Test safety monitoring method and system for transformer test station

Abstract

Disclosed in the present invention are a test safety monitoring method and system for a transformer test station. The present invention comprises: first, acquiring test data of a transformer test station; performing anomaly detection on the test data so as to obtain an anomaly detection result; then, evaluating test safety to obtain a safety evaluation result; on the basis of the evaluation result, determining the optimization space and the optimization direction of test parameters; and further introducing a genetic algorithm to perform a collaborative search with the optimization space and direction, so as to obtain optimized test parameters, thus improving the safety and stability of the transformer test station. The present invention can effectively monitor the test safety, improve the capability of optimizing test parameters, and has broad application prospects and economic values.

Description

A test safety monitoring method and system for a transformer test station TECHNICAL FIELD

[0001] The present application relates to the technical field of transformer test station monitoring, and in particular to a test safety monitoring method and system for a transformer test station. BACKGROUND

[0002] A transformer is an important device in a power system, and its performance and safety directly affect the stable operation of the power system. In order to ensure the safety and reliability of the transformer, various tests need to be performed, including but not limited to rated load tests, short circuit tests, etc. However, due to the complex interaction of various factors during the test process of the transformer test station, such as changes in test parameters, temperature changes, etc., abnormal situations may occur during the test process, thereby affecting the safety and accuracy of the test.

[0003] Currently, the safety monitoring of the transformer test station mainly relies on manual experience judgment or traditional monitoring methods, such as regular inspection, data recording, etc. However, these methods have the following shortcomings: first, manual experience judgment is greatly affected by subjective factors, and is prone to misjudgment or omission; second, traditional monitoring methods can only provide simple records of test data, and cannot perform in-depth abnormal detection and safety evaluation.

[0004] Therefore, there is an urgent need for a method that can automatically monitor the safety of the transformer test station and timely detect and evaluate test abnormal situations, in order to improve the safety and accuracy of the test.

[0005] In view of the problems and deficiencies of the prior art, the present application provides a test safety monitoring method for a transformer test station, which realizes automatic monitoring and evaluation of the safety of the transformer test station by comprehensively analyzing and detecting test data, and optimizing test parameters using a genetic algorithm, thereby improving the safety and accuracy of the test.

[0006] SUMMARY

[0007] In order to solve at least one of the above technical problems, the present application provides a test safety monitoring method and system for a transformer test station.

[0008] The first aspect of the present application provides a test safety monitoring method for a transformer test station, comprising:

[0009] Obtaining test data of a target transformer by a transformer test station, the test data including test parameter change data of the transformer test station, top and bottom oil temperature data, vibration and noise data, and electrical parameter data of the target transformer in operation;

[0010] According to the test data, test abnormality detection is performed on the transformer test station to obtain an abnormality detection result, the abnormality detection result including an abnormality type, a duration, and an abnormality degree;

[0011] According to the abnormality detection result, test safety of the transformer test station is evaluated to obtain a safety evaluation result;

[0012] Based on the safety evaluation result, an optimization space and an optimization direction of test parameters of the transformer test station are determined;

[0013] A genetic algorithm is introduced, and the genetic algorithm is cooperated with the optimization space and the optimization direction to search for optimal test parameters, so as to obtain optimal safety test parameters of the transformer test station.

[0014] In the scheme, the test data of the transformer test station on the target transformer are obtained, and the test data include test parameter change data of the transformer test station, top and bottom oil temperature data, vibration and noise data, and electrical parameter data of the target transformer in operation, and the electrical parameter data specifically include:

[0015] The test parameter change data of the transformer test station in the test process of the target transformer are obtained through an industrial computer of the transformer test station, and the test parameters include output voltage, current, power parameters, output power frequency parameters, top and bottom oil temperature data, and vibration and noise data of the transformer test station;

[0016] The electrical parameter data of the target transformer are obtained through sensors, and the electrical parameter data include operating voltage, current, power parameters, input power frequency parameters, and power factor of the target transformer in the test process.

[0017] In the scheme, according to the test data, test abnormality detection is performed on the transformer test station to obtain an abnormality detection result, the abnormality detection result including an abnormality type, a duration, and an abnormality degree, and the abnormality detection result specifically includes:

[0018] The test data are subjected to time sequence alignment, and the test data after the alignment are subjected to data cleaning, and the data cleaning includes data normalization to obtain standardized test data;

[0019] A box plot abnormality detection method is introduced, and first quartile data, second quartile data, and third quartile data of each test parameter data index in the standardized test data are calculated to obtain quartile data;

[0020] A box plot of each test parameter data index is drawn according to the quartile data to obtain a box plot set;

[0021] According to the quartile data and the box plot set, the distance between each quartile is calculated to obtain a quartile distance, and according to the quartile distance, the upper limit and the lower limit of the abnormal value of each test parameter data index are determined;

[0022] Each test parameter data index is checked to identify whether there is a data point exceeding the upper limit and the lower limit of the abnormal value, and the data point exceeding the upper limit and the lower limit of the abnormal value is marked as an abnormal value to obtain abnormal value data;

[0023] According to the abnormal value data, the test parameter data index with an abnormal value is determined, and according to the test parameter data index with an abnormal value, the abnormal condition type is determined;

[0024] According to the abnormal value data and the standardized test data, the time when the abnormal value exceeds the upper limit and the lower limit of the abnormal value is determined to obtain the duration of the abnormal condition type;

[0025] According to the abnormal value data, the distance between the abnormal value and the upper limit and the lower limit of the abnormal value in each test parameter data index is determined, and according to the distance, the abnormal degree is determined to obtain an abnormal detection result, the abnormal detection result including the abnormal condition type, the duration of the abnormal condition type, and the abnormal degree.

[0026] In this scheme, according to the abnormal detection result, the test safety of the transformer test station is evaluated to obtain a safety evaluation result, specifically:

[0027] The abnormal detection result is classified according to the abnormal condition type, an evaluation test safety index is defined, the safety index including the number of abnormalities, the time length of abnormal timing, and the abnormal degree value, and the influence degree of each abnormal condition type on the test safety is defined to obtain influence weight information;

[0028] According to the abnormal detection result and the influence weight information, the value of each test safety index is calculated to obtain a calculation result;

[0029] The calculation result is summarized by weighted summation to obtain a test safety evaluation value;

[0030] According to the safety evaluation value, a safety evaluation result of different safety prompt levels is generated, the safety evaluation result including the abnormal detection condition, the classification and weight of the abnormal condition, the calculation result of each safety evaluation index, and the comprehensive conclusion of the safety evaluation.

[0031] In this scheme, based on the safety evaluation result, the optimization space and the optimization direction of the test parameter of the transformer test station are determined, specifically:

[0032] According to the safety evaluation result, the influence of each abnormal situation type on the test safety is sorted from large to small to obtain a safety influence list;

[0033] According to the safety influence list and the abnormal degree of each abnormal situation type, the optimization space and the optimization direction of each abnormal situation type are determined.

[0034] In the scheme, the genetic algorithm is introduced, and the genetic algorithm is used for collaborative test parameter optimization search according to the optimization space and the optimization direction, to obtain the preferred safety test parameters of the variable test station.

[0035] The genetic algorithm is introduced, and the optimization target of the test parameters is determined, a group of initial individuals are randomly generated as a population according to the optimization space and the optimization direction, the influence weight information is used as an optimization evaluation standard, and a fitness function is defined according to the optimization target and the optimization evaluation standard.

[0036] According to the fitness function, the fitness of each initial individual in the population is calculated based on the influence weight information, and a preset number of excellent individuals are selected as parents of the next generation according to the fitness.

[0037] The parent individuals are subjected to a crossover operation to generate new child individuals, the child individuals after the crossover operation are subjected to a mutation operation, the parent individuals and the child individuals after the mutation operation are combined to generate a next generation population, and the next generation population is subjected to a crossover and mutation operation until the optimization target is reached.

[0038] When the optimization target is reached, the fitness of the population reaching the optimization target is evaluated to select an optimal individual, and the test parameter combination corresponding to the optimal individual is used as the preferred safety test parameter of the variable test station.

[0039] The second aspect of the present application also provides a test safety monitoring system of a transformer test station, which comprises a memory and a processor, wherein the memory comprises a test safety monitoring method program of the transformer test station, and the test safety monitoring method program of the transformer test station is executed by the processor to realize the following steps:

[0040] Obtaining test data of the transformer test station on a target transformer, wherein the test data comprises test parameter change data of the transformer test station, top and bottom oil temperature data, vibration and noise data, and electrical parameter data of the target transformer in operation;

[0041] According to the test data, test abnormality detection is performed on the transformer test station to obtain an abnormality detection result, wherein the abnormality detection result comprises an abnormal situation type, a duration, and an abnormal degree.

[0042] According to the abnormality detection result, the test safety of the transformer test station is evaluated, and a safety evaluation result is obtained.

[0043] Based on the safety evaluation result, an optimization space and an optimization direction of a test parameter of the transformer test station are determined.

[0044] A genetic algorithm is introduced, and the genetic algorithm is cooperated with the optimization space and the optimization direction to search for an optimal test parameter, and an optimal safety test parameter of the transformer test station is obtained.

[0045] In the scheme, the safety evaluation result is obtained by evaluating the test safety of the transformer test station according to the abnormality detection result, and specifically:

[0046] The abnormality detection result is classified according to abnormality types, an evaluation test safety index is defined, the safety index includes an abnormality frequency, an abnormality time sequence time length, and an abnormality degree value, an influence degree of each abnormality type on the test safety is defined, and influence weight information is obtained.

[0047] The value of each test safety index is calculated according to the abnormality detection result and the influence weight information, and a calculation result is obtained.

[0048] The calculation result is summarized by weighted summation, and a test safety evaluation value is obtained.

[0049] The safety evaluation result of different safety prompt levels is generated according to the safety evaluation value, and the safety evaluation result includes abnormality detection conditions, classification and weight of abnormality types, calculation results of each safety evaluation index, and a comprehensive conclusion of safety evaluation.

[0050] In the scheme, the optimization space and the optimization direction of the test parameter of the transformer test station are determined based on the safety evaluation result, and specifically:

[0051] According to the safety evaluation result, the influence of each abnormality type on the test safety is sorted from large to small, and a safety influence list is obtained.

[0052] According to the safety influence list and the abnormality degree of each abnormality type, the optimization space and the optimization direction of each abnormality type are determined.

[0053] In the scheme, the genetic algorithm is introduced, and the genetic algorithm is cooperated with the optimization space and the optimization direction to search for an optimal test parameter, and an optimal safety test parameter of the transformer test station is obtained, and specifically:

[0054] The genetic algorithm is introduced, an optimization target of the test parameters is determined, a group of initial individuals are randomly generated as a population according to the optimization space and the optimization direction, the influence weight information is taken as an optimization evaluation standard, and a fitness function is defined according to the optimization target and the optimization evaluation standard;

[0055] The fitness of each initial individual in the population is calculated based on the influence weight information according to the fitness function, and a preset number of excellent individuals are selected as parents of the next generation according to the fitness;

[0056] The parent individuals are subjected to a crossover operation to generate new child individuals, the child individuals after the crossover operation are subjected to a mutation operation, the parent individuals and the child individuals after the mutation operation are combined to generate a next-generation population, and the next-generation population is continuously subjected to the crossover and mutation operations until the optimization target is reached;

[0057] When the optimization target is reached, the optimal individual is selected by evaluating the fitness of the population reaching the optimization target, and the test parameter combination corresponding to the optimal individual is taken as the preferred safety test parameter of the transformer test station.

[0058] The application discloses a test safety monitoring method and system of a transformer test station. First, test data of the transformer test station is acquired. An abnormality detection result is obtained by performing abnormality detection on the test data. Then, test safety is evaluated to obtain a safety evaluation result. The optimization space and the optimization direction of the test parameters are determined according to the evaluation result. Further, a genetic algorithm is introduced to perform collaborative search with the optimization space and the direction, and preferred test parameters are obtained to improve the safety and stability of the transformer test station. The application can effectively monitor test safety and improve the selection ability of test parameters, and has wide application prospects and economic value. BRIEF DESCRIPTION OF DRAWINGS

[0059] Fig. 1 shows a flowchart of the test safety monitoring method of the transformer test station according to the application;

[0060] Fig. 2 shows a flowchart of obtaining the safety evaluation result according to the application;

[0061] Fig. 3 shows a flowchart of determining the optimization space and the optimization direction of the test parameters of the transformer test station according to the application;

[0062] Fig. 4 shows a block diagram of the test safety monitoring system of the transformer test station according to the application. DETAILED DESCRIPTION

[0063] In order to more clearly understand the above-mentioned purposes, features and advantages of the application, the application will be further described in detail below with reference to the drawings and specific embodiments. It should be noted that the embodiments of the application and the features in the embodiments can be combined with each other without conflict.

[0064] In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application. However, it will be apparent to one skilled in the art that the present application can be practiced without the specific details set forth in this description.

[0065] FIG. 1 shows a flowchart of a test safety monitoring method of a transformer test station according to the present application.

[0066] As shown in FIG. 1, the first aspect of the present application provides a test safety monitoring method of a transformer test station, comprising:

[0067] S102, obtaining test data of the transformer test station on a target transformer, the test data comprising test parameter change data of the transformer test station, top layer and bottom layer oil temperature data, vibration and noise data, and electrical parameter data of the target transformer in operation;

[0068] S104, performing test anomaly detection on the transformer test station according to the test data to obtain an anomaly detection result, the anomaly detection result comprising an anomaly type, a duration, and an anomaly degree;

[0069] S106, evaluating the test safety of the transformer test station according to the anomaly detection result to obtain a safety evaluation result;

[0070] S108, determining an optimization space and an optimization direction of test parameters of the transformer test station based on the safety evaluation result;

[0071] S110, introducing a genetic algorithm, and performing collaborative test preferred parameter search on the optimization space and the optimization direction by the genetic algorithm to obtain preferred safety test parameters of the transformer test station.

[0072] It should be noted that by obtaining test data of the transformer test station on a target transformer to perform test anomaly detection on the transformer test station, abnormal conditions in the test can be found in time, such as parameter abnormalities, temperature abnormalities, etc., so that measures can be taken in time to avoid potential safety risks and ensure the safe and stable progress of the test process; by evaluating the test safety of the transformer test station according to the anomaly detection result, the safety risks existing in the test process can be understood to help the operator find abnormal conditions in the test process in time and take appropriate measures to avoid equipment damage or safety accidents caused by abnormal conditions; by determining the optimization space and the optimization direction of test parameters based on the safety evaluation result and introducing a genetic algorithm to perform collaborative test preferred parameter search, the optimal test parameter combination can be efficiently found to improve test efficiency and safety, and the genetic algorithm optimization can search for the optimal solution in a complex parameter space to provide more reasonable test parameter settings for the transformer test station, thereby improving the effectiveness and reliability of the test.

[0073] According to the embodiment of the present application, the test data of the target transformer is acquired by the transformer test station, and the test data includes the test parameter change data of the transformer test station, the top and bottom oil temperature data, the vibration and noise data, and the electrical parameter data of the target transformer in operation, specifically:

[0074] The test parameter change data of the target transformer in the test process is acquired by the industrial computer of the transformer test station, and the test parameters include the output voltage, current, power parameter, output power frequency parameter, top and bottom oil temperature data, and vibration and noise data of the transformer test station.

[0075] The operating voltage, current, power parameter, input power frequency parameter and power factor of the target transformer in the test process are acquired by the sensor to obtain the electrical parameter data of the target transformer.

[0076] It should be noted that the sensor includes a voltage, current sensor, frequency sensor, and digital ammeter.

[0077] According to the embodiment of the present application, the test data is subjected to time sequence alignment operation, and the test data after the alignment operation is subjected to data cleaning, and the data cleaning includes data normalization to obtain standardized test data.

[0078] The test data is subjected to time sequence alignment operation, and the test data after the alignment operation is subjected to data cleaning, and the data cleaning includes data normalization to obtain standardized test data.

[0079] The box plot anomaly detection method is introduced to calculate the first quartile, second quartile and third quartile of each test parameter data index in the standardized test data to obtain quartile data.

[0080] The box plot of each test parameter data index is drawn according to the quartile data to obtain a box plot set.

[0081] The distance between each quartile is calculated according to the quartile data and the box plot set to obtain a quartile distance, and the upper and lower limits of the abnormal value of each test parameter data index are determined according to the quartile distance.

[0082] Each test parameter data index is checked to identify whether there is a data point exceeding the upper and lower limits of the abnormal value, and the data point exceeding the upper and lower limits of the abnormal value is marked as an abnormal value to obtain abnormal value data.

[0083] The test parameter data index with the abnormal value is determined according to the abnormal value data, and the abnormal condition type is determined according to the test parameter data index with the abnormal value.

[0084] determine the time when the abnormal value exceeds the upper limit and the lower limit of the abnormal value according to the abnormal value data and the normalized test data, and obtain the duration of the abnormal condition type;

[0085] determine the distance of the abnormal value in each test parameter data index from the upper limit and the lower limit of the abnormal value according to the abnormal value data, determine the abnormality degree according to the distance, and obtain the abnormality detection result, which includes the abnormal condition type, the duration of the abnormal condition type, and the abnormality degree.

[0086] It should be noted that during the test of the target transformer by the transformer test station, the test data is usually in a stable state, and if the data fluctuates within a certain range, it is also a normal condition. By introducing the box plot abnormality detection method to draw a box plot, the box plot can directly show the distribution of the data. By drawing a box plot of each test parameter data index, the existence of the abnormal value can be clearly identified. The abnormal value is usually defined as a data point outside the upper and lower limits of the abnormal value in the box plot. According to the occurrence of the abnormal value and the abnormal value data index, the type of abnormal condition can be determined. For example, if the abnormal value is concentrated on one or more specific parameter data indexes, the corresponding abnormal condition type can be inferred. Through the timestamp and duration calculation of the abnormal value data, the duration of the abnormal condition can be estimated, which helps to evaluate the impact of the abnormal condition on the test process and the urgency of taking measures. The first quartile (Q1) in the quartile data: the first quartile is the position of the first quartile, the second quartile (Q2, i.e. the median): the data in the middle position is the second quartile, the third quartile (Q3): the third quartile is the position of the third quartile. The box in the box plot represents the interquartile range of the data, and the horizontal lines above and below the box represent the maximum and minimum values of the data. The points outside the box are considered to be abnormal values. Each test parameter data index is each data parameter in each test data.

[0087] FIG. 2 shows a flowchart of the safety evaluation result obtained by the present application.

[0088] According to the embodiments of the present application, the test safety of the transformer test station is evaluated according to the abnormality detection result, and a safety evaluation result is obtained, specifically:

[0089] S202, the abnormality detection result is classified according to the abnormal condition type, an evaluation test safety index is defined, the safety index includes the number of abnormalities, the time length of the abnormal time sequence, the abnormality degree value, and the influence degree of each abnormal condition type on the test safety is defined, and the influence weight information is obtained.

[0090] S204, calculate the value of each test safety index according to the abnormality detection result and the influence weight information, and obtain a calculation result;

[0091] S206, aggregate the calculation result by weighted summation, and obtain a test safety evaluation value;

[0092] S208, generate a safety evaluation result of different safety prompt levels according to the safety evaluation value, wherein the safety evaluation result includes an abnormality detection situation, a classification and weight of abnormality situation, a calculation result of each safety evaluation index, and a comprehensive conclusion of safety evaluation.

[0093] It should be noted that classifying the abnormality detection result according to the abnormality situation type helps to more clearly understand the nature and frequency of the abnormality situation; according to the difference of the abnormality situation type, the influence degree of each abnormality situation on the test safety, i.e. the influence weight, is determined, the weight information reflects the importance and urgency of different abnormality situations, which helps to prioritize the abnormality situations with greater influence; the calculation results of each safety index are weighted and summed to obtain the test safety evaluation value, which comprehensively considers the importance and influence degree of each index, provides a comprehensive reference for the overall safety evaluation, and realizes the comprehensive evaluation of the test safety of the transformer test station.

[0094] FIG. 3 shows a flowchart of the method for judging the optimization space and optimization direction of the test parameters of the transformer test station according to the present application.

[0095] According to the embodiment of the present application, the method for judging the optimization space and optimization direction of the test parameters of the transformer test station based on the safety evaluation result specifically includes:

[0096] S302, sort the influence of each abnormality situation type on the test safety from large to small according to the safety evaluation result, and obtain a safety influence list;

[0097] S304, judge the optimization space and optimization direction of each abnormality situation type according to the safety influence list and the abnormality degree of each abnormality situation type.

[0098] It should be noted that by sorting and analyzing the influence of the abnormality situation type, the problems and risks existing in the test process can be accurately located, and the optimization can be targeted, according to the priority and abnormality degree of the abnormality situation type, the optimization space and optimization direction of each abnormality situation type are determined, which helps to guide the formulation and implementation of the optimization measures; the optimization space refers to the aspects or links that can be improved and optimized in the test process, and the optimization direction refers to the direction or focus of the optimization measures determined for each abnormality situation type.

[0099] According to the embodiment of the present application, the genetic algorithm is introduced to cooperatively search the optimal parameters with the optimization space and the optimization direction, and the optimal safety test parameters of the variable test station are obtained, specifically as follows:

[0100] The genetic algorithm is introduced to determine the optimization target of the test parameters, a group of initial individuals are randomly generated as a population according to the optimization space and the optimization direction, the influence weight information is taken as the optimization evaluation standard, and the fitness function is defined according to the optimization target and the optimization evaluation standard;

[0101] The fitness of each initial individual in the population is calculated based on the influence weight information according to the fitness function, and a preset number of excellent individuals are selected as the parents of the next generation according to the fitness;

[0102] The parent individuals are subjected to a crossover operation to generate new child individuals, the child individuals after the crossover operation are subjected to a mutation operation, the parent individuals and the child individuals after the mutation operation are combined to generate the next generation population, and the next generation population is continuously subjected to the crossover and mutation operations until the optimization target is reached;

[0103] When the optimization target is reached, the optimal individual is selected by evaluating the fitness of the population reaching the optimization target, and the test parameter combination corresponding to the optimal individual is taken as the optimal safety test parameters of the variable test station.

[0104] It should be noted that a group of initial individuals are randomly generated as a population by the genetic algorithm and according to the optimization space and the optimization direction, these individuals represent different test parameter combinations, which provide a starting point for the search of the genetic algorithm, the fitness function is defined according to the influence weight information to evaluate the advantages and disadvantages of each individual, the fitness function can comprehensively consider factors such as abnormal situation type, abnormal duration, and abnormal degree, to ensure that the optimal test parameter combination can improve the test safety as much as possible; the population is iterated by the operations such as selection, crossover, and mutation of the genetic algorithm, so that the population gradually evolves to better individuals, and a better test parameter combination can be searched in the parameter space to meet the optimization target; the genetic algorithm is introduced to optimize the test parameters, which can effectively search the optimal test parameter combination, improve the safety and efficiency of the test station, and reduce the occurrence and influence of abnormal situations in the test process; the group of initial individuals includes multiple individuals, each initial individual represents a combination of test parameters, and the generated test parameter combination is within the optimization space.

[0105] According to the embodiment of the present application, the method further comprises:

[0106] The optimal safety test parameters are implemented, and secondary abnormality detection is performed on the transformer test station after the implementation to obtain secondary abnormality detection results;

[0107] According to the comparison between the secondary abnormality detection result and the abnormality detection result, it is judged whether the abnormality situation type in the abnormality detection result still exists in the secondary abnormality detection result, if yes, the abnormality situation type is marked to obtain a marked abnormality situation type;

[0108] According to the secondary abnormality detection result, a secondary abnormality degree of the marked abnormality situation type is obtained, if the secondary abnormality degree does not decrease compared with the abnormality degree in the abnormality detection result, the transformer test station is marked as a fault state;

[0109] According to the marked abnormality situation type, a fault type is determined, and a maintenance operation is performed on the transformer test station according to the fault type.

[0110] It should be noted that after the preferred safety test parameters of the transformer test station are implemented, the secondary abnormality detection is performed on the transformer test station to obtain a secondary abnormality detection result, if the abnormality situation type in the abnormality detection result still appears in the secondary abnormality detection result during the test process of the transformer test station, it can be determined that the transformer test station is in a fault state, and cannot be tested and optimized by adjusting the test parameters, therefore, at this time, the maintenance operation should be performed on the transformer test station, which can timely and accurately diagnose and handle the fault of the transformer test station, and ensure the safe operation and stability of the transformer test station.

[0111] Fig. 4 shows a block diagram of a test safety monitoring system of a transformer test station according to the present application.

[0112] The second aspect of the present application further provides a test safety monitoring system 4 of a transformer test station, which comprises a memory 41 and a processor 42, wherein the memory comprises a test safety monitoring method program of a transformer test station, and the test safety monitoring method program of the transformer test station is executed by the processor to realize the following steps:

[0113] Obtaining test data of the transformer test station on a target transformer, wherein the test data comprises test parameter change data of the transformer test station, top layer and bottom layer oil temperature data, vibration and noise data, and electrical parameter data of the target transformer in operation;

[0114] Performing test abnormality detection on the transformer test station according to the test data to obtain an abnormality detection result, wherein the abnormality detection result comprises an abnormality situation type, a duration, and an abnormality degree;

[0115] Evaluating the test safety of the transformer test station according to the abnormality detection result to obtain a safety evaluation result;

[0116] Judging the optimization space and optimization direction of the test parameters of the transformer test station based on the safety evaluation result;

[0117] The genetic algorithm is introduced, and the genetic algorithm is cooperated with the optimization space and the optimization direction to perform parameter search, and optimal safety test parameters of the transformer test station are obtained.

[0118] It should be noted that the test data of the transformer test station on the target transformer is acquired to detect test abnormalities of the transformer test station, so that abnormal conditions in the test, such as parameter abnormalities and temperature abnormalities, can be found in time, and thus potential safety risks can be avoided in time, and the safety and stability of the test process are ensured; the test safety of the transformer test station is evaluated according to the abnormality detection result, so that the safety risks existing in the test process are known, and the abnormal conditions in the test process are found in time by the operator, and corresponding measures are taken to avoid equipment damage or safety accidents caused by abnormal conditions; the optimization space and the optimization direction of the test parameters are determined through the safety evaluation result, and the genetic algorithm is introduced to perform cooperative test parameter search, and thus the optimal test parameter combination can be efficiently found to improve the test efficiency and safety, and the genetic algorithm optimization can search for the optimal solution in a complex parameter space to provide more reasonable test parameter settings for the transformer test station, and thus the test effect and reliability are improved.

[0119] According to the embodiment of the present application, the test data of the transformer test station on the target transformer is acquired, and the test data includes test parameter change data of the transformer test station, top and bottom oil temperature data, vibration and noise data, and electrical parameter data of the target transformer in operation, and specifically includes:

[0120] The test parameter change data of the transformer test station in the test process of the target transformer is acquired by an industrial computer of the transformer test station, and the test parameters include output voltage, current, power parameters, output power frequency parameters, top and bottom oil temperature data, and vibration and noise data of the transformer test station;

[0121] The running voltage, current, power parameters, input power frequency parameters and power factor of the target transformer in the test process are acquired by a sensor to obtain the electrical parameter data of the target transformer.

[0122] It should be noted that the sensor includes a voltage sensor, a current sensor, a frequency sensor and a digital ammeter.

[0123] According to the embodiment of the present application, the test data is subjected to time sequence alignment operation, and the test data after the alignment operation is subjected to data cleaning, and the data cleaning includes data normalization to obtain standardized test data.

[0124] The test data is subjected to time sequence alignment operation, and the test data after the alignment operation is subjected to data cleaning, and the data cleaning includes data normalization to obtain standardized test data.

[0125] The box plot anomaly detection method is introduced, the first quartile, the second quartile and the third quartile of each test parameter data index in the standardized test data are calculated, and quartile data is obtained;

[0126] According to the quartile data, a box plot of each test parameter data index is drawn, and a box plot set is obtained;

[0127] According to the quartile data and the box plot set, the distance between each quartile is calculated, the quartile range is obtained, and the upper limit and the lower limit of the abnormal value of each test parameter data index are determined according to the quartile range;

[0128] Each test parameter data index is checked to identify whether there is a data point exceeding the upper limit and the lower limit of the abnormal value, the data point exceeding the upper limit and the lower limit of the abnormal value is marked as an abnormal value, and abnormal value data is obtained;

[0129] According to the abnormal value data, the test parameter data index with the abnormal value is determined, and the abnormal condition type is determined according to the test parameter data index with the abnormal value;

[0130] According to the abnormal value data and the standardized test data, the time when the abnormal value exceeds the upper limit and the lower limit of the abnormal value is determined, and the duration of the abnormal condition type is obtained;

[0131] According to the abnormal value data, the distance between the abnormal value and the upper limit and the lower limit of the abnormal value in each test parameter data index is determined, the abnormal degree is determined according to the distance, the abnormal detection result is obtained, and the abnormal detection result includes the abnormal condition type, the duration of the abnormal condition type and the abnormal degree.

[0132] It should be noted that when the transformer test station tests the target transformer, the test data is usually stable, and if the data fluctuates within a certain range, it is also a normal situation; the box plot is drawn by introducing the box plot anomaly detection method, and the box plot can directly show the distribution of the data, and by drawing the box plot of each test parameter data index, the existence of the abnormal value can be clearly identified. The abnormal value is usually defined as the data point outside the upper and lower limits of the abnormal value in the box plot; according to the occurrence of the abnormal value and the abnormal value data index, the type of the abnormal situation can be determined, for example, if the abnormal value is concentrated on one or more specific parameter data indexes, the corresponding abnormal situation type can be inferred; the duration of the abnormal situation can be estimated by the timestamp and duration calculation of the abnormal value data, which helps to evaluate the impact of the abnormal situation on the test process and the urgency of taking measures; the first quartile (Q1) in the quartile data: the first quartile is the position of the first quartile, the second quartile (Q2, i.e. the median): the data in the middle position is the second quartile, the third quartile (Q3): the third quartile is the position of the third quartile; the box in the box plot represents the interquartile range of the data, and the horizontal lines above and below the box represent the maximum and minimum values of the data, and the points outside the box are considered to be abnormal values; each test parameter data index is each data parameter in each test data.

[0133] According to the embodiment of the present application, the test safety of the transformer test station is evaluated according to the abnormality detection result, and a safety evaluation result is obtained, specifically:

[0134] The abnormality detection result is classified according to the type of abnormal situation, an evaluation test safety index is defined, the safety index includes the number of abnormalities, the time length of abnormal time sequence, the abnormality degree value, and the influence degree of each abnormal situation type on the test safety is defined, and the influence weight information is obtained;

[0135] According to the abnormality detection result and the influence weight information, the value of each test safety index is calculated, and a calculation result is obtained;

[0136] The calculation result is summarized by weighted summation, and a test safety evaluation value is obtained;

[0137] According to the safety evaluation value, a safety evaluation result of different safety prompt levels is generated, and the safety evaluation result includes the abnormality detection situation, the classification and weight of the abnormal situation, the calculation result of each safety evaluation index, and the comprehensive conclusion of the safety evaluation.

[0138] It should be noted that classifying the abnormality detection result according to the abnormal situation type helps to more clearly understand the nature and frequency of the abnormal situation; according to the difference of the abnormal situation type, the influence degree of each abnormal situation on the test safety, that is, the influence weight, is determined, the weight information reflects the importance and urgency of different abnormal situations, which helps to prioritize the abnormal situations with greater influence; the calculation results of each safety index are weighted and summed to obtain the test safety evaluation value, which comprehensively considers the importance and influence degree of each index, provides a comprehensive reference for overall safety evaluation, and realizes comprehensive evaluation of the test safety of the transformer test station.

[0139] According to the embodiment of the present application, the optimization space and optimization direction of the test parameter of the transformer test station are determined based on the safety evaluation result, specifically:

[0140] According to the safety evaluation result, the influence of each abnormal situation type on the test safety is sorted from large to small to obtain a safety influence list;

[0141] According to the safety influence list and the abnormal degree of each abnormal situation type, the optimization space and optimization direction of each abnormal situation type are determined.

[0142] It should be noted that by sorting and analyzing the influence of the abnormal situation type, the problems and risks existing in the test process can be accurately located, and optimization can be performed accordingly, according to the priority and abnormal degree of the abnormal situation type, the optimization space and optimization direction of each abnormal situation type are determined, which helps to guide the formulation and implementation of optimization measures; the optimization space refers to the aspects or links that can be improved and optimized in the test process, and the optimization direction refers to the direction or focus of the optimization measures determined for each abnormal situation type.

[0143] According to the embodiment of the present application, the genetic algorithm is introduced, and the genetic algorithm is used to search for the preferred test parameters of the transformer test station in cooperation with the optimization space and optimization direction, specifically:

[0144] The genetic algorithm is introduced to determine the optimization target of the test parameter, a group of initial individuals are randomly generated as a population according to the optimization space and optimization direction, the influence weight information is used as an optimization evaluation standard, and a fitness function is defined according to the optimization target and the optimization evaluation standard;

[0145] According to the fitness function, the fitness of each initial individual in the population is calculated based on the influence weight information, and a preset number of excellent individuals are selected as the parents of the next generation according to the fitness;

[0146] The parent individual is subjected to a crossover operation to generate a new child individual, the child individual after the crossover operation is subjected to a mutation operation, the parent individual and the child individual after the mutation operation are combined to generate a next generation population, and the next generation population is continuously subjected to the crossover and mutation operations until an optimization target is reached.

[0147] When the optimization target is reached, an optimal individual is selected by evaluating the fitness of the population reaching the optimization target, and the test parameter combination corresponding to the optimal individual is used as the preferred safety test parameter of the test station.

[0148] It should be noted that a group of initial individuals are randomly generated as a population by the genetic algorithm and according to the optimization space and the optimization direction, the individuals represent different test parameter combinations and provide a starting point for the search of the genetic algorithm, the fitness function is defined according to the influence weight information to evaluate the advantages and disadvantages of each individual, the fitness function can comprehensively consider factors such as abnormal situation type, abnormal duration and abnormal degree, and ensure that the preferred test parameter combination can improve the test safety as much as possible; the population is iterated by the operations such as selection, crossover and mutation of the genetic algorithm, so that the population gradually evolves to better individuals, and better test parameter combinations can be searched in the parameter space to meet the optimization target; the genetic algorithm is introduced to optimize the test parameters, which can effectively search for the optimal test parameter combination, improve the safety and efficiency of the test station, and reduce the occurrence and influence of abnormal situations in the test process; the group of initial individuals includes multiple individuals, each initial individual represents a combination of test parameters, and the generated test parameter combination is within the optimization space.

[0149] The application discloses a test safety monitoring method and system for a transformer test station. First, the test data of the transformer test station is obtained. The test data is subjected to abnormality detection to obtain an abnormality detection result. Then, the test safety is evaluated to obtain a safety evaluation result. The optimization space and the optimization direction of the test parameters are determined according to the evaluation result. Further, the genetic algorithm is introduced to cooperatively search the optimization space and the direction to obtain preferred test parameters, so as to improve the safety and stability of the transformer test station. The application can effectively monitor the test safety, improve the selection ability of the test parameters, and has wide application prospect and economic value.

[0150] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other manners. The described device embodiments are merely illustrative. For example, the division of the units is only a logical function division. There can be another division manner for the actual implementation, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed coupling, or direct coupling or communication connection between the components can be indirect coupling or communication connection through some interfaces, devices, or units, and can be electrical, mechanical, or in other forms.

[0151] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units; they can be located in one place, or distributed on multiple network units; and some or all of the units can be selected according to actual needs to achieve the purpose of the embodiments.

[0152] In addition, each functional unit in each embodiment of the present application can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be implemented in the form of hardware or in the form of hardware plus software functional units.

[0153] Those of ordinary skill in the art can understand that all or part of the steps of the above-described method embodiments can be completed by a program instructing related hardware, and the foregoing program can be stored in a computer readable storage medium, and when the program is executed, the steps of the method embodiments are executed; and the foregoing storage medium includes: mobile storage devices, read-only memory (ROM), random access memory (RAM), magnetic disks or optical disks, and various media that can store program codes.

[0154] Alternatively, the integrated units of the present application, if implemented in the form of software functional modules and sold or used as independent products, can also be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the embodiments of the present application can be embodied in the form of a software product, and the computer software product is stored in a storage medium, and includes several instructions for causing 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 the embodiments of the present application. The foregoing storage medium includes: mobile storage devices, ROM, RAM, magnetic disks or optical disks, and various media that can store program codes.

[0155] The above merely provides the specific implementation of the present application, but the protection scope of the present application is not limited thereto, any person skilled in the art can easily think of the changes or replacements within the technical range disclosed by the present application, which should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method of monitoring the safety of a test in a transformer test station, characterized in that The method comprises the following steps: obtaining test data of a target transformer by a transformer test station, wherein the test data comprises test parameter change data of the transformer test station, top and bottom oil temperature data, vibration and noise data, and electrical parameter data of the target transformer in operation; performing test anomaly detection on the transformer test station according to the test data to obtain an anomaly detection result, wherein the anomaly detection result comprises an anomaly type, a duration, and an anomaly degree; evaluating test safety of the transformer test station according to the anomaly detection result to obtain a safety evaluation result; judging an optimization space and an optimization direction of test parameters of the transformer test station based on the safety evaluation result; introducing a genetic algorithm, and performing collaborative test optimization parameter searching on the optimization space and the optimization direction by the genetic algorithm to obtain optimal safety test parameters of the transformer test station.

2. A method of monitoring the safety of tests in a transformer test station according to claim 1, characterized in that The test data of the target transformer by the transformer test station comprises test parameter change data of the transformer test station, top and bottom oil temperature data, vibration and noise data, and electrical parameter data of the target transformer in operation, and specifically comprises: obtaining test parameter change data of the target transformer by the transformer test station through an industrial computer of the transformer test station, wherein the test parameters comprise output voltage, current, power parameters, output power frequency parameters, top and bottom oil temperature data, and vibration and noise data of the transformer test station; obtaining electrical voltage, current, power parameters, input power frequency parameters, and power factor of the target transformer in the test process through a sensor to obtain electrical parameter data of the target transformer.

3. The method of claim 1, wherein the method further comprises: The anomaly detection result comprises an anomaly type, a duration, and an anomaly degree, and specifically comprises: performing time sequence alignment on the test data, and performing data cleaning on the test data after the alignment, wherein the data cleaning comprises data normalization to obtain standardized test data; introducing a box plot anomaly detection method, calculating first, second, and third quartiles of each test parameter data index in the standardized test data to obtain quartile data; drawing a box plot of each test parameter data index according to the quartile data to obtain a box plot set; calculating distances between each quartile according to the quartile data and the box plot set to obtain a quartile range, and determining an upper limit and a lower limit of an abnormal value of each test parameter data index according to the quartile range; checking each test parameter data index to identify whether there is a data point exceeding the upper limit and the lower limit of the abnormal value, marking the data point exceeding the upper limit and the lower limit of the abnormal value as an abnormal value to obtain abnormal value data; determining a test parameter data index having an abnormal value according to the abnormal value data, and determining an anomaly type according to the test parameter data index having the abnormal value; determining a time when the abnormal value exceeds the upper limit and the lower limit of the abnormal value according to the abnormal value data and the standardized test data to obtain a duration of the anomaly type. According to the abnormal value data, the distance of the abnormal value in each test parameter data index from the upper limit and the lower limit of the abnormal value is determined, the abnormal degree is determined according to the distance, and an abnormal detection result is obtained, which includes an abnormal situation type, a duration of the abnormal situation type, and an abnormal degree.

4. The method of claim 1, wherein the transformer test station is a transformer test station according to claim 1, characterized in that, According to the abnormal detection result, the test safety of the transformer test station is evaluated, and a safety evaluation result is obtained, which is specifically: The abnormal detection result is classified according to the abnormal situation type, an evaluation test safety index is defined, the safety index includes the number of abnormalities, the time length of abnormal timing, the abnormal degree value, and the influence degree of each abnormal situation type on the test safety is defined, and the influence weight information is obtained; According to the abnormal detection result and the influence weight information, the value of each test safety index is calculated, and a calculation result is obtained; The calculation result is summarized by weighted summation, and a test safety evaluation value is obtained; According to the safety evaluation value, a safety evaluation result of different safety prompt levels is generated, which includes abnormal detection situation, classification and weight of abnormal situation, calculation result of each safety evaluation index, and comprehensive conclusion of safety evaluation.

5. The method of claim 1, wherein the method further comprises: According to the safety evaluation result, the optimization space and optimization direction of the test parameters of the transformer test station are determined, which is specifically: According to the safety evaluation result, the influence of each abnormal situation type on the test safety is sorted from large to small, and a safety influence list is obtained; According to the safety influence list and the abnormal degree of each abnormal situation type, the optimization space and optimization direction of each abnormal situation type are determined.

6. A method of monitoring the safety of tests on a transformer test station according to claim 4, characterized in that, The genetic algorithm is introduced, and the genetic algorithm is used for collaborative test optimization parameter search with the optimization space and optimization direction, and the optimal safety test parameters of the transformer test station are obtained, which is specifically: The genetic algorithm is introduced, the optimization target of the test parameters is determined, a group of initial individuals are randomly generated as a population according to the optimization space and optimization direction, the influence weight information is used as the optimization evaluation standard, and the fitness function is defined according to the optimization target and the optimization evaluation standard; According to the fitness function, the fitness of each initial individual in the population is calculated based on the influence weight information, and the fitness is used to select a predetermined number of excellent individuals as the parents of the next generation; The parent individuals are crossed to generate new child individuals, the child individuals after the crossover operation are mutated, the parent individuals and the mutated child individuals are combined to generate the next generation population, and the next generation population is continuously crossed and mutated until the optimization target is reached. When the optimization target is reached, the optimal individual is selected by evaluating the fitness of the population that reaches the optimization target, and the test parameter combination corresponding to the optimal individual is used as the optimal safety test parameter of the transformer test station.

7. A test safety monitoring system for a transformer test station, characterized by The test safety monitoring system of the transformer test station includes a storage and a processor, the storage includes a transformer test station test safety monitoring method program, and the transformer test station test safety monitoring method program is executed by the processor to realize the following steps: Obtaining test data of a target transformer at a transformer test station, the test data including test parameter change data of the transformer test station, top and bottom oil temperature data, vibration and noise data, and electrical parameter data of the target transformer in operation; Performing test anomaly detection on the transformer test station according to the test data to obtain an anomaly detection result, the anomaly detection result including an anomaly type, a duration, and an anomaly degree; Evaluating test safety of the transformer test station according to the anomaly detection result to obtain a safety evaluation result; Judging an optimization space and an optimization direction of a test parameter of the transformer test station based on the safety evaluation result; Introducing a genetic algorithm, and performing collaborative test preferred parameter searching on the optimization space and the optimization direction by using the genetic algorithm to obtain an optimized safety test parameter of the transformer test station.

8. A test safety monitoring system for a transformer test station according to claim 7, characterized in that The evaluating test safety of the transformer test station according to the anomaly detection result to obtain the safety evaluation result specifically includes: Classifying the anomaly detection result according to the anomaly type, defining an evaluation test safety index including an anomaly frequency, an anomaly time length, and an anomaly degree value, and defining an influence degree of each anomaly type on the test safety to obtain influence weight information; Calculating a value of each test safety index according to the anomaly detection result and the influence weight information to obtain a calculation result; Summarizing the calculation result by weighted summation to obtain a test safety evaluation value; Generating a safety evaluation result of different safety prompt levels according to the safety evaluation value, the safety evaluation result including anomaly detection information, anomaly type classification and weight, a calculation result of each safety evaluation index, and a comprehensive conclusion of the safety evaluation.

9. A test safety monitoring system for a transformer test station according to claim 7, characterized in that, The judging the optimization space and the optimization direction of the test parameter of the transformer test station based on the safety evaluation result specifically includes: Sorting, according to the safety evaluation result, each anomaly type on the test safety from large to small to obtain a safety influence list; Judging, according to the safety influence list and the anomaly degree of each anomaly type, an optimization space and an optimization direction of each anomaly type.

10. A test safety monitoring system for a transformer test station according to claim 8, characterized in that The introducing the genetic algorithm, and performing collaborative test preferred parameter searching on the optimization space and the optimization direction by using the genetic algorithm to obtain the optimized safety test parameter of the transformer test station specifically includes: Introducing the genetic algorithm, determining an optimization target of the test parameter, randomly generating a group of initial individuals as a population according to the optimization space and the optimization direction, taking the influence weight information as an optimization evaluation standard, and defining a fitness function according to the optimization target and the optimization evaluation standard; Calculating a fitness of each initial individual in the population based on the influence weight information according to the fitness function, and selecting a preset number of excellent individuals as parents of the next generation according to the fitness; Performing crossover operation on the parent individuals to generate new child individuals, performing mutation operation on the child individuals after the crossover operation, combining the parent individuals and the child individuals after the mutation operation to generate a next generation population, and continuously performing crossover and mutation operation on the next generation population until the optimization target is reached. When the optimization target is reached, the optimal individual is selected by evaluating the fitness of the population reaching the optimization target, and the test parameter combination corresponding to the optimal individual is used as the preferred safety test parameter of the variable test station.

Images