A method for monitoring the operation of a power distribution cabinet control system

Abstract

The present invention discloses a method for monitoring the operation of a distribution cabinet control system, which relates to the technical field of distribution cabinet control, and comprises the following steps: S1: measuring data during the operation of the distribution cabinet by means of sensors, and obtaining data measured by the sensors, performing significant error detection on the data measured by the sensors, making a preliminary judgment on the status of the sensors and the distribution cabinet based on the detection results, and performing abnormal processing on the measured data to improve the credibility of the measured data. The present invention proposes a method for monitoring the operation of a distribution cabinet control system, which, after obtaining the measurement data during the operation of the distribution cabinet, performs significant error detection on the measurement data, makes a preliminary judgment on the status of the sensors and the distribution cabinet based on the detection results, and performs data coordination processing on the measurement data, improves the credibility of the measurement data and the accurate estimation of the unmeasured data, and when a sensor failure is detected, further judges the operating status of the distribution cabinet.

Description

Technical Field

[0001] The present invention relates to the technical field of power distribution cabinet control, and in particular to an operation monitoring method of a power distribution cabinet control system. Background Art

[0002] With the construction and development of the power system, people's demand for the distribution, control and protection of electric energy is increasing. The distribution, control and protection of electric energy involve many complex technical issues. As one of them, the importance of distribution cabinets is becoming increasingly prominent. In the Chinese patent application number 202311022758.0, "a distribution cabinet control system operation monitoring method, device, equipment and medium are disclosed. The method includes: matching the acquired distribution cabinet information with the preset distribution cabinet model. If the match is unsuccessful, the fluctuation information is determined; the original fault information is obtained, and based on the original fault information, a fault information table is determined; based on the fluctuation information and the fault information table, the target fault cause is determined; based on the target fault cause, fault maintenance information is generated and fed back for display. The present application can improve the accuracy of fault detection while improving the maintenance efficiency."

[0003] This prior art only solves the problem that the traditional distribution cabinet control system operation monitoring is mostly carried out after a fault occurs. It is also impossible to analyze the cause of the abnormal operation of the distribution cabinet with abnormal operation, resulting in a lot of time spent on abnormal cause investigation during maintenance, which reduces the maintenance efficiency. It does not take into account that when measuring the operation data of the distribution cabinet, the measurement data should be error detected, and when there is a significant error, the source of the error should be further determined, and the operation status of the distribution cabinet should be judged based on the measurement data, so as to determine whether the distribution cabinet has a fault and further diagnose the type of fault in the distribution cabinet. Summary of the invention

[0004] The purpose of the present invention is to provide a method for monitoring the operation of a distribution cabinet control system to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solution: a method for monitoring the operation of a distribution cabinet control system, comprising the following steps:

[0006] S1: Measure the data during the operation of the power distribution cabinet through sensors, obtain the data measured by the sensors, perform significant error detection on the data measured by the sensors, make a preliminary judgment on the status of the sensors and the power distribution cabinet based on the detection results, and perform abnormal processing on the measured data to improve the credibility of the measured data;

[0007] S2: When a sensor failure is detected, in order to further determine the operating status of the distribution cabinet, a distribution cabinet operating status evaluation system is constructed, the weights of each evaluation index in the distribution cabinet operating status evaluation system are determined, and the data of the corresponding evaluation index are obtained, so as to evaluate the operating status of the distribution cabinet;

[0008] S3: extract the time feature sequence of the data corresponding to the evaluation index through the long short-term memory neural network, and obtain the predicted value of the corresponding evaluation index in a short time by constructing the equipment operation data prediction model based on the extracted time feature sequence. Determine the operating status of the distribution cabinet within the corresponding prediction time based on the predicted value of the evaluation index in a short time, and determine the change trend of the operating status of the distribution cabinet, so as to facilitate the monitoring of the operating status of the distribution cabinet;

[0009] S4: When it is determined that the distribution cabinet has a fault, the faulty sensor is replaced and the data is re-measured. Based on the re-measured measurement data, the fault state of the distribution cabinet is determined by constructing an equipment fault diagnosis model, and the distribution cabinet is fault-handled based on the determined fault state of the distribution cabinet.

[0010] Preferably, step S1 also includes measuring the data during the operation of the power distribution cabinet with a fixed data measurement cycle through a sensor, and obtaining the data measured by the sensor, performing significant error detection on the data measured by the sensor, and when there is no significant error, judging that the operation state of the power distribution cabinet is normal, and when there is a significant error, it is necessary to judge the working state of the sensor and the power distribution cabinet, and when the sensor is detected to be working normally by fault detection, judging that the power distribution cabinet is faulty, and when the sensor is detected to be faulty by fault detection, the corresponding measurement data is regarded as abnormal data based on the significant error detection result, and the measurement data without significant error is used as input data, and the objective function based on the generalized T distribution is constructed, and its specific expression is as follows:

[0011] In the formula, Indicates Measurement data, Indicates The coordinated value of the measured data, Indicates GT distribution parameters of the measured data.

[0012] Preferably, step S1 also includes using the constructed objective function as a robust estimation function of the data coordination model to improve the data coordination model, eliminating abnormal data to obtain corresponding unmeasured data, and using the measurement data with no significant error as the input of the improved data coordination model, solving the constructed objective function through the sparrow optimization algorithm, obtaining the coordination value of the measurement data with no significant error and the estimated value of the unmeasured data, thereby improving the credibility of the measurement data and the accurate estimation of the unmeasured data.

[0013] Preferably, step S2 further includes, when a sensor failure is detected, to further determine the operating status of the distribution cabinet, constructing a distribution cabinet operating status evaluation system, wherein the evaluation indicators in the distribution cabinet operating status evaluation system are divided into real-time indicators, statistical indicators and basic indicators, wherein the real-time indicators specifically include load rate, three-phase imbalance and voltage deviation, and the specific calculation formula of the real-time indicators is as follows:

[0014] In the formula, Indicates the load factor, Indicates the maximum value among the three-phase currents, Indicates the rated current, Indicates voltage deviation, Indicates the actual phase voltage, represents the nominal phase voltage, Indicates the three-phase unbalance, Indicates the maximum value of three-phase voltage, Indicates the minimum three-phase voltage. It represents the mean value of three-phase voltage, where the statistical indicators include the number of faults, the number of heavy overloads and the number of three-phase imbalances, and the basic indicators include the operating years and whether there are family defects. The weights of the real-time indicators and the statistical indicators are determined by the AHP-Delphi method.

[0015] Preferably, step S2 further includes acquiring data of each evaluation indicator within the current fixed data measurement period, and based on the data of each evaluation indicator in the real-time indicators and the statistical indicators, determining the scores of each evaluation indicator in the real-time indicators and the statistical indicators through the deduction rules in the guideline document of the State Grid Corporation, and for each evaluation indicator in the basic indicators, when there is a family defect in the distribution cabinet, the value of the evaluation indicator of whether there is a family defect is set to 0.95, otherwise it is set to 1, and the calculation formula for the corresponding value of the evaluation indicator of the operating life is as follows:

[0016] In the formula, It represents the service life of the distribution cabinet. The scores of the real-time indicators and the statistical indicators are multiplied by the weights of the corresponding evaluation indicators, and the multiplication results are accumulated. The accumulated results are multiplied by the corresponding values ​​of the evaluation indicators in the basic indicators to obtain the final evaluation value of the operating status of the distribution cabinet, and the operating status of the distribution cabinet is evaluated. Specifically, when the evaluation value is <60, the distribution cabinet is judged to be in a serious fault state; when 60≤evaluation value<75, the distribution cabinet is judged to be in a fault state; when 75≤evaluation value<85, the distribution cabinet is judged to be in a warning state; when 85≤evaluation value≤100, the distribution cabinet is judged to be in a normal state.

[0017] Preferably, step S3 also includes inputting the data of each evaluation indicator in the real-time indicator into the long short-term memory neural network to perform a time series feature extraction operation, and constructing an equipment operation data prediction model based on the kernel ridge regression model, and inputting the extracted time series features into the equipment operation data prediction model, predicting the data of each evaluation indicator in the real-time indicator for the next 12 hours, and obtaining the output result of the equipment operation data prediction model, and statistically analyzing the predicted values ​​of each evaluation indicator in the statistical indicator based on the predicted values ​​of each evaluation indicator in the real-time indicator, and evaluating the operating status of the distribution cabinet within the prediction time in combination with the numerical changes of each evaluation indicator in the basic indicator within the prediction time, and obtaining the changing trend of the operating status of the distribution cabinet in the future by successive prediction.

[0018] Preferably, step S4 also includes building a device fault diagnosis model based on a self-attention network, specifically including a data feature extraction layer, an attention layer and an output layer, wherein the data feature extraction layer performs feature extraction on the input data through a convolutional neural network, wherein the attention layer is divided into sublayer 1 and sublayer 2, wherein sublayer 1 performs standardization on the data features, and then performs residual connection processing with the input data to obtain the output of sublayer 1, wherein sublayer 2 processes and outputs the data features through a feedforward neural network, wherein the output layer sends the output result of the attention layer to a fully connected network, and activates it with a relu function, and then performs a Flatten operation, and finally activates it with a Softmax function through a feedforward neural network containing neurons with a known number of distribution cabinet fault types, outputs the fault classification result, and constructs a distribution cabinet sample data set by crawling samples with a web crawler, and trains the equipment fault diagnosis model through the distribution cabinet sample data set, and performs accuracy verification on the trained equipment fault diagnosis model.

[0019] Preferably, step S4 also includes, when it is determined that a fault occurs in the distribution cabinet, replacing the faulty sensor and measuring the data during the operation of the distribution cabinet through normal sensors based on the trained equipment fault diagnosis model, thereby eliminating the impact of the sensor failure on the identification of the distribution cabinet fault type, inputting the newly acquired distribution cabinet operation data into the equipment fault diagnosis model, determining the type of distribution cabinet fault, and performing fault processing on the distribution cabinet based on the determined type of distribution cabinet fault.

[0020] Compared with the prior art, the beneficial effects of the present invention at least include: the present invention proposes a method for monitoring the operation of a distribution cabinet control system, after obtaining the measurement data during the operation of the distribution cabinet, performing significant error detection on the measurement data, making a preliminary judgment on the status of the sensor and the distribution cabinet based on the detection result, and performing data coordination processing on the measurement data to improve the credibility of the measurement data and the accurate estimation of the unmeasured data, and when a sensor failure is detected, in order to further judge the operating status of the distribution cabinet, the operating status of the distribution cabinet is evaluated to determine the operating status of the distribution cabinet, and further a short-term prediction is made on the operating status of the distribution cabinet to obtain the changing trend of the operating status of the distribution cabinet in the future, and when it is determined that the distribution cabinet has a fault, data measurement is performed through a normal sensor, and the distribution cabinet is diagnosed based on the re-measured data, thereby eliminating the influence of the sensor failure on the identification of the fault type of the distribution cabinet. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 A schematic flow chart of a method for monitoring the operation of a power distribution cabinet control system provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0022] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0023] See also Figure 1 The present invention provides a technical solution: a method for monitoring the operation of a distribution cabinet control system, comprising the following steps:

[0024] S1: Measure the data during the operation of the power distribution cabinet through sensors, obtain the data measured by the sensors, perform significant error detection on the data measured by the sensors, make a preliminary judgment on the status of the sensors and the power distribution cabinet based on the detection results, and perform abnormal processing on the measured data to improve the credibility of the measured data;

[0025] S2: When a sensor failure is detected, in order to further determine the operating status of the distribution cabinet, a distribution cabinet operating status evaluation system is constructed, the weights of each evaluation index in the distribution cabinet operating status evaluation system are determined, and the data of the corresponding evaluation index are obtained, so as to evaluate the operating status of the distribution cabinet;

[0026] S3: extract the time feature sequence of the data corresponding to the evaluation index through the long short-term memory neural network, and obtain the predicted value of the corresponding evaluation index in a short time by constructing the equipment operation data prediction model based on the extracted time feature sequence. Determine the operating status of the distribution cabinet within the corresponding prediction time based on the predicted value of the evaluation index in a short time, and determine the change trend of the operating status of the distribution cabinet, so as to facilitate the monitoring of the operating status of the distribution cabinet;

[0027] S4: When it is determined that the distribution cabinet has a fault, the faulty sensor is replaced and the data is re-measured. Based on the re-measured measurement data, the fault state of the distribution cabinet is determined by constructing an equipment fault diagnosis model, and the distribution cabinet is fault-handled based on the determined fault state of the distribution cabinet.

[0028] Step S1 also includes measuring the data during the operation of the distribution cabinet with a fixed data measurement cycle through a sensor, and obtaining the data measured by the sensor, performing significant error detection on the data measured by the sensor, and when there is no significant error, judging that the operation state of the distribution cabinet is normal, when there is a significant error, it is necessary to judge the working state of the sensor and the distribution cabinet, and when the sensor is detected to be working normally, it is judged that the distribution cabinet is faulty, and when the sensor is detected to be faulty, the corresponding measurement data is regarded as abnormal data based on the significant error detection result, and the measurement data without significant error is used as input data, and the objective function based on the generalized T distribution is constructed, and its specific expression is as follows:

[0029] In the formula, Indicates Measurement data, Indicates The coordinated value of the measured data, Indicates GT distribution parameters of the measured data;

[0030] Step S1 also includes using the constructed objective function as a robust estimation function of the data coordination model to improve the data coordination model, eliminating abnormal data to obtain corresponding unmeasured data, and using the measured data with no significant error as the input of the improved data coordination model, solving the constructed objective function through the sparrow optimization algorithm, obtaining the coordinated value of the measured data with no significant error and the estimated value of the unmeasured data, thereby improving the credibility of the measured data and the accurate estimation of the unmeasured data;

[0031] Step S2 also includes, when a sensor failure is detected, to further determine the operating status of the distribution cabinet, constructing a distribution cabinet operating status evaluation system, the evaluation indicators in the distribution cabinet operating status evaluation system are divided into real-time indicators, statistical indicators and basic indicators, wherein the real-time indicators specifically include load rate, three-phase imbalance and voltage deviation, and the specific calculation formula of the real-time indicators is as follows:

[0032] In the formula, Indicates the load factor, Indicates the maximum value among the three-phase currents, Indicates the rated current, Indicates voltage deviation, Indicates the actual phase voltage, represents the nominal phase voltage, Indicates the three-phase unbalance, Indicates the maximum value of three-phase voltage, Indicates the minimum three-phase voltage. It represents the mean value of three-phase voltage, where the statistical indicators include the number of faults, the number of heavy overloads and the number of three-phase imbalances, and the basic indicators include the operating years and whether there are family defects. The weights of the real-time indicators and the statistical indicators are determined by the AHP-Delphi method;

[0033] Step S2 also includes acquiring the data of each evaluation indicator within the current fixed data measurement period, and based on the data of each evaluation indicator in the real-time indicators and the statistical indicators, determining the scores of each evaluation indicator in the real-time indicators and the statistical indicators through the deduction rules in the guideline documents of the State Grid Corporation, and for each evaluation indicator in the basic indicators, when the distribution cabinet has a family defect, the value of the evaluation indicator of whether there is a family defect is set to 0.95, otherwise it is set to 1, and the calculation formula for the corresponding value of the evaluation indicator of the operating life is as follows:

[0034] In the formula, Indicates the service life of the distribution cabinet. The scores of the real-time indicators and the statistical indicators are multiplied by the weights of the corresponding evaluation indicators, and the multiplication results are accumulated. The accumulated results are respectively multiplied by the corresponding values ​​of the evaluation indicators in the basic indicators to obtain the final evaluation value of the operation status of the distribution cabinet, and the operation status of the distribution cabinet is evaluated. Specifically, when the evaluation value is less than 60, the distribution cabinet is judged to be in a serious fault state; when 60≤evaluation value<75, the distribution cabinet is judged to be in a fault state; when 75≤evaluation value<85, the distribution cabinet is judged to be in a warning state; when 85≤evaluation value≤100, the distribution cabinet is judged to be in a normal state;

[0035] Step S3 also includes inputting the data of each evaluation indicator in the real-time indicator into the long short-term memory neural network for time series feature extraction, and constructing an equipment operation data prediction model based on the kernel ridge regression model, inputting the extracted time series features into the equipment operation data prediction model, predicting the data of each evaluation indicator in the real-time indicator for the next 12 hours, and obtaining the output result of the equipment operation data prediction model, and statistically analyzing the predicted values ​​of each evaluation indicator in the statistical indicator based on the predicted values ​​of each evaluation indicator in the real-time indicator, and evaluating the operating status of the distribution cabinet within the prediction time in combination with the numerical changes of each evaluation indicator in the basic indicator within the prediction time, and obtaining the changing trend of the operating status of the distribution cabinet in the future by successive prediction;

[0036] Step S4 also includes building an equipment fault diagnosis model based on the self-attention network, specifically including a data feature extraction layer, an attention layer and an output layer, wherein the data feature extraction layer extracts features of the input data through a convolutional neural network, wherein the attention layer is divided into sublayer 1 and sublayer 2, wherein sublayer 1 performs standardization processing on the data features, and then performs residual connection processing with the input data to obtain the output of sublayer 1, wherein sublayer 2 processes and outputs the data features through a feedforward neural network, wherein the output layer sends the output result of the attention layer to a fully connected network, and activates it with a relu function, and then performs a Flatten operation, and finally activates it with a Softmax function through a feedforward neural network containing neurons with a known number of distribution cabinet fault types, outputs the fault classification result, and constructs a distribution cabinet sample data set by crawling samples with a web crawler, and trains the equipment fault diagnosis model through the distribution cabinet sample data set, and performs accuracy verification operations on the trained equipment fault diagnosis model;

[0037] Step S4 also includes, when it is determined that a fault occurs in the distribution cabinet, based on the trained equipment fault diagnosis model, replacing the faulty sensor and measuring the data during the operation of the distribution cabinet through normal sensors, thereby eliminating the impact of the sensor failure on the identification of the distribution cabinet fault type, inputting the newly acquired distribution cabinet operation data into the equipment fault diagnosis model, determining the type of distribution cabinet fault, and performing fault processing on the distribution cabinet based on the determined type of distribution cabinet fault.

[0038] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0039] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for monitoring the operation of a power distribution cabinet control system, characterized in that The following steps are involved: S1: Measure the data during the operation of the power distribution cabinet through sensors, obtain the data measured by the sensors, perform significant error detection on the data measured by the sensors, make a preliminary judgment on the status of the sensors and the power distribution cabinet based on the detection results, and perform abnormal processing on the measured data to improve the credibility of the measured data; S2: When a sensor failure is detected, in order to further determine the operating status of the distribution cabinet, a distribution cabinet operating status evaluation system is constructed, the weights of each evaluation index in the distribution cabinet operating status evaluation system are determined, and the data of the corresponding evaluation index are obtained, so as to evaluate the operating status of the distribution cabinet; S3: extract the time feature sequence of the data corresponding to the evaluation index through the long short-term memory neural network, and obtain the predicted value of the corresponding evaluation index in a short time by constructing the equipment operation data prediction model based on the extracted time feature sequence. Determine the operating status of the distribution cabinet within the corresponding prediction time based on the predicted value of the evaluation index in a short time, and determine the change trend of the operating status of the distribution cabinet, so as to facilitate the monitoring of the operating status of the distribution cabinet; S4: When it is determined that the power distribution cabinet has a fault, the faulty sensor is replaced and data is remeasured, and the fault state of the power distribution cabinet is determined by building an equipment fault diagnosis model based on the remeasured measurement data, and the power distribution cabinet is fault-handled based on the determined fault state of the power distribution cabinet; The step S4 also includes building a device fault diagnosis model based on the self-attention network, specifically including a data feature extraction layer, an attention layer and an output layer, wherein the data feature extraction layer extracts features of the input data through a convolutional neural network, wherein the attention layer is divided into sublayer 1 and sublayer 2, wherein sublayer 1 performs standardization processing on the data features, and then performs residual connection processing with the input data to obtain the output of sublayer 1, wherein sublayer 2 processes and outputs the data features through a feedforward neural network, wherein the output layer sends the output result of the attention layer to a fully connected network, and activates it with a relu function, and then performs a Flatten operation, and finally activates it with a Softmax function through a feedforward neural network containing neurons with a known number of distribution cabinet fault types, outputs the fault classification result, and constructs a distribution cabinet sample data set by crawling samples with a web crawler, and trains the equipment fault diagnosis model through the distribution cabinet sample data set, and performs accuracy verification operations on the trained equipment fault diagnosis model; The step S4 also includes, when it is determined that a fault occurs in the distribution cabinet, based on the trained equipment fault diagnosis model, replacing the faulty sensor and measuring the data during the operation of the distribution cabinet through normal sensors, thereby eliminating the impact of the sensor failure on the identification of the distribution cabinet fault type, inputting the newly acquired distribution cabinet operation data into the equipment fault diagnosis model, determining the distribution cabinet fault type, and performing fault processing on the distribution cabinet based on the determined distribution cabinet fault type.

2. A method for monitoring the operation of a power distribution cabinet control system according to claim 1, characterized in that: The step S1 also includes measuring the data during the operation of the distribution cabinet with a fixed data measurement period through a sensor, and obtaining the data measured by the sensor, performing significant error detection on the data measured by the sensor, and when there is no significant error, judging that the operation status of the distribution cabinet is normal, and when there is a significant error, it is necessary to judge the working status of the sensor and the distribution cabinet, and when the sensor is detected to be working normally, it is judged that the distribution cabinet is faulty, and when the sensor is detected to be faulty, the corresponding measurement data is regarded as abnormal data based on the significant error detection result, and the measurement data without significant error is used as input data to construct an objective function based on the generalized T distribution.

3. A method for monitoring the operation of a power distribution cabinet control system according to claim 1, characterized in that: The step S1 also includes using the constructed objective function as a robust estimation function of the data coordination model to improve the data coordination model, eliminating abnormal data to obtain corresponding unmeasured data, and using the measurement data with no significant error as the input of the improved data coordination model, solving the constructed objective function through the sparrow optimization algorithm, and obtaining the coordination value of the measurement data with no significant error and the estimated value of the unmeasured data, thereby improving the credibility of the measurement data and the accurate estimation of the unmeasured data.

4. A method for monitoring the operation of a power distribution cabinet control system according to claim 1, characterized in that: The step S2 also includes, when a sensor fault is detected, in order to further judge the operating status of the distribution cabinet, constructing a distribution cabinet operating status evaluation system, the evaluation indicators in the distribution cabinet operating status evaluation system are divided into real-time indicators, statistical indicators and basic indicators, wherein the real-time indicators specifically include load rate, three-phase imbalance and voltage deviation, wherein the statistical indicators specifically include the number of faults, the number of heavy overloads and the number of three-phase imbalances, wherein the basic indicators specifically include operating years and whether there are family defects, and the weights of each evaluation indicator in the real-time indicators and statistical indicators are determined by the AHP-Delphi method.

5. The method for monitoring the operation of a power distribution cabinet control system according to claim 1, characterized in that: The step S2 also includes acquiring the data of each evaluation indicator within the current fixed data measurement period, and based on the data of each evaluation indicator in the real-time indicator and the statistical indicator, determining the score of each evaluation indicator in the real-time indicator and the statistical indicator through the deduction rules in the guideline document of the State Grid Corporation, and for each evaluation indicator in the basic indicator, when there is a family defect in the distribution cabinet, the value of the evaluation indicator whether there is a family defect is set to 0.95, otherwise it is set to 1, and the score of each evaluation indicator in the real-time indicator and the statistical indicator is compared with The weights of the corresponding evaluation indicators are multiplied, and the products are accumulated. The accumulated results are multiplied with the corresponding values ​​of each evaluation indicator in the basic indicator to obtain the final evaluation value of the operating status of the distribution cabinet, and the operating status of the distribution cabinet is evaluated. Specifically, when the evaluation value is <60, the distribution cabinet is judged to be in a serious fault state; when 60≤evaluation value<75, the distribution cabinet is judged to be in a fault state; when 75≤evaluation value<85, the distribution cabinet is judged to be in a warning state; when 85≤evaluation value≤100, the distribution cabinet is judged to be in a normal state.

6. A method for monitoring the operation of a power distribution cabinet control system according to claim 1, characterized in that: The step S3 also includes inputting the data of each evaluation indicator in the real-time indicator into the long short-term memory neural network to perform a time series feature extraction operation, and constructing an equipment operation data prediction model based on the kernel ridge regression model, inputting the extracted time series features into the equipment operation data prediction model, predicting the data of each evaluation indicator in the real-time indicator for the next 12 hours, and obtaining the output result of the equipment operation data prediction model, and statistically analyzing the predicted values ​​of each evaluation indicator in the statistical indicator based on the predicted values ​​of each evaluation indicator in the real-time indicator, and evaluating the operating status of the distribution cabinet within the prediction time in combination with the numerical changes of each evaluation indicator in the basic indicator within the prediction time, and obtaining the changing trend of the operating status of the distribution cabinet in the future by successive prediction.

Images