Power transformation equipment health state comprehensive evaluation method, system and equipment and storage medium

Abstract

The invention discloses a comprehensive assessment method, system and equipment for a health state of power transformation equipment and a storage medium, and the method comprises the steps: collecting the related data of the power transformation equipment, including the voltage, current, power and service life of the power transformation equipment, and the environment temperature and humidity of the power transformation equipment, carrying out the preprocessing of the collected related data of the power transformation equipment, including data cleaning and missing value filling operation; feature extraction is carried out on the related data of the preprocessed power transformation equipment, dimensionality reduction and screening are carried out on the extracted features, feature parameters with the influence on the health state of the equipment larger than a contribution degree threshold value are selected, a health state evaluation model of the power transformation equipment is constructed, and the health state of the power transformation equipment is evaluated. According to the invention, the healthy operation of the power transformation equipment is ensured, so that the safety and stability of the whole power grid system are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of power systems, relates to health status assessment of substation equipment, and is a comprehensive health status assessment method, system, equipment and storage medium for substation equipment. Background Art

[0002] With the rapid development of power systems, substation equipment, as an important part of the power system, is directly related to the safe operation and power supply reliability of the power grid. Traditional substation equipment maintenance mostly relies on regular inspections and patrols, but this method has certain limitations and cannot timely and accurately reflect the actual health status of the equipment. It may lead to equipment failures not being warned in advance, thus affecting the stability and security of the power grid.

[0003] Current health status assessment methods for substation equipment are mainly based on the electrical, mechanical and environmental parameters of the equipment, such as load, voltage, current, temperature, insulation status, vibration characteristics, etc. However, traditional health assessment methods mainly rely on certain key parameters or simple mathematical models, and fail to fully consider the multi-dimensional information and complex influencing factors during the operation of the equipment, resulting in one-sided or inaccurate assessment results. Based on the above background, a comprehensive health status assessment method for substation equipment is proposed, which aims to comprehensively and accurately assess the health status of the equipment through multi-source data fusion, advanced machine learning algorithms and expert systems, so as to provide decision support for power grid operation and improve the management level and maintenance efficiency of substation equipment.

[0004] For example, a Chinese patent application with publication number CN115859594A discloses a health assessment algorithm for substation equipment based on hierarchical analysis. The steps of the method include: dividing the corresponding components according to the degree of belonging of the same substation equipment, and each component corresponds to the index data of the specified component in turn; respectively obtaining the real-time index data and historical index data of each component, and performing data preprocessing, processing the historical index data of each component through the SOM self-organizing neural network model, and then combining the real-time index data of each component to calculate according to the principle of minimum Euclidean distance to obtain the health value of each component; combining the health value calculation of each component to obtain the health value of the substation equipment to which it belongs, and completing the health assessment of the substation equipment.

[0005] For example, the Chinese patent with the authorization announcement number CN107992678B discloses a transformer health status evaluation method and device based on the whole life cycle, which involves the technical field of substation equipment and solves the problem that in the prior art, when evaluating the health status of the transformer, the health status of the current transformer is evaluated by over-reliance on some of the most important aspects with a relatively large weight, such as short-circuit strength, load capacity, insulation aging, and electrical characteristics, resulting in the evaluation result being relatively one-sided and difficult to accurately reflect the health status of the current transformer. The method includes obtaining the initial state parameters of the transformer; obtaining the aging parameters of the transformer; obtaining the operating value parameters of the transformer; calculating the health status evaluation score of the transformer according to the initial state parameters, aging parameters, operating value parameters, and the health status evaluation score model; and generating the health status evaluation result of the transformer according to the health status evaluation score.

[0006] The defects of the above scheme are: excessive reliance on data from more levels or parts of substation equipment; reliance on aging parameters to evaluate the health status of the transformer. When faced with sudden failures or drastic changes in status, it may not be able to reflect the latest health status of the equipment in a timely manner, affecting the final health assessment value. Summary of the invention

[0007] In view of the shortcomings of the prior art, the present invention proposes a comprehensive assessment method and system for the health status of substation equipment based on data analysis, which collects relevant data of the substation equipment, including the voltage, current, power and service life of the substation equipment, and the ambient temperature and humidity of the substation equipment. The collected relevant data of the substation equipment are preprocessed, including data cleaning and missing value filling operations, and feature extraction is performed on the relevant data of the preprocessed substation equipment. The extracted features are reduced in dimension and screened, and feature parameters whose impact on the health status of the equipment is greater than a contribution threshold are selected to construct a health status assessment model for the substation equipment to evaluate the health status of the substation equipment.

[0008] The technical solution of the present invention is: a comprehensive evaluation method for the health status of a substation equipment, which evaluates the health status of the substation equipment based on data analysis of the substation equipment, comprising the following steps:

[0009] Step S1: Collect relevant data of the substation equipment, including the voltage, current, power and service life of the substation equipment, as well as the ambient temperature and humidity of the substation equipment;

[0010] Step S2: preprocessing the collected data related to the substation equipment, including data cleaning and missing value filling operations;

[0011] Step S3: extracting features from relevant data of the pre-processed substation equipment;

[0012] Step S4: reducing the dimension and screening the extracted features, and selecting the feature parameters whose influence on the health status of the equipment is greater than the contribution threshold;

[0013] Step S5: construct a health status assessment model for the substation equipment to assess the health status of the substation equipment.

[0014] Furthermore, the specific steps of step S3 are:

[0015] Step S301: setting a set of relevant data of the pre-processed substation equipment as A, extracting time domain features and frequency domain features of the set A, and splicing the extracted time domain features and frequency domain features into a feature matrix X;

[0016] Step S302: Standardize the feature data in the feature matrix X to obtain a standardized feature matrix Z. The calculation formula is:

[0017]

[0018] Among them, z ij represents the jth eigenvalue of the i-th feature type in the standardized feature matrix Z, x ij represents the jth eigenvalue of the i-th feature type in the feature matrix X, τ i represents the mean eigenvalue of the i-th feature type, σ i Represents the standard deviation of the eigenvalues ​​of the i-th feature type;

[0019] Step S303: Calculate the covariance matrix of the standardized feature matrix Z, and the calculation formula is:

[0020]

[0021] Among them, C represents the covariance matrix of the standardized feature matrix Z, n represents the number of feature types, and z i Represents the eigenvector of the i-th feature type in the standardized feature matrix Z, represents the mean of the standardized eigenvalues;

[0022] Step S304: Calculate the eigenvalues ​​and eigenvectors of the covariance matrix C. The calculation formula is:

[0023] Cv=λv,

[0024] Among them, λ represents the eigenvalue of the covariance matrix C, and v represents the eigenvector of the covariance matrix C.

[0025] Furthermore, the time domain features in step S301 include: mean, root mean square value, skewness and kurtosis, and the frequency domain features include: power spectrum density, frequency center and spectrum energy.

[0026] Furthermore, the specific steps of step S4 include:

[0027] Step S401: Select the eigenvectors corresponding to the first k largest eigenvalues, and construct the k eigenvectors into a dimensionality-reduced feature space v k ;

[0028] Step S402: The feature space v after dimensionality reduction k Projected into the standardized feature matrix Z, the calculation formula is: Y = Zv k , where Y represents the feature matrix after dimensionality reduction;

[0029] Step S403: Calculate the contribution of the original features in the feature matrix after dimensionality reduction. The calculation formula is: W represents the contribution of the original features in the feature matrix after dimensionality reduction. Represents the feature space v after dimensionality reduction k The transpose of

[0030] Step S404: Set a contribution threshold, select the eigenvalues ​​corresponding to the values ​​in W that are greater than the contribution threshold in the feature matrix Y after dimensionality reduction, and construct the final feature matrix y.

[0031] Furthermore, the specific steps of step S5 are:

[0032] Step S501: using the labeled historical data, using the support vector machine algorithm to train the health assessment model of the substation equipment, and using the cross-validation method to evaluate the model performance;

[0033] Step S502: Calculate the health status index of the substation equipment, the calculation formula is:

[0034]

[0035] Where Jk represents the health status index of the substation equipment, κ1, κ2, κ3, κ4, κ5 and κ6 represent weight coefficients, represents the standardized function, V represents the voltage characteristics of the substation equipment, ln() represents the logarithmic function, e represents the exponential function, I represents the current characteristics of the substation equipment, P represents the power characteristics of the substation equipment, T represents the ambient temperature characteristics of the substation equipment, H represents the ambient humidity characteristics of the substation equipment, S represents the service life of the substation equipment, β represents the smoothing parameter, ε and γ represent the adjustment parameters, and SVM() represents the output of the health assessment model of the substation equipment.

[0036] The present invention also provides a comprehensive evaluation system for the health status of substation equipment based on data analysis, which is used to implement the above-mentioned comprehensive evaluation method for the health status of substation equipment, including: a data acquisition module, a preprocessing module, a feature extraction module, a feature processing module and a health evaluation module;

[0037] The data acquisition module is used to collect relevant data of the substation equipment, including the voltage, current, power and service life of the substation equipment, and the ambient temperature and humidity of the substation equipment;

[0038] The preprocessing module is used to preprocess the collected data related to the substation equipment, including data cleaning and missing value filling operations;

[0039] The feature extraction module is used to extract features from the relevant data of the pre-processed substation equipment;

[0040] The feature processing module is used to reduce the dimension and filter the extracted features, and select feature parameters whose influence on the health status of the equipment is greater than the contribution threshold;

[0041] The health assessment module is used to construct a health status assessment model for the substation equipment and to assess the health status of the substation equipment.

[0042] Furthermore, the feature processing module includes: a feature dimension reduction unit and a feature screening unit;

[0043] The feature dimension reduction unit is used to reduce the dimension of the extracted substation equipment feature matrix;

[0044] The feature screening unit is used to perform contribution screening on the reduced dimension substation feature matrix, and screen out features whose contribution is higher than a contribution threshold.

[0045] The present invention also provides an electronic device, comprising a memory and a processor, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or at least one program is loaded and executed by the processor to implement the above-mentioned comprehensive assessment method for the health status of substation equipment.

[0046] The present invention also provides a computer-readable storage medium, in which at least one instruction or at least one program is stored. When the at least one instruction or at least one program is executed, the above-mentioned comprehensive evaluation method for the health status of substation equipment is implemented.

[0047] Compared with the prior art, the present invention has the following beneficial effects:

[0048] 1. The present invention proposes a comprehensive assessment method for the health status of substation equipment based on data analysis. Through real-time data and historical data analysis technology and machine learning algorithms, the assessment model is continuously optimized to make the health status assessment more accurate.

[0049] 2. The present invention proposes a comprehensive evaluation method for the health status of substation equipment based on data analysis, which collects and analyzes data in real time and can monitor the operating status of equipment in real time. Based on the health status evaluation results, a more accurate maintenance plan can be formulated to avoid unnecessary downtime and excessive maintenance.

[0050] 3. The present invention proposes a comprehensive assessment method for the health status of substation equipment based on data analysis. Through health status assessment, it can provide early warning of equipment failures, avoid safety accidents caused by sudden equipment failures, ensure the healthy operation of substation equipment, and thus improve the safety and stability of the entire power grid system. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 A flow chart of a comprehensive evaluation method for health status of substation equipment based on data analysis provided by the present invention;

[0052] Figure 2 The architecture diagram of the comprehensive evaluation system for health status of substation equipment based on data analysis provided by the present invention;

[0053] Figure 3 A schematic diagram of an electronic device for a comprehensive health status assessment method for substation equipment based on data analysis provided by the present invention;

[0054] Figure 4 A schematic diagram of the computer-readable storage medium structure of the comprehensive evaluation method for health status of substation equipment based on data analysis provided by the present invention. DETAILED DESCRIPTION

[0055] The present invention is further described below in conjunction with specific implementation methods.

[0056] Example 1

[0057] See also Figure 1 The present invention provides an embodiment: a comprehensive evaluation method for the health status of substation equipment based on data analysis, comprising the following specific steps:

[0058] Step S1: collecting real-time data of the substation equipment, including the voltage, current, power and service life of the substation equipment, and the ambient temperature and humidity of the substation equipment;

[0059] Step S2: preprocessing the collected data related to the substation equipment, including data cleaning and missing value filling operations;

[0060] Step S3: extracting features from relevant data of the pre-processed substation equipment;

[0061] The specific steps of step S3 are:

[0062] Step S301: The set of relevant data of the substation equipment after preprocessing is A, the time domain features and frequency domain features of the set A are extracted, and the extracted time domain features and frequency domain features are spliced ​​into a feature matrix X;

[0063] The time domain features in step S301 include: mean, root mean square value, skewness and kurtosis.

[0064] Frequency domain features include: power spectral density, frequency center and spectrum energy.

[0065] The time domain features and the frequency domain features are calculated using formulas in the prior art.

[0066] Step S302: Standardize the feature data in the feature matrix X to obtain a standardized feature matrix Z. The calculation formula is:

[0067]

[0068] Among them, z ij represents the jth eigenvalue of the i-th feature type in the standardized feature matrix Z, x ij represents the jth eigenvalue of the i-th feature type in the feature matrix X, τ i represents the mean eigenvalue of the i-th feature type, σ i Represents the standard deviation of the eigenvalues ​​of the i-th feature type;

[0069] Step S303: Calculate the covariance matrix of the standardized feature matrix Z, and the calculation formula is:

[0070]

[0071] Among them, C represents the covariance matrix of the standardized feature matrix Z, n represents the number of feature types, and z i represents the eigenvector of the i-th feature type in the standardized feature matrix Z, represents the mean of the standardized eigenvalues;

[0072] Step S304: Calculate the eigenvalues ​​and eigenvectors of the covariance matrix C. The calculation formula is:

[0073] Cv=λv,

[0074] Among them, λ represents the eigenvalue of the covariance matrix C, and v represents the eigenvector of the covariance matrix C.

[0075] Step S4: Reduce the dimension and filter the extracted features to select feature parameters whose impact on the health status of the equipment is greater than the contribution threshold; the contribution threshold here is set according to actual needs.

[0076] The specific steps of step S4 also include:

[0077] Step S401: According to the eigenvalues ​​and eigenvectors obtained in step 304, select the eigenvectors corresponding to the first k largest eigenvalues, and construct the k eigenvectors into a dimensionality-reduced feature space v k ;

[0078] Step S402: The feature space v after dimensionality reduction k Projected into the standardized feature matrix Z, the calculation formula is: Y = Zv k , where Y represents the feature matrix after dimensionality reduction;

[0079] Step S403: Calculate the contribution of the original features in the feature matrix after dimensionality reduction. The calculation formula is: W represents the contribution of the original features in the feature matrix after dimensionality reduction. Represents the feature space v after dimensionality reduction k The transpose of

[0080] Step S404: Set a contribution threshold, select the eigenvalues ​​corresponding to the values ​​in W that are greater than the contribution threshold in the feature matrix Y after dimensionality reduction, and construct the final feature matrix y.

[0081] Step S5: construct a health status assessment model for the substation equipment to assess the health status of the substation equipment. The specific steps are as follows:

[0082] Step S501: using the labeled historical data, using the support vector machine algorithm to train the health assessment model of the substation equipment, and using the cross-validation method to evaluate the model performance;

[0083] Step S502: Calculate the health status index of the substation equipment, the calculation formula is:

[0084]

[0085] Where Jk represents the health status index of the substation equipment, κ1, κ2, κ3, κ4, κ5 and κ6 represent weight coefficients, represents the normalization function, V represents the voltage characteristics of the substation, ln() represents the logarithmic function, e represents the exponential function, I represents the current characteristics of the substation, P represents the power characteristics of the substation, T represents the ambient temperature characteristics of the substation, H represents the ambient humidity characteristics of the substation, S represents the service life of the substation, β represents the smoothing parameter, ε and γ represent the adjustment parameters, and SVM() represents the output of the health assessment model of the substation. The voltage characteristics V, current characteristics I, power characteristics P, ambient temperature characteristics T, ambient humidity characteristics H and service life S are all from the real-time data of the substation, and the health status index corresponds to the health status. The larger the Jk value, the higher the health level.

[0086] Explanation of the parameters in the health status index formula of substation equipment: It is to standardize the voltage to prevent the dimension effect, and ln(I+1) is to smooth the current logarithm to avoid the influence of too large a range on the evaluation result. It takes into account the ratio of power and temperature, reflecting the operating efficiency of the equipment. -εH It is the exponential decay effect of humidity, simulating the negative impact of high humidity on the equipment. SVM(y) is the health status score output by the SVM support vector machine model, integrating multi-dimensional information.

[0087] The weight coefficients κ1, κ2, κ3, κ4, κ5 and κ6 are obtained by persons skilled in the art through simulation experiments, or are set according to the demand for attention to the equipment status parameters.

[0088] The evaluation model is built by training with historical data, and then the real-time data is processed through steps S1-S4 and input into the health status evaluation model to evaluate the health status of the substation equipment.

[0089] Example 2

[0090] See also Figure 2 Another embodiment provided by the present invention is a comprehensive evaluation system for health status of substation equipment based on data analysis, comprising:

[0091] Data acquisition module, preprocessing module, feature extraction module, feature processing module and health assessment module;

[0092] The data acquisition module is used to collect relevant data of the substation equipment, including the voltage, current, power and service life of the substation equipment, and the ambient temperature and humidity of the substation equipment;

[0093] The preprocessing module is used to preprocess the collected data related to the substation equipment, including data cleaning and missing value filling operations;

[0094] The feature extraction module is used to extract features from the relevant data of the pre-processed substation equipment;

[0095] The feature processing module is used to reduce the dimension and filter the extracted features, and select feature parameters whose influence on the health status of the equipment is greater than the contribution threshold;

[0096] The health assessment module is used to construct a health status assessment model for the substation equipment and to assess the health status of the substation equipment.

[0097] The feature processing module includes: a feature dimension reduction unit and a feature screening unit;

[0098] The feature dimension reduction unit is used to reduce the dimension of the extracted substation equipment feature matrix;

[0099] The feature screening unit is used to perform contribution screening on the reduced dimension substation feature matrix, and screen out features whose contribution is higher than a contribution threshold.

[0100] Example 3

[0101] Figure 3 1 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present application. Figure 3 As shown, according to another aspect of the present application, an electronic device 500 is also provided. The electronic device 500 may include one or more processors and one or more memories. The memories store computer readable codes, and when the computer readable codes are executed by one or more processors, a comprehensive evaluation method for the health status of a substation equipment based on data analysis may be executed.

[0102] The method or system according to the embodiment of the present application can also be Figure 3 The electronic device architecture shown in FIG. Figure 3As shown, the electronic device 500 may include a bus 501, one or more CPUs 502, ROM 503, RAM 504, a communication port 505 connected to a network, an input / output component 506, a hard disk 507, and the like. The storage device in the electronic device 500, such as ROM 503 or hard disk 507, may store the comprehensive evaluation method for the health status of substation equipment based on data analysis provided in the present application. The comprehensive evaluation method for the health status of substation equipment based on data analysis may, for example, include: collecting relevant data of the substation equipment, including the voltage, current, power and service life of the substation equipment, the ambient temperature and humidity of the substation equipment, preprocessing the collected relevant data of the substation equipment, including data cleaning and missing value filling operations, extracting features from the relevant data of the substation equipment after preprocessing, reducing the dimension and screening the extracted features, selecting feature parameters whose impact on the health status of the equipment is greater than the contribution threshold, constructing a health status evaluation model for the substation equipment, and evaluating the health status of the substation equipment. Furthermore, the electronic device 500 may also include a user interface 508. Of course, Figure 3 The architecture shown is only exemplary and can be omitted according to actual needs when implementing different devices. Figure 3 One or more components of an electronic device are shown.

[0103] Example 4

[0104] Figure 4 Schematic diagram of a computer-readable storage medium structure provided by an embodiment of the present application. Figure 4 As shown, a computer-readable storage medium 600 according to an embodiment of the present application is shown. Computer-readable instructions are stored on the computer-readable storage medium 600. When the computer-readable instructions are executed by the processor, the comprehensive evaluation method for the health status of substation equipment based on data analysis according to the embodiment of the present application described with reference to the above figures can be executed. The storage medium 600 includes, but is not limited to, for example, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory (cache), etc. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc.

[0105] It should be understood that the methods, apparatuses, and devices of the present application can be implemented in many ways. For example, the methods, apparatuses, and devices of the present application can be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above order of steps for the method is only for illustration, and the steps of the method of the present application are not limited to the order specifically described above unless otherwise specified. In addition, in some embodiments, the present application can also be implemented as a program recorded in a recording medium, which includes machine-readable instructions for implementing the method according to the present application. Therefore, the present application also covers a recording medium storing a program for executing the method according to the present application.

[0106] In addition, the parts of the above-mentioned technical solutions provided in the embodiments of the present application that are consistent with the implementation principles of the corresponding technical solutions in the prior art are not described in detail to avoid excessive redundancy.

[0107] The specific implementation modes as described above further describe the purpose, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation mode of the present invention and is not intended to limit the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A comprehensive evaluation method for the health status of substation equipment, characterized by: The health status of the substation equipment is evaluated based on the data analysis of the substation equipment, including the following steps: Step S1: collecting real-time data of the substation equipment, including the voltage, current, and power of the substation equipment, and collecting the service life of the substation equipment, as well as the ambient temperature and humidity of the substation equipment; Step S2: preprocessing the collected real-time data of the substation equipment, including data cleaning and missing value filling operations; Step S3: extracting features from the pre-processed data of the substation equipment; Step S4: reducing the dimension and screening the extracted features, and selecting the feature parameters whose influence on the health status of the equipment is greater than the contribution threshold; Step S5: construct and train a health status assessment model for the substation equipment, and assess the health status of the substation equipment based on the characteristic parameters obtained in step S4.

2. The comprehensive evaluation method for the health status of substation equipment according to claim 1 is characterized by: The specific steps of step S3 are: Step S301: Assume that a set of data of the preprocessed substation equipment is A, extract the time domain features and frequency domain features of the set A, and splice the extracted time domain features and frequency domain features into a feature matrix X; Step S302: Standardize the feature data in the feature matrix X to obtain a standardized feature matrix Z. The calculation formula is: Among them, z ij represents the jth eigenvalue of the i-th feature type in the standardized feature matrix Z, x ij represents the jth eigenvalue of the i-th feature type in the feature matrix X, τ i represents the mean eigenvalue of the i-th feature type, σ i Indicates the standard deviation of the eigenvalues ​​of the i-th feature type; Step S303: Calculate the covariance matrix of the standardized feature matrix Z, and the calculation formula is: Among them, C represents the covariance matrix of the standardized feature matrix Z, n represents the number of feature types, and z i Represents the eigenvector of the i-th feature type in the standardized feature matrix Z, represents the mean of the standardized eigenvalues; Step S304: Calculate the eigenvalues ​​and eigenvectors of the covariance matrix C. The calculation formula is: Cv=λv, Among them, λ represents the eigenvalue of the covariance matrix C, and v represents the eigenvector of the covariance matrix C.

3. The comprehensive evaluation method for the health status of substation equipment according to claim 2 is characterized by: The time domain features in step S301 include: mean, root mean square value, skewness and kurtosis, and the frequency domain features include: power spectrum density, frequency center and spectrum energy.

4. The comprehensive evaluation method for the health status of substation equipment according to claim 2 is characterized by: The specific steps of step S4 include: Step S401: Select the eigenvectors corresponding to the first k largest eigenvalues, and construct the k eigenvectors into a dimensionality-reduced feature space v k ; Step S402: The feature space v after dimensionality reduction k Projected into the standardized feature matrix Z, the calculation formula is: Y = Zv k , where Y represents the feature matrix after dimensionality reduction; Step S403: Calculate the contribution of the original features in the feature matrix after dimensionality reduction. The calculation formula is: W represents the contribution of the original features in the feature matrix after dimensionality reduction. Represents the feature space v after dimensionality reduction k The transpose of Step S404: Set a contribution threshold, select the eigenvalues ​​corresponding to the values ​​in W that are greater than the contribution threshold in the feature matrix Y after dimensionality reduction, and construct the final feature matrix y.

5. The comprehensive evaluation method for the health status of substation equipment according to claim 4 is characterized in that The specific steps of step S5 are: Step S501: using the labeled historical data, training a health assessment model for substation equipment based on a support vector machine, and using a cross-validation method to evaluate the model performance; Step S502: Calculate the health status index of the substation equipment, the calculation formula is: Where Jk represents the health status index of the substation equipment, κ1, κ2, κ3, κ4, κ5 and κ6 represent weight coefficients, represents the standardized function, V represents the voltage characteristics of the substation equipment, ln() represents the logarithmic function, e represents the exponential function, I represents the current characteristics of the substation equipment, P represents the power characteristics of the substation equipment, T represents the ambient temperature characteristics of the substation equipment, H represents the ambient humidity characteristics of the substation equipment, S represents the service life of the substation equipment, β represents the smoothing parameter, ε and γ represent the adjustment parameters, and SVM() represents the output of the health assessment model of the substation equipment.

6. A comprehensive evaluation system for the health status of substation equipment based on data analysis, used to implement the comprehensive evaluation method for the health status of substation equipment according to any one of claims 1 to 5, characterized in that include: Data acquisition module, preprocessing module, feature extraction module, feature processing module and health assessment module; The data acquisition module is used to collect relevant data of the substation equipment, including the voltage, current, power and service life of the substation equipment, and the ambient temperature and humidity of the substation equipment; The preprocessing module is used to preprocess the collected data related to the substation equipment, including data cleaning and missing value filling operations; The feature extraction module is used to extract features from the relevant data of the pre-processed substation equipment; The feature processing module is used to reduce the dimension and filter the extracted features, and select feature parameters whose influence on the health status of the equipment is greater than the contribution threshold; The health assessment module is used to construct a health status assessment model for the substation equipment and to assess the health status of the substation equipment.

7. The comprehensive evaluation system for health status of substation equipment based on data analysis according to claim 6, Its characteristic is that the feature processing module includes: a feature dimension reduction unit and a feature screening unit; The feature dimension reduction unit is used to reduce the dimension of the extracted substation equipment feature matrix; The feature screening unit is used to screen the contribution of the substation feature matrix after dimension reduction, and screen out features whose contribution is higher than a contribution threshold.

8. An electronic device comprising a memory and a processor, characterized in that The memory stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement the comprehensive health status assessment method of substation equipment according to any one of claims 1-5.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores at least one instruction or at least one program, and when the at least one instruction or at least one program is executed, the method for comprehensive health status assessment of substation equipment according to any one of claims 1 to 5 is implemented.

Images