Test monitoring method and system for combined transformer test power supply

Abstract

The invention discloses a test monitoring method and system for a combined transformer test power supply, and the method comprises the steps: carrying out the test monitoring of a target test power supply, obtaining power supply test monitoring information, carrying out the data preprocessing of the power supply test monitoring information, and obtaining the preprocessing result information; an anomaly detection model is constructed, preprocessing result information is input to detect operation anomaly data occurring during power supply testing, and anomaly detection information is obtained; performing trend analysis based on the abnormal detection information, predicting the change of the power supply test monitoring data at the future moment, and detecting an abnormal trend to obtain abnormal trend detection information; extracting abnormal features based on the abnormal trend detection information, presetting a risk assessment rule, and performing risk assessment according to the extracted abnormal features to obtain risk assessment information; according to the risk assessment information, it is judged that a test safety risk exists, and if yes, a fuzzy controller is used for generating a regulation and control scheme for regulation and control, so that the safety and reliability of power supply testing are guaranteed.

Description

Technical Field

[0001] The invention relates to the technical field of power supply test monitoring, and in particular to a test monitoring method and system for a combined transformer test power supply. Background Art

[0002] With the development of the power system, the demand for transformer power supplies has increased according to the needs of different scenarios. The use of a single power supply is not enough to support the needs of the scenario, and multiple sets of power supplies are needed to be used together, that is, a combined transformer power supply. The combined transformer power supply uses different combinations to improve the operating efficiency of the power grid. However, combining power supplies requires further improvement in the monitoring and control capabilities of power supply operation to ensure the safety of use. The corresponding combination needs to be tested before it is put into use to ensure the stability and reliability of the work.

[0003] Due to different testing requirements for transformer power supplies, comprehensive tests are required under different frequencies and load conditions to verify their operating performance under different working conditions. Variable test conditions and environments will bring unknown test risks. Therefore, how to accurately respond to and control test risks when conducting power supply testing is an urgent problem to be solved. Summary of the invention

[0004] The present invention overcomes the defects of the prior art and provides a test monitoring method and system for a combined transformer test power supply, the important purpose of which is to improve the safety and reliability of power supply testing.

[0005] To achieve the above-mentioned purpose, the present invention provides a test monitoring method of a combined transformer test power supply in a first aspect, comprising:

[0006] Performing test monitoring on the target test power supply to obtain power supply test monitoring information, and performing data preprocessing on the power supply test monitoring information to obtain preprocessing result information;

[0007] Constructing an abnormality detection model, inputting the preprocessing result information to detect abnormal operation data occurring during power supply testing, and obtaining abnormality detection information;

[0008] Perform trend analysis based on the abnormal detection information, predict changes in power supply test monitoring data at future moments, and detect abnormal trends to obtain abnormal trend detection information;

[0009] Extracting abnormal features based on the abnormal trend detection information, presetting risk assessment rules, performing risk assessment according to the extracted abnormal features, and obtaining risk assessment information;

[0010] The existence of a test safety risk is determined based on the risk assessment information. If so, a control scheme is generated by using a fuzzy controller to control the target combined transformer test power supply.

[0011] In this solution, the target test power supply is tested and monitored to obtain power supply test monitoring information, and the power supply test monitoring information is preprocessed to obtain preprocessing result information, which specifically includes:

[0012] A sensor array is set at a target combined transformer test power supply, and power supply test monitoring is performed based on the set sensor array to obtain power supply test monitoring information;

[0013] Performing signal filtering processing on the power supply test monitoring information by using a low-pass filter to remove high-frequency signal noise, and calibrating the power supply test monitoring information data after signal filtering;

[0014] Setting a standard reference signal, comparing the power supply test monitoring information after signal filtering with the standard reference signal, performing sensor response calibration according to the comparison result, and obtaining the calibrated power supply test monitoring information;

[0015] Perform time sequence processing on the calibrated power supply test monitoring information, calculate the data standard deviation of the power supply test monitoring information after time sequence processing, and make a judgment with the preset standard deviation range.

[0016] The data corresponding to the data standard deviation that is not within the preset standard deviation range is defined as an outlier and then eliminated. The linear interpolation method is used for interpolation compensation to obtain the preprocessing result information.

[0017] In this solution, the abnormality detection model is constructed, and the preprocessing result information is input to detect the abnormal operation data that occurs when the power supply test is performed, and the abnormality detection information is obtained, which specifically includes:

[0018] Building an anomaly detection model based on the isolation forest, obtaining preprocessing result information and generating a time series sequence, which is input into the anomaly detection model to detect operation abnormality data occurring during power supply testing;

[0019] The RANSAC algorithm is introduced to randomly select a number of sample data according to the input time series, perform linear fitting through the selected sample data, and calculate the difference between the actual observation value and the fitted prediction value according to the linear fitting to generate residual features;

[0020] Extract features from the input time series, build a new feature matrix based on the residual features, determine the total number of trees in the isolated forest based on the new feature matrix and build a feature space;

[0021] A random binary search tree is constructed to detect low-density and isolated data points in the feature space, which are defined as isolated points. The path length of each isolated point in the corresponding tree is calculated as the anomaly score, which is compared with the preset threshold to obtain anomaly detection information.

[0022] In this solution, the trend analysis is performed based on the abnormal detection information to predict the power supply test monitoring data changes at future moments, and to detect abnormal trends to obtain abnormal trend detection information, specifically including:

[0023] A trend prediction model is constructed using a Markov algorithm, the anomaly detection information is input into the trend prediction model for analysis, and an original sequence is generated according to the input anomaly detection information;

[0024] Extract features from the original sequence to form a feature matrix of the original sequence, and perform similarity calculation with the feature matrix corresponding to each state transfer matrix in the preset state space to obtain a similarity value;

[0025] The calculated similarity value is judged with a preset threshold, a corresponding state transition matrix is ​​obtained according to the judgment result, and the state transition probability at the next moment is calculated in combination with the feature matrix of the original sequence;

[0026] The calculated state transition probabilities for the next moment are sorted, and the state with the highest transition probability is selected as the prediction result according to the sorting result to generate a prediction sequence, and obtain trend prediction result information;

[0027] The trend prediction result information is input into the anomaly detection model for detection, and the abnormal data at future moments are marked according to the detection result to obtain abnormal trend detection information and generate an abnormal trend detection graph.

[0028] In this solution, the abnormal features are extracted based on the abnormal trend detection information, risk assessment rules are preset, and risk assessment is performed according to the extracted abnormal features to obtain risk assessment information, which specifically includes:

[0029] Acquire abnormal trend detection information, extract abnormal data features and corresponding time features according to the abnormal trend detection information, and obtain abnormal feature information;

[0030] Perform risk assessment based on the abnormal feature information, calculate the abnormal feature information and preset reference parameters to obtain the degree of abnormal deviation, and associate the corresponding time feature with the degree of abnormal deviation based on the abnormal feature information;

[0031] A risk assessment rule is preset, and the calculated abnormal deviation degree is judged against the risk assessment rule to evaluate the test risk existing in the current power supply test and obtain risk assessment information.

[0032] In this solution, the risk assessment information is used to determine whether there is a test safety risk. If so, a fuzzy controller is used to generate a control scheme to control the target combined transformer test power supply, specifically including:

[0033] Obtain risk assessment information, preset a test safety threshold, compare the risk assessment information with the test safety threshold, and analyze whether there is a test safety risk;

[0034] If the judgment result is that there is a test safety risk in the current power supply test, the fuzzy controller is used to generate a control scheme to control the target combined transformer test power supply;

[0035] Acquire abnormal characteristic information and generate a control target according to the abnormal characteristic information, set input variables based on the degree of abnormal deviation, fuzzify the input variables, map them into fuzzy sets, and construct a membership function according to the fuzzy sets;

[0036] Based on big data retrieval, we obtain control examples of different types of power supply test anomalies, and combine expert analysis to establish fuzzy rules for control measures of different types of power supply test anomalies, and form a fuzzy rule base;

[0037] Using the set input variables to perform fuzzy rule matching in the fuzzy rule base to obtain matching rules, calculating the activation degree of each matching rule based on the Min-Max reasoning method, and combining the outputs of multiple rules through Max operation to obtain a fuzzy output set;

[0038] Solving the fuzzy output set by a centroid method, obtaining a corresponding membership function according to the fuzzy output set and updating the membership function based on the activation degree of each output fuzzy set;

[0039] The centroid of each fuzzy output set is calculated according to the updated membership function and weighted average is performed, a control output value is generated according to the weighted average result, and a control scheme is constructed based on the control output value and input into the actuator for risk control.

[0040] A second aspect of the present invention provides a test monitoring system for a combined transformer test power supply, the system comprising: a memory, a processor, the memory containing a test monitoring method program for the combined transformer test power supply, the test monitoring method program for the combined transformer test power supply being executed by the processor to implement the following steps:

[0041] Performing test monitoring on the target test power supply to obtain power supply test monitoring information, and performing data preprocessing on the power supply test monitoring information to obtain preprocessing result information;

[0042] Constructing an abnormality detection model, inputting the preprocessing result information to detect abnormal operation data occurring during power supply testing, and obtaining abnormality detection information;

[0043] Perform trend analysis based on the abnormal detection information, predict changes in power supply test monitoring data at future moments, and detect abnormal trends to obtain abnormal trend detection information;

[0044] Extracting abnormal features based on the abnormal trend detection information, presetting risk assessment rules, performing risk assessment according to the extracted abnormal features, and obtaining risk assessment information;

[0045] The existence of a test safety risk is determined based on the risk assessment information. If so, a control scheme is generated by using a fuzzy controller to control the target combined transformer test power supply.

[0046] The invention discloses a test monitoring method and system for a combined transformer test power supply, comprising: testing and monitoring a target test power supply to obtain power supply test monitoring information, performing data preprocessing on the power supply test monitoring information to obtain preprocessing result information; constructing an abnormality detection model, inputting the preprocessing result information to detect abnormal operation data appearing during power supply testing, and obtaining abnormality detection information; performing trend analysis based on the abnormality detection information, predicting power supply test monitoring data changes at future moments, detecting abnormal trends, and obtaining abnormal trend detection information; extracting abnormal features based on the abnormal trend detection information, presetting risk assessment rules, and performing risk assessment according to the extracted abnormal features to obtain risk assessment information; judging whether there is a test safety risk according to the risk assessment information, and if so, generating a control scheme using a fuzzy controller for control to ensure the safety and reliability of the power supply test. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the embodiments or exemplary embodiments of the present invention, the drawings required for use in the embodiments or exemplary descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained according to the drawings without paying creative work.

[0048] Figure 1 A flow chart of a test monitoring method for a combined transformer test power supply provided by an embodiment of the present invention;

[0049] Figure 2 Provided for an embodiment of the present invention;

[0050] Figure 3 A block diagram of a test monitoring system for a combined transformer test power supply provided by an embodiment of the present invention;

[0051] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0052] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0053] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0054] Figure 1 A flow chart of a test monitoring method for a combined transformer test power supply provided by an embodiment of the present invention;

[0055] like Figure 1 As shown, the present invention provides a flow chart of a test monitoring method for a combined transformer test power supply, comprising:

[0056] S102, testing and monitoring the target test power supply to obtain power supply test monitoring information, and performing data preprocessing on the power supply test monitoring information to obtain preprocessing result information;

[0057] S104, constructing an abnormality detection model, inputting the preprocessing result information to detect abnormal operation data occurring during power supply testing, and obtaining abnormality detection information;

[0058] S106, performing trend analysis based on the abnormality detection information, predicting changes in power supply test monitoring data at future moments, and detecting abnormal trends to obtain abnormality trend detection information;

[0059] S108, extracting abnormal features based on the abnormal trend detection information, presetting risk assessment rules, performing risk assessment according to the extracted abnormal features, and obtaining risk assessment information;

[0060] S110, judging whether there is a test safety risk based on the risk assessment information, and if so, using a fuzzy controller to generate a control scheme to control the target combined transformer test power supply.

[0061] It should be noted that the present invention provides a test monitoring method and system for a combined transformer test power supply, sets a sensor array for the power supply during the test, performs power supply test monitoring based on the set sensor array to obtain power supply test monitoring information, including test data such as voltage, current and temperature, and further performs data preprocessing to obtain preprocessing result information. Then, a random forest algorithm is used to construct an abnormality detection model, and the preprocessing result information is input into the model to detect abnormal data that occurs during the test process to obtain abnormality detection information. Subsequently, trend prediction is performed based on the abnormality detection information, and the changes in test data at future moments are analyzed, and whether the test data at future moments will be abnormal is detected to obtain abnormal trend detection information. Finally, a risk assessment is performed based on the abnormal trend detection information to determine whether there is a test risk. If there is a test risk, a fuzzy controller is used to generate a control scheme to control the target combined transformer test power supply to improve the safety and reliability during the test process.

[0062] Further, in a preferred embodiment of the present invention, the target test power supply is tested and monitored to obtain power supply test monitoring information, and the power supply test monitoring information is preprocessed to obtain preprocessing result information, specifically including:

[0063] A sensor array is set at a target combined transformer test power supply, and power supply test monitoring is performed based on the set sensor array to obtain power supply test monitoring information;

[0064] Performing signal filtering processing on the power supply test monitoring information by using a low-pass filter to remove high-frequency signal noise, and calibrating the power supply test monitoring information data after signal filtering;

[0065] Setting a standard reference signal, comparing the power supply test monitoring information after signal filtering with the standard reference signal, performing sensor response calibration according to the comparison result, and obtaining the calibrated power supply test monitoring information;

[0066] Perform time sequence processing on the calibrated power supply test monitoring information, calculate the data standard deviation of the power supply test monitoring information after time sequence processing, and make a judgment with the preset standard deviation range.

[0067] The data corresponding to the data standard deviation that is not within the preset standard deviation range is defined as an outlier and then eliminated. The linear interpolation method is used for interpolation compensation to obtain the preprocessing result information.

[0068] It should be noted that in the process of testing the target combined transformer power supply, the corresponding voltage, current, temperature and other data are collected in real time through the set sensor array. First, data preprocessing is required. By preliminarily filtering the collected data, abnormal parameters that may be caused by sensor interference and other factors are eliminated. Then, sensor correction judgment is performed to correct the possible deviation of the sensor. The specific correction scheme is divided into linear correction and nonlinear correction. The corresponding correction scheme is determined according to the response type of the sensor. Due to the deviation of the acquisition time of different sensors, further book sequence processing is required to unify the acquisition time and form complete acquisition data. Finally, the collected data is cleaned and outliers are eliminated, and interpolation compensation is performed to obtain accurate test monitoring data, which provides a basis for subsequent analysis.

[0069] Further, in a preferred embodiment of the present invention, the abnormality detection model is constructed, and the preprocessing result information is input to detect the abnormal operation data that occurs when the power supply test is performed, and the abnormality detection information is obtained, which specifically includes:

[0070] Building an anomaly detection model based on the isolation forest, obtaining preprocessing result information and generating a time series sequence, which is input into the anomaly detection model to detect operation abnormality data occurring during power supply testing;

[0071] The RANSAC algorithm is introduced to randomly select a number of sample data according to the input time series, perform linear fitting through the selected sample data, and calculate the difference between the actual observation value and the fitted prediction value according to the linear fitting to generate residual features;

[0072] Extract features from the input time series, build a new feature matrix based on the residual features, determine the total number of trees in the isolated forest based on the new feature matrix and build a feature space;

[0073] A random binary search tree is constructed to detect low-density and isolated data points in the feature space, which are defined as isolated points. The path length of each isolated point in the corresponding tree is calculated as the anomaly score, which is compared with the preset threshold to obtain anomaly detection information.

[0074] It should be noted that in order to ensure the safety of the test during the test, it is necessary to accurately identify the abnormal data that occurs during the test. The anomaly detection model is constructed based on the isolation forest. The core of the isolation forest model is to identify abnormal points in the data by randomly selecting features and constructing a binary tree. In order to further improve the accuracy of anomaly detection, the RANSAC algorithm is introduced. By randomly selecting several sample data in the time series for linear fitting, the difference between the actual observation value and the fitted prediction value is calculated to generate residual features. The residual feature reflects the degree of deviation between the data and the linear model and can capture potential abnormalities more sensitively. By extracting features from the time series and combining the residual features to construct a new feature matrix, the model's ability to identify anomalies can be effectively improved. After the new feature matrix is ​​constructed, the total number of trees in the isolation forest model is determined, and the feature space is constructed accordingly. Next, a random binary search tree is constructed in the feature space to detect data points with low distribution density and appearing isolated in space. After detecting isolated points, their path lengths in the corresponding trees are calculated. The shorter the path, the more abnormal the data point. Finally, the path lengths of these isolated points are used as anomaly scores and compared with the preset threshold to determine whether the data is abnormal, and then obtain the final anomaly detection information. This can accurately identify the abnormal operation data that occurs during the power supply test and ensure the stability and reliability of the test process.

[0075] Further, in a preferred embodiment of the present invention, the trend analysis is performed based on the abnormal detection information to predict the power supply test monitoring data changes at future moments, and the abnormal trend is detected to obtain the abnormal trend detection information, which specifically includes:

[0076] A trend prediction model is constructed using a Markov algorithm, the anomaly detection information is input into the trend prediction model for analysis, and an original sequence is generated according to the input anomaly detection information;

[0077] Extract features from the original sequence to form a feature matrix of the original sequence, and perform similarity calculation with the feature matrix corresponding to each state transfer matrix in the preset state space to obtain a similarity value;

[0078] The calculated similarity value is judged with a preset threshold, a corresponding state transition matrix is ​​obtained according to the judgment result, and the state transition probability at the next moment is calculated in combination with the feature matrix of the original sequence;

[0079] The calculated state transition probabilities for the next moment are sorted, and the state with the highest transition probability is selected as the prediction result according to the sorting result to generate a prediction sequence, and obtain trend prediction result information;

[0080] The trend prediction result information is input into the anomaly detection model for detection, and the abnormal data at future moments are marked according to the detection result to obtain abnormal trend detection information and generate an abnormal trend detection graph.

[0081] It should be noted that after detecting the abnormal parameters of the real-time data collection, it is necessary to make predictions based on the abnormal situation to determine whether the data changes at the future moment will lead to test risks, because the abnormal situation that occurs during the test may be a normal power supply operation fluctuation. The Markov algorithm is used to construct a trend prediction model, and the abnormal detection information is used as input to form the original sequence for trend prediction. The original sequence is feature extracted to form a feature matrix of the original sequence. Subsequently, the similarity calculation is performed with the feature matrix corresponding to each state transfer matrix in the preset state space, and the similarity value between the original sequence and each state transfer matrix is ​​obtained to determine the matching degree between the original sequence and the existing state model, thereby providing a basis for the next prediction. The state transfer matrix that is most similar to the original sequence is selected. The state transfer probability of the next moment is calculated through this state transfer matrix. After obtaining the state transfer probability of the next moment, these probabilities are sorted, and the state with the highest transfer probability is selected as the prediction result according to the sorting result. The generated prediction sequence forms the trend prediction result information. Finally, the trend prediction result information is re-input into the anomaly detection model for detection. Then, the abnormal data appearing in the prediction result is marked, which represents the abnormal situation existing at the future moment, thereby obtaining abnormal trend detection information.

[0082] Further, in a preferred embodiment of the present invention, the abnormal features are extracted based on the abnormal trend detection information, risk assessment rules are preset, and risk assessment is performed according to the extracted abnormal features to obtain risk assessment information, which specifically includes:

[0083] Acquire abnormal trend detection information, extract abnormal data features and corresponding time features according to the abnormal trend detection information, and obtain abnormal feature information;

[0084] Perform risk assessment based on the abnormal feature information, calculate the abnormal feature information and preset reference parameters to obtain the degree of abnormal deviation, and associate the corresponding time feature with the degree of abnormal deviation based on the abnormal feature information;

[0085] A risk assessment rule is preset, and the calculated abnormal deviation degree is judged against the risk assessment rule to evaluate the test risk existing in the current power supply test and obtain risk assessment information.

[0086] It should be noted that after completing trend prediction and anomaly detection, risk assessment is further performed based on the anomaly detection results to determine whether there is a test risk. Risk assessment rules can be further formed by analyzing historical abnormal test data that have test risks, setting different risk levels and feature portraits of each risk level, so as to conduct risk assessment on the current test.

[0087] Further, in a preferred embodiment of the present invention, the presence of a test safety risk is determined based on the risk assessment information. If so, a control scheme is generated by a fuzzy controller to control the target combined transformer test power supply, specifically including:

[0088] Obtain risk assessment information, preset a test safety threshold, compare the risk assessment information with the test safety threshold, and analyze whether there is a test safety risk;

[0089] If the judgment result is that there is a test safety risk in the current power supply test, the fuzzy controller is used to generate a control scheme to control the target combined transformer test power supply;

[0090] Acquire abnormal characteristic information and generate a control target according to the abnormal characteristic information, set input variables based on the degree of abnormal deviation, fuzzify the input variables, map them into fuzzy sets, and construct a membership function according to the fuzzy sets;

[0091] Based on big data retrieval, we obtain control examples of different types of power supply test anomalies, and combine expert analysis to establish fuzzy rules for control measures of different types of power supply test anomalies, and form a fuzzy rule base;

[0092] Using the set input variables to perform fuzzy rule matching in the fuzzy rule base to obtain matching rules, calculating the activation degree of each matching rule based on the Min-Max reasoning method, and combining the outputs of multiple rules through Max operation to obtain a fuzzy output set;

[0093] Solving the fuzzy output set by a centroid method, obtaining a corresponding membership function according to the fuzzy output set and updating the membership function based on the activation degree of each output fuzzy set;

[0094] The centroid of each fuzzy output set is calculated according to the updated membership function and weighted average is performed, a control output value is generated according to the weighted average result, and a control scheme is constructed based on the control output value and input into the actuator for risk control.

[0095] It should be noted that the risk assessment information is used to determine whether risk control is required. If risk control is required, the fuzzy controller is used to generate a corresponding control scheme to control the target transformer test power supply to eliminate safety risks. Based on the abnormal feature information, the control target, such as voltage or temperature, is generated. Then, the input variable, that is, the abnormal parameter feature at the current moment, is set, and fuzzification is performed based on the degree of abnormal deviation and converted into a fuzzy set. In order to formulate an effective control scheme, big data technology is used to retrieve and obtain control instances of different types of power supply test anomalies. At the same time, the expert analysis method is used to establish fuzzy rules for control measures for different types of power supply test anomalies, and a complete fuzzy rule base is formed. Next, the set input variables are used to match fuzzy rules in the fuzzy rule base, and the activation degree of each matching rule is calculated by the Min-Max reasoning method, and the outputs of multiple rules are combined by the Max operation to obtain the final fuzzy output set. After the fuzzy output set is obtained, it is solved by the centroid method. First, the corresponding membership function is obtained according to the fuzzy output set, and the membership function is updated based on the activation degree of each output fuzzy set. Then, the centroid of each fuzzy output set is calculated, and the final control output value is generated by weighted average and input into the actuator, and finally the operating state of the transformer test power supply is regulated to ensure that the risks in the test process are effectively controlled.

[0096] Figure 2 A flow chart of a test risk monitoring and control method for a combined transformer test power supply provided in one embodiment of the present invention;

[0097] like Figure 2 As shown, the present invention provides a flow chart of a test risk monitoring and control method for a combined transformer test power supply, including:

[0098] S202, setting a sensor array at a target combined transformer test power supply, performing power supply test monitoring based on the set sensor array to obtain power supply test monitoring information, and preprocessing the power supply test monitoring information;

[0099] S204, inputting the preprocessing result into the abnormality detection model to detect the abnormal operation data appearing during the power supply test, performing trend prediction and detecting the abnormal trend according to the abnormality detection result, and obtaining abnormal trend detection information;

[0100] S206, performing risk assessment based on the abnormal trend detection information to analyze whether there is a test risk. If there is a test risk, using a fuzzy controller to generate a control plan to control the target combined transformer test power supply.

[0101] In addition, in a test monitoring method of a combined transformer test power supply provided by the present invention, the following steps are also included:

[0102] Acquire test monitoring information of the target combined transformer test power supply and corresponding abnormal detection information when a test risk occurs, analyze the cause of the test risk abnormality, and obtain test risk abnormality cause analysis information;

[0103] Determine whether it is a test temperature abnormality risk according to the test risk abnormality cause analysis information; if it is a test temperature abnormality risk, analyze the performance release degree of the target combined transformer test power supply when the test risk occurs according to the test monitoring information;

[0104] Construct a performance evaluation model and set performance evaluation indicators, calculate the characterization parameters corresponding to each performance evaluation indicator when a test risk occurs in combination with the test monitoring information, input them into the performance evaluation model for performance evaluation, and obtain performance evaluation result information;

[0105] Based on the performance evaluation result information, it is determined whether the performance of the target combined transformer test power supply is beneficially increased when the risk of abnormal test temperature occurs. If it is beneficially increased, the test parameters corresponding to the current abnormal test temperature are defined as performance release parameters and constitute a performance mode;

[0106] Based on the abnormal detection information corresponding to the test temperature risk, the abnormal temperature characteristics are extracted, the safe temperature benchmark is obtained and set as the optimization target, and the abnormal temperature control parameters are solved by using the genetic algorithm to obtain the temperature control parameter analysis information;

[0107] A temperature control strategy scheme for the performance mode is formed according to the temperature control parameter analysis information and is set as an activation condition restriction for the current performance mode.

[0108] It should be noted that when conducting a power supply test, if the test abnormality risk is a temperature abnormality, due to the controllability of temperature, it is possible to analyze whether the performance of the power supply at this time is better improved based on the test parameters of the power supply at this time, that is, to determine whether the test parameters at this time bring a better power supply usage mode when other parameters are normal. If there is a temperature abnormality risk, the performance of the target combined transformer test power supply is beneficially improved, that is, there is a positive improvement compared to the preset performance, which means that the current test parameters can further release the corresponding power supply performance. At this time, through the current temperature abnormality characteristics, only the temperature abnormality needs to be adjusted to obtain a better power supply usage mode, thereby better understanding the actual capabilities of the target combined transformer test power supply.

[0109] Figure 3A test monitoring system 3 for a combined transformer test power supply is provided in one embodiment of the present invention. The system comprises: a memory 31 and a processor 32. The memory 31 contains a test monitoring method program for a combined transformer test power supply. When the test monitoring method program for a combined transformer test power supply is executed by the processor 32, the following steps are implemented:

[0110] Performing test monitoring on the target test power supply to obtain power supply test monitoring information, and performing data preprocessing on the power supply test monitoring information to obtain preprocessing result information;

[0111] Constructing an abnormality detection model, inputting the preprocessing result information to detect abnormal operation data occurring during power supply testing, and obtaining abnormality detection information;

[0112] Perform trend analysis based on the abnormal detection information, predict changes in power supply test monitoring data at future moments, and detect abnormal trends to obtain abnormal trend detection information;

[0113] Extracting abnormal features based on the abnormal trend detection information, presetting risk assessment rules, performing risk assessment according to the extracted abnormal features, and obtaining risk assessment information;

[0114] The existence of a test safety risk is determined based on the risk assessment information. If so, a control scheme is generated by using a fuzzy controller to control the target combined transformer test power supply.

[0115] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0116] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0117] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0118] Those skilled in the art can understand that: all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiments; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), disks or optical disks, and other media that can store program codes.

[0119] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0120] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A test monitoring method for a combined transformer test power supply, characterized in that: include: Performing test monitoring on the target test power supply to obtain power supply test monitoring information, and performing data preprocessing on the power supply test monitoring information to obtain preprocessing result information; Constructing an abnormality detection model, inputting the preprocessing result information to detect abnormal operation data occurring during power supply testing, and obtaining abnormality detection information; Perform trend analysis based on the abnormal detection information, predict changes in power supply test monitoring data at future moments, and detect abnormal trends to obtain abnormal trend detection information; Extracting abnormal features based on the abnormal trend detection information, presetting risk assessment rules, performing risk assessment according to the extracted abnormal features, and obtaining risk assessment information; The existence of a test safety risk is determined based on the risk assessment information. If so, a control scheme is generated by using a fuzzy controller to control the target combined transformer test power supply.

2. The test monitoring method of a combined transformer test power supply according to claim 1, characterized in that: The step of testing and monitoring the target test power supply to obtain power supply test monitoring information and performing data preprocessing on the power supply test monitoring information to obtain preprocessing result information specifically includes: A sensor array is set at a target combined transformer test power supply, and power supply test monitoring is performed based on the set sensor array to obtain power supply test monitoring information; Performing signal filtering processing on the power supply test monitoring information by using a low-pass filter to remove high-frequency signal noise, and calibrating the power supply test monitoring information data after signal filtering; Setting a standard reference signal, comparing the power supply test monitoring information after signal filtering with the standard reference signal, performing sensor response calibration according to the comparison result, and obtaining the calibrated power supply test monitoring information; Perform time sequence processing on the calibrated power supply test monitoring information, calculate the data standard deviation of the power supply test monitoring information after time sequence processing, and make a judgment with the preset standard deviation range. The data corresponding to the data standard deviation that is not within the preset standard deviation range is defined as an outlier and then eliminated. The linear interpolation method is used for interpolation compensation to obtain the preprocessing result information.

3. The test monitoring method of a combined transformer test power supply according to claim 1, characterized in that: The abnormality detection model is constructed, and the preprocessing result information is input to detect the abnormal operation data that occurs when the power supply test is performed, and the abnormality detection information is obtained, which specifically includes: Building an anomaly detection model based on the isolation forest, obtaining preprocessing result information and generating a time series sequence, which is input into the anomaly detection model to detect operation abnormality data occurring during power supply testing; The RANSAC algorithm is introduced to randomly select a number of sample data according to the input time series, perform linear fitting through the selected sample data, and calculate the difference between the actual observation value and the fitted prediction value according to the linear fitting to generate residual features; Extract features from the input time series, build a new feature matrix based on the residual features, determine the total number of trees in the isolated forest based on the new feature matrix and build a feature space; A random binary search tree is constructed to detect low-density and isolated data points in the feature space, which are defined as isolated points. The path length of each isolated point in the corresponding tree is calculated as the anomaly score, which is compared with the preset threshold to obtain anomaly detection information.

4. The test monitoring method of a combined transformer test power supply according to claim 1, characterized in that: The performing trend analysis based on the abnormal detection information, predicting the power supply test monitoring data changes at future moments, and detecting abnormal trends to obtain abnormal trend detection information specifically includes: A trend prediction model is constructed using a Markov algorithm, the anomaly detection information is input into the trend prediction model for analysis, and an original sequence is generated according to the input anomaly detection information; Extract features from the original sequence to form a feature matrix of the original sequence, and perform similarity calculation with the feature matrix corresponding to each state transfer matrix in the preset state space to obtain a similarity value; The calculated similarity value is judged with a preset threshold, a corresponding state transition matrix is ​​obtained according to the judgment result, and the state transition probability at the next moment is calculated in combination with the feature matrix of the original sequence; The calculated state transition probabilities for the next moment are sorted, and the state with the highest transition probability is selected as the prediction result according to the sorting result to generate a prediction sequence, and obtain trend prediction result information; The trend prediction result information is input into the anomaly detection model for detection, and the abnormal data at future moments are marked according to the detection result to obtain abnormal trend detection information and generate an abnormal trend detection graph.

5. The test monitoring method of a combined transformer test power supply according to claim 1, characterized in that: The extracting of abnormal features based on the abnormal trend detection information, presetting risk assessment rules, and performing risk assessment according to the extracted abnormal features to obtain risk assessment information specifically include: Acquire abnormal trend detection information, extract abnormal data features and corresponding time features according to the abnormal trend detection information, and obtain abnormal feature information; Perform risk assessment based on the abnormal feature information, calculate the abnormal feature information and preset reference parameters to obtain the degree of abnormal deviation, and associate the corresponding time feature with the degree of abnormal deviation based on the abnormal feature information; A risk assessment rule is preset, and the calculated abnormal deviation degree is judged against the risk assessment rule to evaluate the test risk existing in the current power supply test and obtain risk assessment information.

6. The test monitoring method of a combined transformer test power supply according to claim 1, characterized in that: The determining whether there is a test safety risk based on the risk assessment information, and if so, using a fuzzy controller to generate a control scheme to control the target combined transformer test power supply, specifically includes: Obtain risk assessment information, preset a test safety threshold, compare the risk assessment information with the test safety threshold, and analyze whether there is a test safety risk; If the judgment result is that there is a test safety risk in the current power supply test, the fuzzy controller is used to generate a control scheme to control the target combined transformer test power supply; Acquire abnormal characteristic information and generate a control target according to the abnormal characteristic information, set input variables based on the degree of abnormal deviation, fuzzify the input variables, map them into fuzzy sets, and construct a membership function according to the fuzzy sets; Based on big data retrieval, we obtain examples of control measures for different types of power supply test anomalies, and combine expert analysis to establish fuzzy rules for control measures for different types of power supply test anomalies, and form a fuzzy rule base; Using the set input variables to perform fuzzy rule matching in the fuzzy rule base to obtain matching rules, calculating the activation degree of each matching rule based on the Min-Max reasoning method, and combining the outputs of multiple rules through Max operation to obtain a fuzzy output set; Solving the fuzzy output set by a centroid method, obtaining a corresponding membership function according to the fuzzy output set and updating the membership function based on the activation degree of each output fuzzy set; The centroid of each fuzzy output set is calculated according to the updated membership function and weighted average is performed, a control output value is generated according to the weighted average result, and a control scheme is constructed based on the control output value and input into the actuator for risk control.

7. A test monitoring system for a combined transformer test power supply, characterized in that: The system includes: a memory and a processor, wherein the memory contains a test monitoring method program of a combined transformer test power supply, and when the test monitoring method program of the combined transformer test power supply is executed by the processor, the following steps are implemented: Performing test monitoring on the target test power supply to obtain power supply test monitoring information, and performing data preprocessing on the power supply test monitoring information to obtain preprocessing result information; Constructing an abnormality detection model, inputting the preprocessing result information to detect abnormal operation data occurring during power supply testing, and obtaining abnormality detection information; Perform trend analysis based on the abnormal detection information, predict changes in power supply test monitoring data at future moments, and detect abnormal trends to obtain abnormal trend detection information; Extracting abnormal features based on the abnormal trend detection information, presetting risk assessment rules, performing risk assessment according to the extracted abnormal features, and obtaining risk assessment information; The existence of a test safety risk is determined based on the risk assessment information. If so, a control scheme is generated by using a fuzzy controller to control the target combined transformer test power supply.

Images