Cable degradation evaluation method, device, equipment, readable storage medium and program product

Abstract

The invention relates to a cable degradation evaluation method, device and equipment, a readable storage medium and a program product. The method comprises the steps of obtaining harmonic data of a target cable under different working conditions, determining original feature data according to the harmonic data, then performing principal component analysis on the original feature data, determining target feature data corresponding to the original feature data, and thus obtaining a target evaluation model according to the target feature data and the target evaluation model. And determining a degradation evaluation result corresponding to the target cable. By adopting the method, the accuracy of deterioration evaluation can be improved.

Description

Technical Field

[0001] The present application relates to the field of cable technology, and in particular to a cable degradation assessment method, device, equipment, readable storage medium and program product. Background Art

[0002] Cable degradation refers to the gradual decline in the physical and chemical properties of cables during long-term operation due to the influence of various factors. If the degree of cable degradation is too high, it may cause the cable to fail. Therefore, it is necessary to evaluate the degree of cable degradation.

[0003] Traditional cable degradation assessment methods usually use a preset regression method to process high-dimensional harmonic data based on L1 regularization constraints to assess the degree of cable degradation.

[0004] However, the above methods have the problem of low evaluation accuracy. Summary of the invention

[0005] Based on this, it is necessary to provide a cable degradation assessment method, device, equipment, readable storage medium and program product that can improve the assessment accuracy in response to the above technical problems.

[0006] In a first aspect, the present application provides a cable degradation assessment method, comprising:

[0007] Obtain harmonic data of the target cable under different working conditions, and determine original characteristic data based on each harmonic data;

[0008] Performing principal component analysis on the original feature data to determine the target feature data corresponding to the original feature data;

[0009] According to the target characteristic data and the target assessment model, the degradation assessment result corresponding to the target cable is determined.

[0010] In one embodiment, performing principal component analysis on the original feature data to determine target feature data corresponding to the original feature data includes:

[0011] Performing principal component analysis on the original feature data to obtain a plurality of principal component data corresponding to the original feature data, wherein the principal component data includes a feature vector and a feature value corresponding to the feature vector;

[0012] The target feature data is determined based on each principal component data.

[0013] In one embodiment, the number of original feature data is multiple, and principal component analysis is performed on the original feature data to obtain multiple principal component data corresponding to the original feature data, including:

[0014] Obtain statistical feature data of each original feature data, and perform decentralized processing on each original feature data according to the statistical feature data to obtain a plurality of decentralized feature data;

[0015] The covariance matrix is ​​determined according to each decentralized feature data, and the eigenvalue decomposition is performed on the covariance matrix to obtain multiple eigenvectors and eigenvalues ​​corresponding to each eigenvector.

[0016] In one embodiment, determining target feature data according to each principal component data includes:

[0017] Sort the principal component data in descending order of the eigenvalues ​​to obtain a sorted sequence;

[0018] Determine multiple target principal component data from the sorted sequence;

[0019] The target feature data is determined according to the target feature vectors of each target principal component data and each decentralized data.

[0020] In one embodiment, the target assessment model is a regression model, and the degradation assessment result corresponding to the target cable is determined according to the target feature data and the target assessment model, including:

[0021] Input the target feature data into the target evaluation model to obtain the current degradation degree output by the target evaluation model;

[0022] Determine a target maintenance suggestion from multiple candidate maintenance suggestions according to the current degradation degree, and obtain the target eigenvalue of each target principal component data and the regression coefficient corresponding to the target evaluation model;

[0023] The current degradation degree, target maintenance suggestion, target characteristic values ​​and regression coefficient are taken as degradation assessment results.

[0024] In one embodiment, the method further comprises:

[0025] Obtain historical harmonic data of the target cable under various working conditions and the degree of degradation corresponding to each historical harmonic data;

[0026] Determine historical target characteristic data corresponding to each historical harmonic data according to each historical harmonic data;

[0027] According to each historical target characteristic data and the degradation degree corresponding to each historical harmonic data, the original evaluation model is trained to obtain the target evaluation model.

[0028] In a second aspect, the present application also provides a cable degradation assessment device, comprising:

[0029] An acquisition module is used to acquire harmonic data of the target cable under different working conditions and determine original characteristic data according to each harmonic data;

[0030] An analysis module is used to perform principal component analysis on the original feature data to determine the target feature data corresponding to the original feature data;

[0031] The evaluation module is used to determine the degradation evaluation result corresponding to the target cable according to the target characteristic data and the target evaluation model.

[0032] In a third aspect, an embodiment of the present application provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method of the first aspect when executing the computer program.

[0033] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the method of the first aspect described above.

[0034] In a fifth aspect, the present application further provides a computer program product, wherein the computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the method in the first aspect are implemented.

[0035] The above-mentioned cable degradation assessment method, device, equipment, readable storage medium and program product obtain the harmonic data of the target cable under different working conditions, and determine the original characteristic data according to each harmonic data, and then perform principal component analysis on the original characteristic data to determine the target characteristic data corresponding to the original characteristic data, thereby determining the degradation assessment result corresponding to the target cable according to the target characteristic data and the target assessment model. In this way, the original characteristic data corresponding to the harmonic data under different working conditions are comprehensively subjected to principal component analysis, and the obtained target characteristic data retains the main components in the data while reducing the data dimension, avoiding the problem of incomplete feature data extraction in the traditional technology of local feature extraction of harmonic data based on L1 regularization constraint, and using the target characteristic data obtained in the present application to perform cable degradation assessment, the obtained degradation assessment result is more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0037] FIG1 is a diagram showing an application environment of a cable degradation assessment method in one embodiment;

[0038] Figure 2 is a schematic flow chart of a cable degradation assessment method in one embodiment;

[0039] Figure 3 A schematic diagram of harmonic data in another embodiment;

[0040] Figure 4 is a flow chart of step 202 in another embodiment;

[0041] Figure 5 is a cumulative statistical graph of characteristic values ​​in another embodiment;

[0042] Figure 6 A statistical graph of regression coefficients in another embodiment;

[0043] Figure 7 is a structural block diagram of a cable degradation assessment device in one embodiment;

[0044] Figure 8 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0046] As the scale and complexity of power systems continue to increase, cables play an increasingly important role in power transmission and distribution. Cable degradation refers to the gradual decline in the physical and chemical properties of cables during long-term operation due to the influence of various factors. Excessive cable degradation may lead to cable failure. Among them, the degradation of the insulation layer may directly affect the safe operation of the power system and cause serious problems such as partial discharge, short circuit and fire. Therefore, it is necessary to evaluate the degree of cable degradation.

[0047] Traditional cable degradation assessment methods usually use preset regression methods, such as the Lasso regression method. This method extracts local features from high-dimensional harmonic data based on the L1 regularization constraint, and uses the extracted features to assess the degree of cable degradation. However, the L1 regularization constraint often causes some data with important physical significance to be ignored, and feature extraction is incomplete. Using the features extracted by traditional technology to assess the degree of cable degradation has the problem of low assessment accuracy.

[0048] In addition, harmonic data usually has high-dimensional characteristics, and there is a strong correlation between the harmonic components (i.e., multicollinearity). Under multicollinearity, the Lasso regression method will have unstable parameter estimation, which will also lead to poor evaluation results.

[0049] In view of this, the present application provides a cable degradation assessment method, device, equipment, readable storage medium and program product, which obtains the harmonic data of the target cable under different working conditions, and determines the original characteristic data according to each harmonic data, and then performs principal component analysis on the original characteristic data to determine the target characteristic data corresponding to the original characteristic data, thereby determining the degradation assessment result corresponding to the target cable according to the target characteristic data and the target assessment model. In this way, the original characteristic data corresponding to the harmonic data under different working conditions are comprehensively subjected to principal component analysis, and the obtained target characteristic data retains the main components in the data while reducing the data dimension, avoiding the problem of incomplete feature data extraction in the traditional technology of local feature extraction of harmonic data based on L1 regularization constraint, and using the target characteristic data obtained by the present application to perform cable degradation assessment, the obtained degradation assessment result is more accurate.

[0050] The cable degradation assessment method provided in the embodiment of the present application can be applied in the application environment shown in FIG1. ​​The data storage system can store data that the server 101 needs to process. The data storage system can be integrated on the server 101, or placed on the cloud or other network servers. The server 101 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services.

[0051] In an exemplary embodiment, Figure 2 As shown, a cable degradation assessment method is provided, which is described by taking the method applied to the server 101 in FIG. 1 as an example, and includes the following steps 201 to 203. Among them:

[0052] Step 201, obtaining harmonic data of a target cable under different working conditions, and determining original characteristic data according to each harmonic data.

[0053] The target cable is a cable to be tested and evaluated. In the embodiment of the present application, the server can obtain harmonic data of the target cable under different working conditions.

[0054] In the embodiment of the present application, the working conditions include but are not limited to different load conditions, temperature, humidity and other conditions. Harmonic data of the cable is collected under different working conditions to fully reflect the state of the cable in various actual operation scenarios.

[0055] In the embodiment of the present application, the harmonic data is data collected in real time, and the server can evaluate the current degree of degradation of the target cable by analyzing the harmonic data.

[0056] Regarding the collection of harmonic data, in one possible implementation, for a working condition, the harmonic data may include harmonic components of different frequencies. In an embodiment of the present application, the range of harmonic components acquired by the server may include a 50 Hz fundamental wave and its corresponding multiple harmonic components, such as the 3rd, 5th, and 7th harmonic components.

[0057] After acquiring different harmonic data, the server can format each harmonic data to facilitate subsequent data analysis.

[0058] Regarding the formatting method, in one possible implementation, the server may convert the collected harmonic data into a multidimensional vector form suitable for subsequent modeling. In the embodiment of the present application, each vector component corresponds to the amplitude or phase of a specific harmonic. For example, for a harmonic data containing n harmonics, it can be expressed as , where x i The amplitude or phase of the i-th harmonic.

[0059] The server can process the acquired harmonic data to extract original feature data. In the embodiment of the present application, the processing process may include normalization processing, denoising processing and feature extraction.

[0060] In a possible embodiment, in order to eliminate the magnitude difference between the data, the harmonic data may be normalized. The processing formula may refer to formula (1):

[0061] (1)

[0062] Among them, x is the original data, x' is the normalized data, and x min and x max are the minimum and maximum values ​​of the harmonic data, respectively. Through normalization, the values ​​of all harmonic components are mapped to the same scale range (such as [0,1]).

[0063] De-noising the normalized harmonic data can prevent the data from being affected by environmental noise. De-noising methods may include wavelet transform and fast Fourier transform.

[0064] For the data after normalization and denoising, the server can extract the original feature data corresponding to each harmonic data. In the embodiment of the present application, the original feature data may include the amplitude, phase and total harmonic distortion (THD) of the harmonic component.

[0065] Step 202: perform principal component analysis on the original feature data to determine target feature data corresponding to the original feature data.

[0066] After obtaining the original feature data, since the harmonic data is high-dimensional data, in order to reduce the data dimension, in an embodiment of the present application, by performing principal component analysis on the original feature data, the dimensionality reduction processing of the original feature data can be achieved, thereby avoiding the multicollinearity problem of the harmonic data and improving the accuracy of the evaluation.

[0067] Regarding the principal component analysis process, in an embodiment of the present application, the server may first convert the original feature data into low-dimensional principal component data, and then determine the target feature data based on the principal component data whose variance satisfies a preset condition.

[0068] Step 203: Determine a degradation assessment result corresponding to the target cable according to the target feature data and the target assessment model.

[0069] After obtaining the target feature data, the server can input the target feature data into a pre-trained target evaluation model to obtain a degradation evaluation result output by the target evaluation model.

[0070] Optionally, the degradation assessment result may include a quantified degree of degradation and maintenance recommendations related to the degree of degradation; optionally, the degradation assessment result may also include relevant parameters of the target assessment model and principal component parameters (e.g., variance) corresponding to the target feature data, which may be used to optimize the target assessment model.

[0071] Regarding the training process of the target evaluation model, in one possible implementation, the server can obtain the historical harmonic data of the target cable under various working conditions and the degree of degradation corresponding to each historical harmonic data, and determine the historical target feature data corresponding to each historical harmonic data based on each historical harmonic data. Then, based on each historical target feature data and the degree of degradation corresponding to each historical harmonic data, the original evaluation model is trained to obtain the target evaluation model.

[0072] Historical harmonic data can be the harmonic data corresponding to different working conditions obtained by the server at different test time points, refer to Figure 3 , which is the historical harmonic data collected for a 10kV damp-aged cable, where the test points are different time points. Figure 3 The middle is the harmonic data consisting of the 3rd harmonic, 5th harmonic and 7th harmonic collected at different time points.

[0073] After collecting the historical harmonic data, the server can process the historical harmonic data. The processing process includes formatting, normalization, denoising and feature extraction, and obtains the historical original feature data corresponding to the historical feature data. Then, these historical original feature data are subjected to component analysis to obtain the historical target feature data corresponding to each historical harmonic data. In the embodiment of the present application, the degree of degradation corresponding to each historical harmonic data is known. The server can mark each historical target feature data according to the degree of degradation corresponding to each historical harmonic data, thereby determining the degree of degradation corresponding to each historical target feature data.

[0074] After obtaining each historical target feature data and the degree of degradation corresponding to each historical target feature data, the server can construct an original evaluation model. The basic model of the original evaluation model can be a model trained by a machine learning algorithm, such as a support vector machine, a neural network, etc.

[0075] In the embodiment of the present application, the basic model of the original evaluation model may be a regression model, and the server may use the reduced-dimensional historical target feature data (Z) as an independent variable and the degree of degradation corresponding to each historical target feature data as a dependent variable Ŷ to construct the original evaluation model. The model may refer to formula (2):

[0076] (2)

[0077] Among them, β is the regression coefficient of the model, is the error term.

[0078] The server can use a cross-validation method to train the original evaluation model through each historical target feature data and the degree of degradation corresponding to each historical target feature data until the evaluation effect of the evaluation model reaches a preset condition. For example, the degree of degradation output by the evaluation model matches the degree of degradation corresponding to the director feature data. The server can then end the model training and obtain the target evaluation model.

[0079] In the above embodiment, principal component analysis is performed on the original feature data corresponding to the harmonic data under different working conditions. The obtained target feature data retains the main components in the data while reducing the data dimension, avoiding the problem of incomplete feature data extraction in the traditional technology of local feature extraction of harmonic data based on L1 regularization constraint. The target feature data obtained by the present application is used to perform cable degradation assessment, and the degradation assessment result obtained is more accurate.

[0080] In one embodiment, based on the above Figure 2 The embodiment shown, see Figure 4 This embodiment involves a process of performing principal component analysis on original feature data to determine target feature data corresponding to the original feature data. Figure 4 As shown, step 202 may include step 401 and step 402 .

[0081] Step 401 , performing principal component analysis on the original feature data to obtain a plurality of principal component data corresponding to the original feature data.

[0082] The principal component data includes eigenvectors and eigenvalues ​​corresponding to the eigenvectors.

[0083] In the embodiment of the present application, the number of original feature data may be multiple, and the server may convert each original feature data into a high-dimensional feature vector, and these high-dimensional feature vectors constitute a matrix to be subjected to principal component analysis.

[0084] Regarding the process of principal component analysis performed by the server, in one possible implementation, the server can obtain statistical feature data of each original feature data, and decentralized each original feature data based on the statistical feature data to obtain multiple decentralized feature data, and then determine the covariance matrix based on each decentralized feature data, and perform eigenvalue decomposition on the covariance matrix to obtain multiple eigenvectors and eigenvalues ​​corresponding to each eigenvector.

[0085] In the embodiment of the present application, the server may first decentralize the feature vector corresponding to the original feature data, referring to formula (3):

[0086] (3)

[0087] in, is the mean vector of the feature (i.e., statistical feature data), is the centralized data matrix.

[0088] For the decentralized feature vector, the server can calculate its corresponding covariance matrix. The specific calculation process can refer to formula (4):

[0089] (4)

[0090] in, is the covariance matrix, m is the number of samples, It is the transposed matrix of the decentralized eigenvector matrix.

[0091] After obtaining the covariance matrix, the server can perform eigenvalue decomposition on the covariance matrix to obtain multiple eigenvectors representing the direction of data change, and the eigenvalues ​​corresponding to each eigenvector. The eigenvalue represents the variance of the eigenvector. The larger the eigenvalue, the greater the degree of variation of the data in the direction indicated by the eigenvector.

[0092] The formula for eigendecomposition can refer to formula (5):

[0093] (5)

[0094] Among them, λ i is the eigenvalue, v i is the feature vector.

[0095] In this way, multiple principal component data of low dimension corresponding to the original feature data can be obtained through the above method.

[0096] Step 402, determining target feature data based on each principal component data.

[0097] After obtaining multiple principal component data, in order to enable the final target feature data to better explain the information included in the data, the server can determine the final target feature data based on the eigenvalues ​​corresponding to each principal component data. In a possible implementation, the server can sort the principal component data in descending order of the eigenvalues ​​to obtain a sorted sequence, and then determine multiple target principal component data from the sorted sequence, that is, determine the target feature data based on the target feature vectors of each target principal component data and each decentralized data.

[0098] In the embodiment of the present application, each principal component data is sorted in descending order of each eigenvalue, and multiple principal component data with larger eigenvalues ​​can be selected as target eigenvalues. In the embodiment of the present application, the server can also accumulate the eigenvalues ​​of the principal component data with the highest eigenvalues. When the accumulated result of the eigenvalues ​​exceeds a preset threshold, the server can stop accumulating and use the principal component data corresponding to the accumulated eigenvalues ​​as the target principal component data. Figure 5 , which is a statistical chart of the eigenvalues ​​corresponding to each principal component data. It can be seen that when the number of principal component data reaches 6 (i.e. the first 6 principal component data in the ranking), the cumulative result of the eigenvalue exceeds 95% (the preset threshold). At this time, the server can determine that the first 6 principal component data are the target principal component data.

[0099] After obtaining multiple target principal component data, the server can determine the target feature data according to the target feature vector of each target principal component data and each decentralized data. In the embodiment of the present application, the server can determine the target feature data according to the target feature vector of the target principal component data and each decentralized data to construct a low-dimensional data matrix. The construction method can refer to formula (6):

[0100] (6)

[0101] Where k is the number of principal component data, V kIt is a matrix composed of each target feature vector, and Z is the data matrix after dimensionality reduction, which is the target feature data.

[0102] Based on the above embodiments, in a possible implementation manner, determining a degradation assessment result corresponding to a target cable according to target characteristic data and a target assessment model may include: inputting the target characteristic data into the target assessment model to obtain the current degree of degradation output by the target assessment model, and then determining a target maintenance suggestion from multiple candidate maintenance suggestions according to the current degree of degradation, and obtaining the target characteristic value of each target principal component data and the regression coefficient corresponding to the target assessment model, and the current degree of degradation, target maintenance suggestion, each target characteristic value and the regression coefficient may be used as the degradation assessment result.

[0103] In the embodiment of the present application, the target eigenvalue can represent the influence of the corresponding principal component data on the degree of degradation, and the target evaluation model can be a regression model, and the corresponding regression coefficient can represent the influence direction of each principal component data on the degree of degradation. For example, referring to Figure 6 , is the regression coefficient corresponding to each principal component data, and the corresponding expression of the target evaluation model is:

[0104] (7)

[0105] It can be seen that the first and second principal component data have a positive impact on the degree of degradation, while the third to sixth principal component data have a negative impact on the degree of degradation.

[0106] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0107] In one embodiment, an exemplary cable degradation assessment method is provided. The method is used for a server and can be applied in the implementation environment shown in FIG. 1 .

[0108] Step a, obtaining historical harmonic data of the target cable under various working conditions and the degree of degradation corresponding to each historical harmonic data;

[0109] Step b, determining historical target characteristic data corresponding to each historical harmonic data according to each historical harmonic data;

[0110] Step c: training the original evaluation model according to each historical target feature data and the degradation degree corresponding to each historical harmonic data to obtain a target evaluation model.

[0111] Step d, obtaining harmonic data of the target cable under different working conditions, and determining original characteristic data according to each harmonic data;

[0112] The number of original feature data is multiple.

[0113] Step e: obtaining statistical feature data of each original feature data, and performing decentralized processing on each original feature data according to the statistical feature data to obtain a plurality of decentralized feature data;

[0114] Step f: determining a covariance matrix according to each decentralized feature data, and performing eigenvalue decomposition on the covariance matrix to obtain a plurality of eigenvectors and eigenvalues ​​corresponding to each eigenvector.

[0115] The principal component data includes eigenvectors and eigenvalues ​​corresponding to the eigenvectors;

[0116] Step g, sorting the principal component data in descending order of the eigenvalues ​​to obtain a sorted sequence;

[0117] Step h, determining a plurality of target principal component data from the sorted sequence;

[0118] Step i: determine the target feature data according to the target feature vectors of each target principal component data and each decentralized data.

[0119] Step j, inputting the target feature data into the target evaluation model to obtain the current degradation degree output by the target evaluation model;

[0120] Step k: determining a target maintenance suggestion from multiple candidate maintenance suggestions according to the current degradation degree, and obtaining a target eigenvalue of each target principal component data and a regression coefficient corresponding to a target evaluation model;

[0121] Step 1: The current degradation degree, target maintenance suggestion, target characteristic values ​​and regression coefficient are taken as degradation assessment results.

[0122] Among them, the target evaluation model is a regression model.

[0123] Based on the same inventive concept, the embodiment of the present application also provides a cable degradation assessment device for implementing the cable degradation assessment method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more cable degradation assessment device embodiments provided below can refer to the limitations of the cable degradation assessment method above, and will not be repeated here.

[0124] In an exemplary embodiment, Figure 7 As shown, a cable degradation assessment device is provided, including: an acquisition module 701, an analysis module 702 and an assessment module 703, wherein:

[0125] An acquisition module 701 is used to acquire harmonic data of a target cable under different working conditions, and determine original characteristic data according to each harmonic data;

[0126] An analysis module 702 is used to perform principal component analysis on the original feature data to determine target feature data corresponding to the original feature data;

[0127] The evaluation module 703 is used to determine the degradation evaluation result corresponding to the target cable according to the target characteristic data and the target evaluation model.

[0128] In one embodiment, the analysis module 702 includes:

[0129] A principal component analysis unit is used to perform principal component analysis on the original feature data to obtain a plurality of principal component data corresponding to the original feature data, wherein the principal component data includes a feature vector and a feature value corresponding to the feature vector;

[0130] The determination unit is used to determine the target characteristic data according to each principal component data.

[0131] In one embodiment, the number of original feature data is multiple, and the principal component analysis unit is specifically used to perform:

[0132] Obtain statistical feature data of each original feature data, and perform decentralized processing on each original feature data according to the statistical feature data to obtain a plurality of decentralized feature data;

[0133] The covariance matrix is ​​determined according to each decentralized feature data, and the eigenvalue decomposition is performed on the covariance matrix to obtain multiple eigenvectors and eigenvalues ​​corresponding to each eigenvector.

[0134] In one embodiment, the determining unit is specifically configured to perform:

[0135] Sort the principal component data in descending order of the eigenvalues ​​to obtain a sorted sequence;

[0136] Determine multiple target principal component data from the sorted sequence;

[0137] The target feature data is determined according to the target feature vectors of each target principal component data and each decentralized data.

[0138] In one embodiment, the target evaluation model is a regression model, and the evaluation module 703 includes:

[0139] An input unit, used to input target feature data into a target evaluation model to obtain a current degradation degree output by the target evaluation model;

[0140] A result acquisition unit, used to determine a target maintenance suggestion from a plurality of candidate maintenance suggestions according to the current degradation degree, and to obtain a target characteristic value of each target principal component data and a regression coefficient corresponding to a target evaluation model;

[0141] The result unit is used to take the current degradation degree, target maintenance suggestion, each target characteristic value and regression coefficient as the degradation assessment result.

[0142] In one embodiment, the apparatus further comprises:

[0143] A history acquisition module is used to obtain the historical harmonic data of the target cable under various working conditions and the degree of degradation corresponding to each historical harmonic data;

[0144] A historical determination module, used to determine historical target characteristic data corresponding to each historical harmonic data according to each historical harmonic data;

[0145] The training module is used to train the original evaluation model according to each historical target feature data and the degradation degree corresponding to each historical harmonic data to obtain a target evaluation model.

[0146] Each module in the above cable degradation assessment device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0147] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 8As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store cable degradation assessment data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a cable degradation assessment method is implemented.

[0148] Those skilled in the art will understand that Figure 8 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0149] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0150] Acquire harmonic data of the target cable under different working conditions, and determine original characteristic data according to each of the harmonic data;

[0151] Performing principal component analysis on the original feature data to determine target feature data corresponding to the original feature data;

[0152] A degradation assessment result corresponding to the target cable is determined according to the target feature data and the target assessment model.

[0153] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0154] Performing principal component analysis on the original feature data to obtain a plurality of principal component data corresponding to the original feature data, wherein the principal component data includes a feature vector and a feature value corresponding to the feature vector;

[0155] The target feature data is determined according to each of the principal component data.

[0156] In one embodiment, the number of the original feature data is multiple, and the processor further implements the following steps when executing the computer program:

[0157] Obtaining statistical feature data of each of the original feature data, and performing decentralized processing on each of the original feature data according to the statistical feature data to obtain a plurality of decentralized feature data;

[0158] A covariance matrix is ​​determined according to each of the decentralized feature data, and eigenvalue decomposition is performed on the covariance matrix to obtain a plurality of eigenvectors and eigenvalues ​​corresponding to each of the eigenvectors.

[0159] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0160] Sorting the principal component data in descending order of the eigenvalues ​​to obtain a sorted sequence;

[0161] Determining a plurality of target principal component data from the sorted sequence;

[0162] The target feature data is determined according to the target feature vector of each target principal component data and each decentralized data.

[0163] In one embodiment, the target evaluation model is a regression model, and the processor further implements the following steps when executing the computer program:

[0164] Inputting the target feature data into the target evaluation model to obtain the current degradation degree output by the target evaluation model;

[0165] Determining a target maintenance suggestion from a plurality of candidate maintenance suggestions according to the current degradation degree, and obtaining a target eigenvalue of each target principal component data and a regression coefficient corresponding to the target evaluation model;

[0166] The current degradation degree, the target maintenance suggestion, each target characteristic value and the regression coefficient are used as the degradation assessment result.

[0167] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0168] Obtaining historical harmonic data of the target cable under each of the working conditions and a degree of degradation corresponding to each of the historical harmonic data;

[0169] Determine historical target characteristic data corresponding to each of the historical harmonic data according to each of the historical harmonic data;

[0170] The original evaluation model is trained according to the degradation degree corresponding to each of the historical target feature data and each of the historical harmonic data to obtain the target evaluation model.

[0171] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0172] Acquire harmonic data of the target cable under different working conditions, and determine original characteristic data according to each of the harmonic data;

[0173] Performing principal component analysis on the original feature data to determine target feature data corresponding to the original feature data;

[0174] A degradation assessment result corresponding to the target cable is determined according to the target feature data and the target assessment model.

[0175] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0176] Performing principal component analysis on the original feature data to obtain a plurality of principal component data corresponding to the original feature data, wherein the principal component data includes a feature vector and a feature value corresponding to the feature vector;

[0177] The target feature data is determined according to each of the principal component data.

[0178] In one embodiment, the number of the original feature data is multiple, and when the computer program is executed by the processor, the following steps are also implemented:

[0179] Obtaining statistical feature data of each of the original feature data, and performing decentralized processing on each of the original feature data according to the statistical feature data to obtain a plurality of decentralized feature data;

[0180] A covariance matrix is ​​determined according to each of the decentralized feature data, and eigenvalue decomposition is performed on the covariance matrix to obtain a plurality of eigenvectors and eigenvalues ​​corresponding to each of the eigenvectors.

[0181] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0182] Sorting the principal component data in descending order of the eigenvalues ​​to obtain a sorted sequence;

[0183] Determining a plurality of target principal component data from the sorted sequence;

[0184] The target feature data is determined according to the target feature vector of each target principal component data and each decentralized data.

[0185] In one embodiment, the target evaluation model is a regression model, and the computer program, when executed by a processor, further implements the following steps:

[0186] Inputting the target feature data into the target evaluation model to obtain the current degradation degree output by the target evaluation model;

[0187] Determining a target maintenance suggestion from a plurality of candidate maintenance suggestions according to the current degradation degree, and obtaining a target eigenvalue of each target principal component data and a regression coefficient corresponding to the target evaluation model;

[0188] The current degradation degree, the target maintenance suggestion, each target characteristic value and the regression coefficient are used as the degradation assessment result.

[0189] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0190] Obtaining historical harmonic data of the target cable under each of the working conditions and a degree of degradation corresponding to each of the historical harmonic data;

[0191] Determine historical target characteristic data corresponding to each of the historical harmonic data according to each of the historical harmonic data;

[0192] The original evaluation model is trained according to the degradation degree corresponding to each of the historical target feature data and each of the historical harmonic data to obtain the target evaluation model.

[0193] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0194] Acquire harmonic data of the target cable under different working conditions, and determine original characteristic data according to each of the harmonic data;

[0195] Performing principal component analysis on the original feature data to determine target feature data corresponding to the original feature data;

[0196] A degradation assessment result corresponding to the target cable is determined according to the target feature data and the target assessment model.

[0197] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0198] Performing principal component analysis on the original feature data to obtain a plurality of principal component data corresponding to the original feature data, wherein the principal component data includes a feature vector and a feature value corresponding to the feature vector;

[0199] The target feature data is determined according to each of the principal component data.

[0200] In one embodiment, the number of the original feature data is multiple, and when the computer program is executed by the processor, the following steps are also implemented:

[0201] Obtaining statistical feature data of each of the original feature data, and performing decentralized processing on each of the original feature data according to the statistical feature data to obtain a plurality of decentralized feature data;

[0202] A covariance matrix is ​​determined according to each of the decentralized feature data, and eigenvalue decomposition is performed on the covariance matrix to obtain a plurality of eigenvectors and eigenvalues ​​corresponding to each of the eigenvectors.

[0203] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0204] Sorting the principal component data in descending order of the eigenvalues ​​to obtain a sorted sequence;

[0205] Determining a plurality of target principal component data from the sorted sequence;

[0206] The target feature data is determined according to the target feature vector of each target principal component data and each decentralized data.

[0207] In one embodiment, the target evaluation model is a regression model, and the computer program, when executed by a processor, further implements the following steps:

[0208] Inputting the target feature data into the target evaluation model to obtain the current degradation degree output by the target evaluation model;

[0209] Determining a target maintenance suggestion from a plurality of candidate maintenance suggestions according to the current degradation degree, and obtaining a target eigenvalue of each target principal component data and a regression coefficient corresponding to the target evaluation model;

[0210] The current degradation degree, the target maintenance suggestion, each target characteristic value and the regression coefficient are used as the degradation assessment result.

[0211] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0212] Obtaining historical harmonic data of the target cable under each of the working conditions and a degree of degradation corresponding to each of the historical harmonic data;

[0213] Determine historical target characteristic data corresponding to each of the historical harmonic data according to each of the historical harmonic data;

[0214] The original evaluation model is trained according to the degradation degree corresponding to each of the historical target feature data and each of the historical harmonic data to obtain the target evaluation model.

[0215] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0216] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0217] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0218] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A cable degradation assessment method, characterized in that: The method comprises: Acquire harmonic data of the target cable under different working conditions, and determine original characteristic data according to each of the harmonic data; Performing principal component analysis on the original feature data to determine target feature data corresponding to the original feature data; A degradation assessment result corresponding to the target cable is determined according to the target feature data and the target assessment model.

2. The method according to claim 1, characterized in that The performing principal component analysis on the original feature data to determine the target feature data corresponding to the original feature data includes: Performing principal component analysis on the original feature data to obtain a plurality of principal component data corresponding to the original feature data, wherein the principal component data includes a feature vector and a feature value corresponding to the feature vector; The target feature data is determined according to each of the principal component data.

3. The method according to claim 2, characterized in that The number of the original feature data is multiple, and the principal component analysis is performed on the original feature data to obtain multiple principal component data corresponding to the original feature data, including: Obtaining statistical feature data of each of the original feature data, and performing decentralized processing on each of the original feature data according to the statistical feature data to obtain a plurality of decentralized feature data; A covariance matrix is ​​determined according to each of the decentralized feature data, and eigenvalue decomposition is performed on the covariance matrix to obtain a plurality of eigenvectors and eigenvalues ​​corresponding to each of the eigenvectors.

4. The method according to claim 3, characterized in that The determining the target feature data according to each of the principal component data comprises: Sorting the principal component data in descending order of the eigenvalues ​​to obtain a sorted sequence; Determining a plurality of target principal component data from the sorted sequence; The target feature data is determined according to the target feature vector of each target principal component data and each decentralized data.

5. The method according to claim 3, characterized in that: The target evaluation model is a regression model, and determining the degradation evaluation result corresponding to the target cable according to the target feature data and the target evaluation model includes: Inputting the target feature data into the target evaluation model to obtain the current degradation degree output by the target evaluation model; Determining a target maintenance suggestion from a plurality of candidate maintenance suggestions according to the current degradation degree, and obtaining a target eigenvalue of each target principal component data and a regression coefficient corresponding to the target evaluation model; The current degradation degree, the target maintenance suggestion, each target characteristic value and the regression coefficient are used as the degradation assessment result.

6. The method according to claim 1, characterized in that The method further comprises: Obtaining historical harmonic data of the target cable under each of the working conditions and a degree of degradation corresponding to each of the historical harmonic data; Determine historical target characteristic data corresponding to each of the historical harmonic data according to each of the historical harmonic data; The original evaluation model is trained according to the degradation degree corresponding to each of the historical target feature data and each of the historical harmonic data to obtain the target evaluation model.

7. A cable degradation assessment device, characterized in that: The device comprises: An acquisition module is used to acquire harmonic data of the target cable under different working conditions, and determine original characteristic data according to each of the harmonic data; An analysis module, used to perform principal component analysis on the original feature data to determine target feature data corresponding to the original feature data; An evaluation module is used to determine a degradation evaluation result corresponding to the target cable according to the target characteristic data and the target evaluation model.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images