malfunction Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 230000004083 survival effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/003—Environmental or reliability tests
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/04—Ageing analysis or optimisation against ageing
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Business, Economics & Management (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Environmental & Geological Engineering (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Testing Relating To Insulation (AREA)
Abstract
The application belongs to the technical field of power equipment maintenance and application, and particularly relates to a cable aging state assessment method based on data analysis. The method provided by the application fully extracts the state parameter index with high correlation, effectively eliminates irrelevant variables and realizes real-time evaluation of the aging degree of the cable.
Description
Technical Field
The application belongs to the technical field of power equipment maintenance and application, and particularly relates to a cable aging state assessment method based on data analysis.
Background
The power cable is an important component of the urban power grid, and the failure of the cable not only causes economic loss and bad social influence, but also affects the safe and stable operation of the urban power grid, so the reliability of the power cable is very important. Due to the influence of factors such as force, heat, electricity, environment and the like, the cable insulation can gradually age and malfunction occurs.
Existing methods for evaluating the ageing state of cables focus on studying the relationship between a single factor and the ageing state. The insulation aging of the cable is a complex process, and the mechanical, thermal and dielectric properties of the material are changed during the aging period, but the relation between the multi-performance parameter index and the insulation aging state is still unclear. Although the physical and chemical quantity of the slice can well reflect the relation between each parameter index and the aging of the cable, the physical and chemical quantity of the slice is usually detected only in a laboratory stage, and the practical application difficulty is very high. In addition, as the aging factors to be considered increase, the evaluation work faces a large amount of experimental data to be analyzed, and real-time analysis is difficult.
Disclosure of Invention
Aiming at the technical problems existing in the cable aging state evaluation, the application provides the cable aging state evaluation method based on data analysis, which has the advantages of reasonable design, simple method, strong theories, and capability of determining state parameter indexes with high correlation with the cable aging degree, and solving the problems of difficult real-time analysis, large actual application difficulty and the like.
In order to achieve the above purpose, the application adopts the following technical scheme: a cable aging state assessment method based on data analysis comprises the following steps:
s1, collecting state parameter indexes related to existing cable samples and cable aging degrees;
s2, carrying out standardization processing on the state parameter indexes of the existing cable sample, wherein a standardization formula is as follows:
wherein X is ij The original value of the j state parameter index of the i-th existing cable sample, X' ij Normalized values for the j-th state parameter index for the i-th sample,and S is j The mean value and standard deviation of the j state parameter indexes are respectively;
s3, extracting features, namely extracting features in standardized existing cable sample state parameter indexes based on improved principal component analysis and a competitive self-adaptive re-weighting algorithm to obtain two groups of feature variables, wherein the improved principal component analysis firstly calculates entropy values of all principal components, and the calculation formula is as follows:
wherein E is i For the entropy value occupied by the ith main component, n represents the number of state parameter indexes related to the existing cable samples, m represents the number of the existing cable samples, and P ci The variance contribution rate of the ith principal component of the c-th sample is used for scoring all the principal components based on a loop ratio scoring method to determine a score, and the weight of each principal component is determined as follows:
wherein w is i For the weight occupied by the ith principal component, n represents the number of state parameter indexes related to the existing cable sample, E i And finally, calculating the comprehensive score of the principal component as follows for the entropy value occupied by the ith principal component:
wherein P is ci Variance contribution ratio, w, of ith principal component for the c-th sample i For the weight occupied by the ith principal component, m represents the number of existing cable samples, n represents the number of state parameter indexes related to the existing cable samples, and when the comprehensive score reaches 99, k principal component components participating in calculation are based on characteristic variables of improved principal component analysis;
s4, feature layer fusion is carried out on the two groups of feature variables obtained through feature extraction, and training data are obtained through splicing of the two groups of feature variables;
s5, building a Stacking model by combining different basic classifiers, and training the model by using training data to obtain a Stacking model for evaluating the cable aging degree and analyzing in real time;
s6, collecting state parameter indexes related to the cable sample to be evaluated, and processing the state parameter indexes and the existing cable data sample, wherein the state parameter indexes comprise standardization processing, feature extraction and feature layer fusion;
and S7, introducing the processed data into a Stacking model for evaluating the cable aging degree in real time to obtain the cable sample aging degree to be evaluated.
Preferably, the parameter indexes of the step S1 include: cable run time, cable average load factor, cable partial discharge, discharge pulse density, cable conductor temperature, resistance, operating voltage, operating current, whether fault tripping has occurred, the number of heavy loads/overloads, whether mechanical damage has been suffered, cable temperature, ambient humidity, the mode of laying and manufacturer, the cable ageing degree includes: normal 1, attention 2, anomaly 3, and hazard 4.
Preferably, the number of the two sets of characteristic variables in the step S3 is smaller than the number of the state parameter indexes related to the existing cable sample.
Preferably, the step of extracting the feature variable by the competitive adaptive re-weighting algorithm in the step S3 is as follows:
s321, constructing a corresponding partial least square model by utilizing the existing cable sample screened by Monte Carlo sampling;
s322, calculating the weight of the absolute value of the regression coefficient in the sampling and eliminating the parameter index with smaller absolute value, and judging the number of the parameter indexes after eliminating by using an exponential decay method;
s323, screening out parameter indexes by utilizing self-adaptive re-weighted sampling according to the rest parameter indexes, and constructing a PLS model, wherein the parameter indexes corresponding to the RMSECV minimum PLS model are the screened out characteristic variables.
Preferably, the Stacking model in the step S5 includes a two-layer classifier, the first layer classifier includes a support vector machine, naive bayes and a decision tree, and the second layer classifier is a random forest.
Compared with the prior art, the application has the advantages and positive effects that:
1. the method for respectively extracting the characteristics and then carrying out the characteristic layer fusion based on the improved principal component analysis and the competitive self-adaptive weighting algorithm fully extracts the state parameter indexes with high correlation with the cable aging degree, effectively eliminates irrelevant variables and avoids a large amount of experimental data.
2. The Stacking model built by the application comprises a support vector machine, a naive Bayes and a decision tree classifier in a first layer, and a random forest classifier in a second layer, and combines different basic classifiers, so that the real-time evaluation of the cable aging degree is realized.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort to a person skilled in the art.
Fig. 1 is a structure diagram of a Stacking model provided in an embodiment of the present application.
Detailed Description
In order that the above objects, features and advantages of the application will be more clearly understood, a further description of the application will be rendered by reference to the appended drawings and examples. It should be noted that, without conflict, the embodiments of the present application and features in the embodiments may be combined with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application, however, the present application may be practiced otherwise than as described herein, and therefore the present application is not limited to the specific embodiments of the disclosure that follow.
Embodiments, consider that existing cable aging state assessment methods focus on studying the relationship between a single factor and aging state. The insulation aging of the cable is a complex process, and the mechanical, thermal and dielectric properties of the material are changed during the aging period, but the relation between the multi-performance parameter index and the insulation aging state is still unclear. Although the physical and chemical quantity of the slice can well reflect the relation between each parameter index and the aging of the cable, the physical and chemical quantity of the slice is usually detected only in a laboratory stage, and the practical application difficulty is very high. In addition, as the aging factors to be considered increase, the evaluation work faces a large amount of experimental data to be analyzed, and real-time analysis is difficult. The application provides a cable aging state evaluation method based on data analysis, which comprises the steps of firstly collecting state parameter indexes and cable aging degree related to existing cable samples, wherein the parameter indexes comprise: cable run time, cable average load factor, cable partial discharge, discharge pulse density, cable conductor temperature, resistance, operating voltage, operating current, whether fault tripping has occurred, the number of heavy loads/overloads, whether mechanical damage has been suffered, cable temperature, ambient humidity, the mode of laying and manufacturer, the cable ageing degree includes: normal 1, attention 2, anomaly 3, and hazard 4.
In order to reduce errors caused by inconsistent dimension of each state parameter index, the state parameter index is subjected to standardized processing, and a standardized formula is as follows:
wherein X is ij The original value of the j state parameter index of the i-th existing cable sample, X' ij Normalized values for the j-th state parameter index for the i-th sample,and S is j The mean value and standard deviation of the j state parameter indexes are respectively.
Because the state parameter indexes of the high-voltage cable are relatively large and the regularity is not strong, the differential information of different ageing degrees needs to be extracted from complicated data. In order to avoid insufficient feature extraction, the application respectively performs feature extraction in the standardized state parameter indexes of the existing cable sample based on the improved principal component analysis and the competitive self-adaptive re-weighting algorithm to obtain two groups of feature variables. Principal component analysis maps high-dimensional data into a low-dimensional space through linear changes, and these low-dimensional data can preserve information of the original data as much as possible. However, PCA transforms the original data according to the global structural features such as the mean, variance and covariance of the data, but ignores the local structure of the data, so that aliasing occurs in the features with different aging degrees after the PCA processing of the data.
The entropy weighting method is an objective weighting method for describing the irreversible phenomenon of molecules. The larger the difference between the parameter indexes of a system is, the more information is contained, the smaller the entropy value is, and the larger the entropy value is, so that the contribution degree of a certain weight index to the system is evaluated. The entropy weight method has the advantages of being capable of highlighting local information of the system, being small in influence of subjective factors and the like, and is widely applied to the field of multiple projects.
When the first principal component of the conventional principal component analysis method does not meet the requirement that the cumulative variance contribution ratio is greater than 85%, a plurality of principal components are fused, and weight distribution among the principal components is a main factor affecting the evaluation of the cable aging degree. The traditional principal component analysis method is to comprehensively calculate the weighting of the principal components by using the variance contribution rate of each principal component, but the principal components are mutually independent, the information quantity of the calculated result can not rise or fall, and the requirement of the cable aging degree dividing precision can not be met. The application refers to an entropy weight method for improving the traditional principal component analysis method, and recalculates the weight of each principal component, wherein the improved principal component analysis firstly calculates the entropy value of each principal component, and the calculation formula is as follows:
wherein E is i For the entropy value occupied by the ith main component, n represents the number of state parameter indexes related to the existing cable samples, m represents the number of the existing cable samples, and P ci The variance contribution rate of the ith principal component of the c-th sample is then considered, the situation that the loop ratio scoring method can be directly compared and the functional importance ratio can be accurately assessed is based onThe loop ratio scoring method scores each principal component to determine a score, and the weight of each principal component is determined as follows:
wherein w is i For the weight occupied by the ith principal component, n represents the number of state parameter indexes related to the existing cable sample, E i And finally, calculating the comprehensive score of the principal component as follows for the entropy value occupied by the ith principal component:
wherein P is ci Variance contribution ratio, w, of ith principal component for the c-th sample i For the weight occupied by the ith principal component, m represents the number of existing cable samples, n represents the number of state parameter indexes related to the existing cable samples, and when the comprehensive score reaches 99, k principal component components participating in calculation are based on characteristic variables of improved principal component analysis;
the competitive self-adaptive re-weighting algorithm takes the' survival of the right of Darwin evolution theory as a guiding theory, and adopts a characteristic variable optimization method of a Monte Carlo sampling and partial least square regression method. The step of extracting characteristic variables by the competitive self-adaptive re-weighting algorithm is as follows: firstly, constructing a corresponding partial least square model by utilizing the existing cable sample screened by Monte Carlo sampling; then calculating the weight of the absolute value of the regression coefficient in the sampling and eliminating the parameter index with smaller absolute value, and judging the number of the parameter index after eliminating by using an exponential decay method; and finally, screening out parameter indexes by utilizing self-adaptive re-weighted sampling according to the rest parameter indexes, and constructing a PLS model, wherein the parameter indexes corresponding to the RMSECV minimum PLS model are the screened characteristic variables.
Because the feature extraction can effectively remove irrelevant variables, and the selected feature variables are vectorized according to a certain sequence, the fusion of state parameter indexes is realized. And therefore, feature layer fusion is carried out on the two groups of feature variables obtained by feature extraction, and the two groups of feature variables are spliced to obtain training data. Considering that the Stacking model is WOLPERT development, the learning method of combining a plurality of trainers in a layered manner firstly transforms the original data into new features and based on the new features trains by using a second layer classifier. Different from the traditional model, the Stacking model combines different basic classifiers to realize the construction of a new model, and as shown in fig. 1, the Stacking model is constructed by combining different basic classifiers, and comprises two layers of classifiers, wherein the first layer of classifier comprises a support vector machine, naive Bayes and a decision tree, and the second layer of classifier is a random forest. Training the model by using training data to obtain a Stacking model for cable aging degree evaluation real-time analysis, collecting state parameter indexes related to a cable sample to be evaluated, processing the state parameter indexes and the existing cable data sample, including standardization processing, feature extraction and feature layer fusion, and then introducing processed data into the Stacking model for cable aging degree evaluation real-time analysis to obtain the cable sample aging degree to be evaluated.
The present application is not limited to the above-mentioned embodiments, and any equivalent embodiments which can be changed or modified by the technical content disclosed above can be applied to other fields, but any simple modification, equivalent changes and modification made to the above-mentioned embodiments according to the technical substance of the present application without departing from the technical content of the present application still belong to the protection scope of the technical solution of the present application.
Claims (5)
1. The cable aging state evaluation method based on data analysis is characterized by comprising the following steps of:
s1, collecting state parameter indexes related to existing cable samples and cable aging degrees;
s2, carrying out standardization processing on the state parameter indexes of the existing cable sample, wherein a standardization formula is as follows:
wherein X is ij The original value of the j state parameter index of the i-th existing cable sample, X' ij Normalized values for the j-th state parameter index for the i-th sample,and S is j The mean value and standard deviation of the j state parameter indexes are respectively;
s3, extracting features, namely extracting features in standardized existing cable sample state parameter indexes based on improved principal component analysis and a competitive self-adaptive re-weighting algorithm to obtain two groups of feature variables, wherein the improved principal component analysis firstly calculates entropy values of all principal components, and the calculation formula is as follows:
wherein E is i For the entropy value occupied by the ith main component, n represents the number of state parameter indexes related to the existing cable samples, m represents the number of the existing cable samples, and P ci The variance contribution rate of the ith principal component of the c-th sample is used for scoring all the principal components based on a loop ratio scoring method to determine a score, and the weight of each principal component is determined as follows:
wherein w is i For the weight occupied by the ith principal component, n represents the number of state parameter indexes related to the existing cable sample, F i And finally, calculating the comprehensive score of the principal component as follows for the entropy value occupied by the ith principal component:
wherein P is ci Variance contribution ratio, w, of ith principal component for the c-th sample i For the weight occupied by the ith principal component, m represents the number of existing cable samples, n represents the number of state parameter indexes related to the existing cable samples, and when the comprehensive score reaches 99, k principal component components participating in calculation are based on characteristic variables of improved principal component analysis;
s4, feature layer fusion is carried out on the two groups of feature variables obtained through feature extraction, and training data are obtained through splicing of the two groups of feature variables;
s5, building a Stacking model by combining different basic classifiers, and training the model by using training data to obtain a Stacking model for evaluating the cable aging degree and analyzing in real time;
s6, collecting state parameter indexes related to the cable sample to be evaluated, and processing the state parameter indexes and the existing cable data sample, wherein the state parameter indexes comprise standardization processing, feature extraction and feature layer fusion;
and S7, introducing the processed data into a Stacking model for evaluating the cable aging degree in real time to obtain the cable sample aging degree to be evaluated.
2. The method for evaluating the aging state of a cable based on data analysis according to claim 1, wherein the parameter indexes of the step S1 comprise: cable run time, cable average load factor, cable partial discharge, discharge pulse density, cable conductor temperature, resistance, operating voltage, operating current, whether fault tripping has occurred, the number of heavy loads/overloads, whether mechanical damage has been suffered, cable temperature, ambient humidity, the mode of laying and manufacturer, the cable ageing degree includes: normal 1, attention 2, anomaly 3, and hazard 4.
3. The method for evaluating the aging state of a cable according to claim 1, wherein the number of the two sets of characteristic variables in the step S3 is smaller than the number of the state parameter indexes related to the existing cable sample.
4. The method for evaluating the aging state of a cable based on data analysis according to claim 1, wherein the step of extracting the feature variable by the competitive adaptive re-weighting algorithm in the step S3 is as follows:
s321, constructing a corresponding partial least square model by utilizing the existing cable sample screened by Monte Carlo sampling;
s322, calculating the weight of the absolute value of the regression coefficient in the sampling and eliminating the parameter index with smaller absolute value, and judging the number of the parameter indexes after eliminating by using an exponential decay method;
s323, screening out parameter indexes by utilizing self-adaptive re-weighted sampling according to the rest parameter indexes, and constructing a PLS model, wherein the parameter indexes corresponding to the RMSECV minimum PLS model are the screened out characteristic variables.
5. The method for evaluating the aging state of the cable based on data analysis according to claim 1, wherein the Stacking model in the step S5 comprises two layers of classifiers, the first layer of classifiers comprises a support vector machine, naive bayes and a decision tree, and the second layer of classifiers is a random forest.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311160592.9A CN116894165B (en) | 2023-09-11 | 2023-09-11 | Cable aging state assessment method based on data analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311160592.9A CN116894165B (en) | 2023-09-11 | 2023-09-11 | Cable aging state assessment method based on data analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116894165A CN116894165A (en) | 2023-10-17 |
| CN116894165B true CN116894165B (en) | 2023-12-08 |
Family
ID=88315183
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311160592.9A Active CN116894165B (en) | 2023-09-11 | 2023-09-11 | Cable aging state assessment method based on data analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116894165B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117829675A (en) * | 2024-01-05 | 2024-04-05 | 聊城市茌平区环境监控中心 | Environment and rating system based on big data analysis |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102129676A (en) * | 2010-01-19 | 2011-07-20 | 中国科学院空间科学与应用研究中心 | Microscopic image fusing method based on two-dimensional empirical mode decomposition |
| US8428985B1 (en) * | 2009-09-04 | 2013-04-23 | Ford Motor Company | Multi-feature product inventory management and allocation system and method |
| CN106127594A (en) * | 2016-06-30 | 2016-11-16 | 武汉斗鱼网络科技有限公司 | User room interest-degree computational methods based on principal component analysis and system |
| CN108764675A (en) * | 2018-05-17 | 2018-11-06 | 河海大学 | A kind of water system Connectivity Evaluation method |
| CN113376483A (en) * | 2021-06-10 | 2021-09-10 | 云南电网有限责任公司电力科学研究院 | XLPE cable insulation state evaluation method |
| CN113533236A (en) * | 2021-09-13 | 2021-10-22 | 广东省农业科学院农业质量标准与监测技术研究所 | Fruit spectrum feature extraction method, model training method and detection method |
| CN114202141A (en) * | 2021-06-25 | 2022-03-18 | 国网浙江省电力有限公司营销服务中心 | Metering equipment verification line running state evaluation method based on edge cloud cooperation |
| WO2022140386A1 (en) * | 2020-12-21 | 2022-06-30 | The Johns Hopkins University | Detection of lung cancer using cell-free dna fragmentation |
| CN116298720A (en) * | 2023-02-14 | 2023-06-23 | 国网河北省电力有限公司石家庄供电分公司 | Cable aging state testing device, method, equipment, terminal and evaluation system |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8004279B2 (en) * | 2008-05-23 | 2011-08-23 | Baker Hughes Incorporated | Real-time NMR distribution while drilling |
| US8442279B2 (en) * | 2008-06-27 | 2013-05-14 | Lockheed Martin Corporation | Assessing biometric sample quality using wavelets and a boosted classifier |
| US12025615B2 (en) * | 2017-09-15 | 2024-07-02 | Arizona Board Of Regents On Behalf Of Arizona State University | Methods of classifying response to immunotherapy for cancer |
| US11137761B2 (en) * | 2017-11-20 | 2021-10-05 | At&T Intellectual Property I, L.P. | Object modeling with adversarial learning |
| CN109960873B (en) * | 2019-03-24 | 2021-09-10 | 北京工业大学 | Soft measurement method for dioxin emission concentration in urban solid waste incineration process |
-
2023
- 2023-09-11 CN CN202311160592.9A patent/CN116894165B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8428985B1 (en) * | 2009-09-04 | 2013-04-23 | Ford Motor Company | Multi-feature product inventory management and allocation system and method |
| CN102129676A (en) * | 2010-01-19 | 2011-07-20 | 中国科学院空间科学与应用研究中心 | Microscopic image fusing method based on two-dimensional empirical mode decomposition |
| CN106127594A (en) * | 2016-06-30 | 2016-11-16 | 武汉斗鱼网络科技有限公司 | User room interest-degree computational methods based on principal component analysis and system |
| CN108764675A (en) * | 2018-05-17 | 2018-11-06 | 河海大学 | A kind of water system Connectivity Evaluation method |
| WO2022140386A1 (en) * | 2020-12-21 | 2022-06-30 | The Johns Hopkins University | Detection of lung cancer using cell-free dna fragmentation |
| CN113376483A (en) * | 2021-06-10 | 2021-09-10 | 云南电网有限责任公司电力科学研究院 | XLPE cable insulation state evaluation method |
| CN114202141A (en) * | 2021-06-25 | 2022-03-18 | 国网浙江省电力有限公司营销服务中心 | Metering equipment verification line running state evaluation method based on edge cloud cooperation |
| CN113533236A (en) * | 2021-09-13 | 2021-10-22 | 广东省农业科学院农业质量标准与监测技术研究所 | Fruit spectrum feature extraction method, model training method and detection method |
| CN116298720A (en) * | 2023-02-14 | 2023-06-23 | 国网河北省电力有限公司石家庄供电分公司 | Cable aging state testing device, method, equipment, terminal and evaluation system |
Non-Patent Citations (4)
| Title |
|---|
| Early-Stage Diagnosis of Panax Notoginseng Plant Blight Disease by Multispectral Imaging;Zhihong Zhang;《2022 International Conference on Intelligent Systems and Computational Intelligence (ICISCI) 》;全文 * |
| 不同非常规蛋白饲料原料成分特性的表征研究;周兴藩;《 中国博士学位论文电子期刊网》;全文 * |
| 基于主成分分析的变压器状态量权重方法研究;黎佳;王鹏飞;陈小民;周力行;王建军;;陕西电力(第02期);全文 * |
| 黎佳 ; 王鹏飞 ; 陈小民 ; 周力行 ; 王建军 ; .基于主成分分析的变压器状态量权重方法研究.陕西电力.2017,(第02期),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116894165A (en) | 2023-10-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106908674B (en) | Transformer state evaluation method based on multi-state quantity prediction | |
| CN116894165B (en) | Cable aging state assessment method based on data analysis | |
| CN110542819B (en) | Transformer fault type diagnosis method based on semi-supervised DBNC | |
| CN105719048A (en) | Intermediate-voltage distribution operation state fuzzy integrated evaluation method based on principle component analysis method and entropy weight method | |
| CN108038300A (en) | Optical fiber state evaluating method based on improved membership function combination neutral net | |
| CN107274067B (en) | Distribution transformer overload risk assessment method | |
| CN110298012B (en) | Test data and operation and maintenance information-based medium and low voltage XLPE cable service life assessment method | |
| CN106446571A (en) | Error evaluation method of wind power forecasting | |
| CN104020401A (en) | Cloud-model-theory-based method for evaluating insulation thermal ageing states of transformer | |
| CN105912857B (en) | Matching method of power distribution equipment state monitoring sensors | |
| CN104156775B (en) | Meteorological disaster Forecasting Methodology based on arithmetic of linearity regression | |
| CN110852441B (en) | Fire disaster early warning method based on improved naive Bayes algorithm | |
| CN105719094A (en) | State evaluation method of power transmission equipment | |
| CN115689114A (en) | Submarine cable running state prediction method based on combined neural network | |
| CN113435492A (en) | Power system dominant instability mode discrimination method based on active learning | |
| CN113780401A (en) | Composite insulator fault detection method and system based on principal component analysis method | |
| CN106845711A (en) | Processing method and processing device for power supply reliability data | |
| CN117674119A (en) | Power grid operation risk assessment method, device, computer equipment and storage medium | |
| Ghaemi et al. | Situational awareness and deficiency warning system in a smart distribution network based on stacking ensemble learning | |
| CN113782113A (en) | Method for identifying gas fault in transformer oil based on deep residual error network | |
| CN111582634B (en) | Multi-factor safety grading method and system for underground large-space construction | |
| Tang et al. | Predicting typhoon-induced transmission line outages with coordination of static and dynamic data | |
| Song et al. | Comprehensive evaluation of the transformer oil-paper insulation state based on RF-combination weighting and an improved TOPSIS method | |
| Tan et al. | Condition assessment method for power transformers based on variable weight principle and fuzzy comprehensive evaluation | |
| CN113393102B (en) | Distribution transformer operation state trend prediction method based on data driving |
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 |