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

Abstract

The present invention discloses a method and system for monitoring the test safety of a transformer test station. The present invention first obtains the test data of the transformer test station. By performing anomaly detection on the test data, an anomaly detection result is obtained. Subsequently, the test safety is evaluated to obtain a safety evaluation result. According to the evaluation result, the optimization space and direction of the test parameters are determined. Further, a genetic algorithm is introduced to perform collaborative search with the optimization space and direction to obtain the optimized test parameters, so as to improve the safety and stability of the transformer test station. The present invention can effectively monitor the test safety, improve the optimization ability of the test parameters, and has broad application prospects and economic value.

Description

Technical Field

[0001] The present invention relates to the technical field of transformer test station monitoring, and particularly relates to a test safety monitoring method and system for a transformer test station. Background Art

[0002] A transformer is an important device in the power system, and its performance and safety directly affect the stable operation of the power system. To ensure the safety and reliability of the transformer, various tests are usually required, 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, thus affecting the safety and accuracy of the test.

[0003] Currently, the safety monitoring of transformer test stations mainly relies on manual experience judgment or traditional monitoring methods, such as regular inspections, data records, etc. However, these methods have the following disadvantages: one is that manual experience judgment is greatly affected by subjective factors and is prone to misjudgment or missed judgment; the other is that traditional monitoring methods usually can only provide simple records of test data and cannot perform in-depth anomaly detection and safety assessment.

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

[0005] In view of the problems and deficiencies existing in the above-mentioned prior art, the present invention proposes a test safety monitoring method for a transformer test station. By comprehensively analyzing test data and performing anomaly detection, and combining a genetic algorithm to optimize test parameters, the automatic monitoring and evaluation of the safety of the transformer test station are realized, and the safety and accuracy of the test are improved. Summary of the Invention

[0006] To solve the above-mentioned at least one technical problem, the present invention proposes a test safety monitoring method and system for a transformer test station.

[0007] The first aspect of the present invention provides a test safety monitoring method for a transformer test station, including:

[0008] Obtain the test data of the target transformer by the transformer test station, where the test data includes the test parameter change data of the transformer test station, the top-layer and bottom-layer oil temperature data, the vibration and noise data, and the electrical parameter data of the operation of the target transformer;

[0009] Perform test anomaly detection on the transformer test station according to the test data to obtain an anomaly detection result, where the anomaly detection result includes the type of abnormal situation, the duration, and the degree of abnormality;

[0010] Evaluate the test safety of the transformer test station based on the abnormal detection result to obtain a safety evaluation result;

[0011] Judge the optimization space and optimization direction of the test parameters of the transformer test station based on the safety evaluation result;

[0012] Introduce a genetic algorithm, and conduct collaborative test optimization parameter search with the genetic algorithm and the optimization space and direction to obtain the optimized safety test parameters of the transformer test station.

[0013] In this solution, the test data of the transformer test station for the target transformer is obtained. 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 during operation. Specifically:

[0014] Obtain the test parameter change data during the test of the transformer test station for the target transformer through the industrial control computer of the transformer test station. The test parameters include the output voltage, current, power parameter, output power supply frequency parameter, top and bottom oil temperature data, vibration and noise data of the transformer test station;

[0015] Obtain the electrical parameter data of the target transformer by using sensors to measure the operating voltage, current, power parameter, input power supply frequency parameter and power factor during the test.

[0016] In this solution, the test data is used to perform abnormal detection on the transformer test station to obtain an abnormal detection result. The abnormal detection result includes the type of abnormal situation, the duration, and the degree of abnormality. Specifically:

[0017] Perform time series alignment operation on the test data, and perform data cleaning on the aligned test data. The data cleaning includes data normalization to obtain standardized test data;

[0018] Introduce a box plot abnormal detection method, calculate the first quartile, second quartile, and third quartile of each test parameter data index in the standardized test data to obtain quartile data;

[0019] Draw a box plot of each test parameter data index based on the quartile data to obtain a box plot set;

[0020] Calculate the distance between each quartile based on the quartile data and the box plot set to obtain the interquartile range, and determine the upper and lower limits of the abnormal values of each test parameter data index according to the interquartile range;

[0021] Check each test parameter data index to identify data points that exceed the upper and lower limits of the outliers. Mark the data points that exceed the upper and lower limits of the outliers as outliers to obtain outlier data;

[0022] Determine the test parameter data index where the outlier appears based on the outlier data, and determine the type of abnormal situation based on the test parameter data index where the outlier appears;

[0023] Determine the time when the outlier exceeds the upper and lower limits of the outlier based on the outlier data and the standardized test data to obtain the duration of the abnormal situation type;

[0024] Determine the distance between the outlier and the upper and lower limits of the outlier in each test parameter data index based on the outlier data, and determine the degree of abnormality based on the distance to obtain the abnormal detection result. The abnormal detection result includes the type of abnormal situation, the duration of the abnormal situation type, and the degree of abnormality.

[0025] In this solution, evaluate the test safety of the transformer test station based on the abnormal detection result to obtain the safety evaluation result. Specifically:

[0026] Classify the abnormal detection results according to the type of abnormal situation, define the evaluation index of test safety. The safety index includes the number of abnormalities, the length of the abnormal time series, and the degree of abnormality value, and define the influence degree of each abnormal situation type on the test safety to obtain the influence weight information;

[0027] Calculate the value of each test safety index according to the abnormal detection result and the influence weight information to obtain the calculation result;

[0028] Summarize the calculation results through weighted summation to obtain the test safety evaluation value;

[0029] Generate a safety evaluation result with different safety prompt levels according to the safety evaluation value. The safety evaluation result includes the abnormal detection situation, the classification and weight of the abnormal situation, the calculation results of each safety evaluation index, and the comprehensive conclusion of the safety evaluation.

[0030] In this solution, judge the optimization space and optimization direction of the test parameters of the transformer test station based on the safety evaluation result. Specifically:

[0031] Sort the influence of each abnormal situation type on the test safety from large to small according to the safety evaluation result to obtain a safety influence list;

[0032] Judge the optimization space and optimization direction of each abnormal situation type according to the safety influence list and the degree of abnormality of each abnormal situation type.

[0033] In this solution, a genetic algorithm is introduced, and the genetic algorithm is used to conduct collaborative experimental optimization for parameter search in combination with the optimization space and optimization direction to obtain the optimal safety test parameters for the variable voltage test station. Specifically:

[0034] Introduce a genetic algorithm, determine the optimization objective of the test parameters, randomly generate a group of initial individuals as the population according to the optimization space and optimization direction, use the influence weight information as the optimization evaluation criterion, and define the fitness function according to the optimization objective and the optimization evaluation criterion;

[0035] Calculate the fitness of each initial individual in the population based on the influence weight information according to the fitness function, and select a preset number of excellent individuals as the parents of the next generation according to the fitness;

[0036] Perform crossover operations on the parent individuals to generate new offspring individuals, perform mutation operations on the offspring individuals after the crossover operations, combine the parent individuals and the mutated offspring individuals to generate the next generation of population, and continue the crossover and mutation operations on the next generation of population until the optimization objective is achieved;

[0037] When the optimization objective is achieved, select the optimal individual by evaluating the fitness of the population that has achieved the optimization objective, and use the test parameter combination corresponding to the optimal individual as the optimal safety test parameters for the variable voltage test station.

[0038] The second aspect of the present invention also provides a test safety monitoring system for a transformer test station. The system includes: a memory and a processor. The memory includes a test safety monitoring method program for the transformer test station. When the test safety monitoring method program for the transformer test station is executed by the processor, the following steps are implemented:

[0039] Obtain the test data of the transformer test station for the target transformer. 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 during operation;

[0040] Conduct test anomaly detection on the transformer test station according to the test data to obtain an anomaly detection result. The anomaly detection result includes the type of anomaly situation, the duration, and the degree of anomaly;

[0041] Evaluate the test safety of the transformer test station according to the anomaly detection result to obtain a safety evaluation result;

[0042] Judge the optimization space and optimization direction of the test parameters of the transformer test station based on the safety evaluation result;

[0043] Introduce a genetic algorithm, and conduct collaborative experiment and optimal parameter search with the genetic algorithm, the optimization space, and the optimization direction to obtain the optimal safety test parameters of the variable voltage test station.

[0044] In this solution, evaluate the test safety of the transformer test station according to the anomaly detection result to obtain a safety evaluation result, specifically:

[0045] Classify the anomaly detection results according to the types of anomaly situations, define the safety evaluation indicators for the test. The safety indicators include the number of anomalies, the length of the anomaly time series, and the anomaly degree value, and define the influence degree of each anomaly situation type on the test safety to obtain influence weight information;

[0046] Calculate the value of each test safety indicator according to the anomaly detection result and the influence weight information to obtain a calculation result;

[0047] Summarize the calculation results through weighted summation to obtain a test safety evaluation value;

[0048] Generate a safety evaluation result with different safety prompt levels according to the safety evaluation value. The safety evaluation result includes the anomaly detection situation, the classification and weight of the anomaly situation, the calculation results of each safety evaluation indicator, and the comprehensive conclusion of the safety evaluation.

[0049] In this solution, judge the optimization space and optimization direction of the test parameters of the transformer test station based on the safety evaluation result, specifically:

[0050] Sort the influence of each anomaly situation type on the test safety from large to small according to the safety evaluation result to obtain a safety influence list;

[0051] Judge the optimization space and optimization direction of each anomaly situation type according to the safety influence list and the anomaly degree of each anomaly situation type.

[0052] In this solution, introduce a genetic algorithm, and conduct collaborative experiment and optimal parameter search with the genetic algorithm, the optimization space, and the optimization direction to obtain the optimal safety test parameters of the variable voltage test station, specifically:

[0053] Introduce a genetic algorithm, determine the optimization goal of the test parameters, randomly generate a group of initial individuals as a population according to the optimization space and optimization direction, use the influence weight information as the optimization evaluation criterion, and define a fitness function according to the optimization goal and the optimization evaluation criterion;

[0054] Calculate the fitness of each initial individual in the population based on the influence weight information according to the fitness function, and select a preset number of excellent individuals as the parents of the next generation according to the fitness;

[0055] Perform crossover operation on the parental individuals to generate new offspring individuals, perform mutation operation on the offspring individuals after crossover operation, combine the parental individuals and the mutated offspring individuals to generate the next generation population, and continue the crossover and mutation operations on the next generation population until the optimization goal is reached;

[0056] When the optimization goal is reached, select the optimal individual by evaluating the fitness of the population that reaches the optimization goal, and the combination of test parameters corresponding to the optimal individual is used as the preferred safety test parameters of the variable voltage test station.

[0057] The present invention discloses a method and system for monitoring the test safety of a transformer test station. The present invention first obtains the test data of the transformer test station. By performing anomaly detection on the test data, the anomaly detection result is obtained. Subsequently, the test safety is evaluated to obtain the safety evaluation result. According to the evaluation result, the optimization space and optimization direction of the test parameters are determined. Further introduce the genetic algorithm, and perform collaborative search with the optimization space and direction to obtain the preferred test parameters, so as to improve the safety and stability of the transformer test station. The present invention can effectively monitor the test safety, improve the ability to select the preferred test parameters, and has broad application prospects and economic value. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 Shows the flowchart of a method for monitoring the test safety of a transformer test station according to the present invention;

[0059] Figure 2 Shows the flowchart of obtaining the safety evaluation result according to the present invention;

[0060] Figure 3 Shows the flowchart of determining the optimization space and optimization direction of the test parameters of the transformer test station according to the present invention;

[0061] Figure 4 Shows the block diagram of a system for monitoring the test safety of a transformer test station according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0062] In order to more clearly understand the above objects, features and advantages of the present invention, the present invention will be further described in detail below with reference to the drawings and specific embodiments. It should be noted that, without conflict, the embodiments of the present application and the features in the embodiments can be combined with each other.

[0063] Many specific details are set forth in the following description in order to provide a thorough understanding of the present invention. However, the present invention may be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited by the specific embodiments disclosed below.

[0064] Figure 1The flowchart of a test safety monitoring method for a transformer test station according to the present invention is shown.

[0065] As Figure 1 shown, a first aspect of the present invention provides a test safety monitoring method for a transformer test station, including:

[0066] S102, obtaining test data of the transformer test station for the target transformer, where 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 during operation;

[0067] S104, performing test anomaly detection on the transformer test station according to the test data to obtain an anomaly detection result, where the anomaly detection result includes the type of anomaly situation, duration, and degree of anomaly;

[0068] S106, evaluating the test safety of the transformer test station according to the anomaly detection result to obtain a safety evaluation result;

[0069] S108, judging the optimization space and optimization direction of the test parameters of the transformer test station based on the safety evaluation result;

[0070] S110, introducing a genetic algorithm, and performing collaborative test optimal parameter search with the genetic algorithm and the optimization space and optimization direction to obtain the optimal safety test parameters of the transformer test station.

[0071] It should be noted that by obtaining the test data of the transformer test station for the target transformer to perform test anomaly detection on the transformer test station, abnormal situations in the test can be discovered in time, such as parameter anomalies, temperature anomalies, etc., so as to take measures in time to avoid potential safety risks and ensure the safe and stable progress of the test process; evaluating the test safety of the transformer test station according to the anomaly detection result to understand the safety risks existing in the test process helps the operation personnel to discover abnormal situations in the test process in time, take corresponding measures, and avoid equipment damage or safety accidents caused by abnormal situations; determining the optimization space and optimization direction of the test parameters through the safety evaluation result, and introducing a genetic algorithm for collaborative test optimal parameter search can efficiently find the optimal test parameter combination to improve the test efficiency and safety. The genetic algorithm optimization can search for the optimal solution in a complex parameter space, provide a more reasonable test parameter setting for the transformer test station, and thus improve the test effect and reliability.

[0072] According to an embodiment of the present invention, the obtaining of the test data of the transformer test station for the target transformer, where 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 during operation, specifically is:

[0073] Obtain the test parameter change data of the transformer test station during the test of the target transformer through the industrial control computer of the transformer test station. The test parameters include the output voltage, current, power parameters, output power supply frequency parameters, top and bottom oil temperature data, vibration and noise data of the transformer test station;

[0074] Obtain the operating voltage, current, power parameters, input power supply frequency parameters and power factor of the target transformer during the test through sensors, and obtain the electrical parameter data of the target transformer.

[0075] It should be noted that the sensors include voltage, current sensors, frequency sensors, and digital meters.

[0076] According to the embodiments of the present invention, perform test anomaly detection on the transformer test station based on the test data to obtain an anomaly detection result. The anomaly detection result includes the type of anomaly situation, duration, and degree of anomaly. Specifically:

[0077] Perform time series alignment operation on the test data, and perform data cleaning on the test data after the alignment operation. The data cleaning includes data normalization to obtain standardized test data;

[0078] Introduce the box plot anomaly detection method, calculate the first quartile, second quartile, and third quartile of each test parameter data index in the standardized test data to obtain quartile data;

[0079] Draw box plots of each test parameter data index according to the quartile data to obtain a box plot set;

[0080] Calculate the distance between each quartile according to the quartile data and the box plot set to obtain the interquartile range. Determine the upper and lower limits of the anomaly values of each test parameter data index according to the interquartile range;

[0081] Check each test parameter data index to identify whether there are data points exceeding the upper and lower limits of the anomaly values, and mark the data points exceeding the upper and lower limits of the anomaly values as anomaly values to obtain anomaly value data;

[0082] Determine the test parameter data index with anomaly values according to the anomaly value data, and determine the type of anomaly situation according to the test parameter data index with anomaly values;

[0083] Determine the time when the anomaly value exceeds the upper and lower limits of the anomaly value according to the anomaly value data and the standardized test data to obtain the duration of the anomaly situation type;

[0084] Determine the distances between the outliers and the upper and lower limits of the upper and lower limits of each test parameter data index according to the outlier data, determine the degree of abnormality according to the distances, and obtain an anomaly detection result, where the anomaly detection result includes the type of anomaly situation, the duration of the anomaly situation type, and the degree of abnormality.

[0085] It should be noted that during the process of the transformer test station testing the target transformer, the test data often remains stable. If there are data fluctuations and the data fluctuations are within a certain range, it is also normal; by introducing the box plot anomaly detection method to draw a box plot, the box plot can intuitively display the data distribution. By drawing the box plot of each test parameter data index, the existence of outliers can be clearly identified. Outliers are usually defined as data points outside the upper and lower limits of the box plot; according to the appearance of outliers and the outlier data index, the type of anomaly situation can be determined. For example, if the outliers are concentrated on a certain or certain specific parameter data index, the corresponding anomaly situation type can be inferred; by calculating the timestamp and duration of the outlier data, the duration of the anomaly situation can be estimated, which helps to evaluate the impact of the anomaly situation on the test process and the urgency of taking countermeasures; in the quartile data, the first quartile (Q1): divides the data into four equal parts, and the position of the first equal part is Q1, the second quartile (Q2, that is, the median): divides the data into two equal parts, and the data at the middle position is Q2, and the third quartile (Q3): divides the data into four equal parts, and the position of the third equal part is Q3; the box in the box plot represents the interquartile range of the data, 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 outliers; each test parameter data index is each data parameter in each test data.

[0086] Figure 2 The flowchart showing the safety evaluation result obtained by the present invention is shown.

[0087] According to an embodiment of the present invention, the test safety of the transformer test station is evaluated according to the anomaly detection result to obtain a safety evaluation result, specifically:

[0088] S202, classify the anomaly detection results according to the type of anomaly situation, define the safety index for evaluating the test, where the safety index includes the number of anomalies, the length of the abnormal time series, and the degree of abnormality value, and define the influence degree of each anomaly situation type on the test safety to obtain influence weight information;

[0089] S204, calculate the value of each test safety index according to the anomaly detection result and the influence weight information to obtain a calculation result;

[0090] S206, summarize the calculation results through weighted summation to obtain the test safety evaluation value;

[0091] S208, generate safety evaluation results with different safety prompt levels according to the safety evaluation value. The safety evaluation results include abnormal detection situations, classifications and weights of abnormal situations, calculation results of various safety evaluation indicators, and comprehensive conclusions of safety evaluations.

[0092] It should be noted that classifying the abnormal detection results according to the types of abnormal situations helps to more clearly understand the nature and occurrence frequency of abnormal situations; according to the different types of abnormal situations, determine the degree of influence of each abnormal situation on the test safety, that is, the influence weight. The weight information reflects the importance and urgency of different abnormal situations, which helps to prioritize the handling of abnormal situations with greater influence; perform weighted summation on the calculation results of various safety indicators to obtain the test safety evaluation value, comprehensively considering the importance and influence degree of each indicator, providing a comprehensive reference for the overall safety evaluation, and realizing a comprehensive evaluation of the test safety of the transformer test station.

[0093] Figure 3 The flowchart shows the optimization space and optimization direction of the test parameters of the transformer test station in the present invention.

[0094] According to the embodiment of the present invention, judging the optimization space and optimization direction of the test parameters of the transformer test station based on the safety evaluation results is specifically as follows:

[0095] S302, sort the impacts of each abnormal situation type on the test safety from large to small according to the safety evaluation results to obtain a safety impact list;

[0096] S304, judge the optimization space and optimization direction of each abnormal situation type according to the safety impact list and the abnormal degree of each abnormal situation type.

[0097] It should be noted that by sorting and analyzing the impacts of abnormal situation types, the problems and risks existing in the test process can be accurately located, and targeted optimizations can be carried out. According to the priority and abnormal degree of abnormal situation types, 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.

[0098] According to the embodiment of the present invention, introduce the genetic algorithm, and perform collaborative test optimization parameter search on the genetic algorithm with the optimization space and optimization direction to obtain the preferred safety test parameters of the transformer test station, specifically as follows:

[0099] Introduce a genetic algorithm to determine the optimization objective of the test parameters. Randomly generate a group of initial individuals as a population according to the optimization space and optimization direction. Use the influence weight information as the optimization evaluation criterion, and define a fitness function according to the optimization objective and the optimization evaluation criterion;

[0100] Calculate the fitness of each initial individual in the population based on the influence weight information according to the fitness function, and select a preset number of excellent individuals as the parents of the next generation according to the fitness;

[0101] Perform a crossover operation on the parent individuals to generate new offspring individuals, perform a mutation operation on the offspring individuals after the crossover operation, combine the parent individuals and the mutated offspring individuals to generate the next generation population, and continue the crossover and mutation operations on the next generation population until the optimization objective is reached;

[0102] When the optimization objective is reached, select the optimal individual by evaluating the fitness of the population that reaches the optimization objective, and use the test parameter combination corresponding to the optimal individual as the preferred safety test parameter of the transformer test station.

[0103] It should be noted that, through the genetic algorithm and according to the optimization space and optimization direction, a group of initial individuals are randomly generated as a population. These individuals represent different test parameter combinations, providing a starting point for the search of the genetic algorithm. According to the influence weight information, a fitness function is defined to evaluate the quality of each individual. The fitness function can comprehensively consider factors such as the type of abnormal situation, the duration of the abnormality, and the degree of the abnormality, ensuring that the selected test parameter combination can improve the test safety as much as possible; through operations such as selection, crossover, and mutation of the genetic algorithm, the population is continuously iterated, enabling the population to gradually evolve towards more excellent individuals, and better test parameter combinations can be searched in the parameter space to meet the optimization objective; by introducing the genetic algorithm to optimize the test parameters, the optimal test parameter combination can be effectively searched, improving the safety and efficiency of the test station, and reducing the occurrence and impact of abnormal situations during the test process; the group of initial individuals contains multiple individuals, each initial individual represents a combination of a group of test parameters, and the generated test parameter combinations are within the optimization space.

[0104] According to an embodiment of the present invention, it further includes:

[0105] Implement the preferred safety test parameters, and perform secondary anomaly detection on the transformer test station after implementation to obtain the secondary anomaly detection result;

[0106] Compare the secondary anomaly detection result with the anomaly detection result to determine whether the types of abnormal situations in the anomaly detection result still exist in the secondary anomaly detection result. If so, mark the type of abnormal situation to obtain the marked type of abnormal situation;

[0107] Obtain the secondary anomaly degree that marks the type of anomaly situation according to the secondary anomaly detection result. If the secondary anomaly degree does not decrease compared to the anomaly degree in the anomaly detection result, mark the transformer test station as a faulty state.

[0108] Determine the fault type according to the marked anomaly situation type, and perform maintenance operations on the transformer test station according to the fault type.

[0109] It should be noted that after implementing the optimal safety test parameters for the transformer test station, perform secondary anomaly detection on the transformer test station to obtain the secondary anomaly detection result. If the type of anomaly situation in the secondary anomaly detection result still appears during the test process of the transformer test station, it can be determined that the transformer test station has a faulty state and cannot optimize the test by adjusting the test parameters. Therefore, maintenance operations should be performed on the transformer test station at this time, which can diagnose and handle the faults of the transformer test station in a timely and accurate manner, and ensure the safe operation and stability of the transformer test station.

[0110] Figure 4 The block diagram of a test safety monitoring system for a transformer test station according to the present invention is shown.

[0111] The second aspect of the present invention also provides a test safety monitoring system 4 for a transformer test station. The system includes: a memory 41 and a processor 42. The memory includes a test safety monitoring method program for the transformer test station. When the test safety monitoring method program for the transformer test station is executed by the processor, the following steps are implemented:

[0112] Obtain the test data of the transformer test station for the target transformer. 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 during operation.

[0113] Perform test anomaly detection on the transformer test station according to the test data to obtain an anomaly detection result. The anomaly detection result includes the type of anomaly situation, the duration, and the anomaly degree.

[0114] Evaluate the test safety of the transformer test station according to the anomaly detection result to obtain a safety evaluation result.

[0115] Based on the safety evaluation result, judge the optimization space and optimization direction of the test parameters of the transformer test station.

[0116] Introduce a genetic algorithm, and perform collaborative test optimization parameter search on the genetic algorithm with the optimization space and optimization direction to obtain the optimal safety test parameters of the transformer test station.

[0117] It should be noted that by obtaining the test data of the target transformer from the transformer test station for test anomaly detection of the transformer test station, abnormal situations in the test can be detected in a timely manner, such as abnormal parameters, abnormal temperature, etc., so as to take measures in a timely manner to avoid potential safety risks and ensure the safe and stable progress of the test process; evaluate the test safety of the transformer test station according to the anomaly detection results, understand the safety risks existing in the test process to help the operation personnel detect abnormal situations in the test process in a timely manner, and take corresponding measures to avoid equipment damage or safety accidents caused by abnormal situations; determine the optimization space and optimization direction of the test parameters according to the safety evaluation results, and introduce a genetic algorithm to search for optimal test parameters collaboratively, which can efficiently find the optimal combination of test parameters to improve the test efficiency and safety. The genetic algorithm optimization can search for the optimal solution in a complex parameter space, provide more reasonable test parameter settings for the transformer test station, and thus improve the test effect and reliability.

[0118] According to an embodiment of the present invention, for the acquisition of the test data of the target transformer from the transformer test station, 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 during operation, specifically:

[0119] Obtain the test parameter change data of the transformer test station during the test of the target transformer through the industrial control computer of the transformer test station, and the test parameters include the output voltage, current, power parameters, output power supply frequency parameters, top and bottom oil temperature data, vibration and noise data of the transformer test station;

[0120] Obtain the electrical parameter data of the target transformer by using sensors to acquire the operating voltage, current, power parameters, input power supply frequency parameters and power factor of the target transformer during the test.

[0121] It should be noted that the sensors include voltage sensors, current sensors, frequency sensors, and digital electric meters.

[0122] According to an embodiment of the present invention, for the test anomaly detection of the transformer test station based on the test data to obtain an anomaly detection result, the anomaly detection result includes the type of abnormal situation, the duration, and the degree of abnormality, specifically:

[0123] Perform a time series alignment operation on the test data, and perform data cleaning on the test data after the alignment operation. The data cleaning includes data normalization to obtain standardized test data;

[0124] Introduce a box plot anomaly detection method, calculate the first quartile, second quartile, and third quartile of each test parameter data index in the standardized test data to obtain quartile data;

[0125] Draw a box plot of each test parameter data index based on the quartile data to obtain a box plot set;

[0126] Calculate the distance between each quartile according to the quartile data and the box plot set to obtain the interquartile range, and determine the upper and lower limits of outliers for each test parameter data index according to the interquartile range;

[0127] Check each test parameter data index to identify whether there are data points exceeding the upper and lower limits of outliers, and mark the data points exceeding the upper and lower limits of outliers as outliers to obtain outlier data;

[0128] Determine the test parameter data index with outliers according to the outlier data, and determine the type of abnormal situation according to the test parameter data index with outliers;

[0129] Determine the time when the outliers exceed the upper and lower limits of outliers according to the outlier data and the standardized test data to obtain the duration of the abnormal situation type;

[0130] Determine the distance between the outliers and the upper and lower limits of outliers in each test parameter data index according to the outlier data, and determine the degree of abnormality according to the distance to obtain the abnormal detection result, where the abnormal detection result includes the type of abnormal situation, the duration of the abnormal situation type, and the degree of abnormality.

[0131] It should be noted that during the process of the transformer test station testing the target transformer, the test data often remains stable. If there are fluctuations in the data and the fluctuations are within a certain range, it is also normal. By introducing the box plot anomaly detection method to draw the box plot, the box plot can intuitively display the data distribution. By drawing the box plot of each test parameter data index, the existence of outliers can be clearly identified. Outliers are usually defined as the data points outside the upper and lower limits of the outliers in the box plot. According to the appearance of the outliers and the outlier data index, the type of the abnormal situation can be determined. For example, if the outliers are concentrated on a certain or certain specific parameter data index, the corresponding abnormal situation type can be inferred. By calculating the timestamp and duration of the outlier data, the duration of the abnormal situation can be estimated, which helps to evaluate the impact of the abnormal situation on the test process and the urgency of taking countermeasures. The first quartile (Q1) in the quartile data: The data is divided into four equal parts, and the position of the first equal part is Q1. The second quartile (Q2, that is, the median): The data is divided into two equal parts, and the data at the middle position is Q2. The third quartile (Q3): The data is divided into four equal parts, and the position of the third equal part is Q3. The box in the box plot represents the interquartile range of the data, 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 outliers. Each test parameter data index is each data parameter in each test data.

[0132] According to an embodiment of the present invention, evaluating the test safety of the transformer test station according to the anomaly detection result to obtain a safety evaluation result, specifically:

[0133] Classify the anomaly detection results according to the type of abnormal situation, define the safety evaluation index for the test, the safety index includes the number of anomalies, the abnormal time series length, and the degree of abnormality value, and define the influence degree of each abnormal situation type on the test safety to obtain the influence weight information;

[0134] Calculate the value of each test safety index according to the anomaly detection result and the influence weight information to obtain a calculation result;

[0135] Summarize the calculation results by weighted summation to obtain the test safety evaluation value;

[0136] Generate a safety evaluation result with different safety prompt levels according to the safety evaluation value. The safety evaluation result includes the anomaly detection situation, the classification and weight of the abnormal situation, the calculation results of each safety evaluation index, and the comprehensive conclusion of the safety evaluation.

[0137] It should be noted that classifying the anomaly detection results according to the types of anomalies helps to more clearly understand the nature and occurrence frequency of anomalies; according to the different types of anomalies, determine the degree of impact of each anomaly on the test safety, that is, the impact weight. The weight information reflects the importance and urgency of different anomalies, which helps to prioritize the handling of anomalies with greater impact; perform weighted summation on the calculation results of various safety indicators to obtain the test safety evaluation value, comprehensively considering the importance and impact degree of each indicator, providing a comprehensive reference for the overall safety evaluation, and realizing a comprehensive evaluation of the test safety of the transformer test station.

[0138] According to an embodiment of the present invention, based on the safety evaluation result, judging the optimization space and optimization direction of the test parameters of the transformer test station specifically includes:

[0139] Sort the impacts of each anomaly type on the test safety from large to small according to the safety evaluation result to obtain a safety impact list;

[0140] Judge the optimization space and optimization direction of each anomaly type according to the safety impact list and the anomaly degree of each anomaly type.

[0141] It should be noted that by sorting and analyzing the impacts of anomaly types, the problems and risks existing in the test process can be accurately located, and targeted optimizations can be carried out. According to the priority and anomaly degree of the anomaly types, the optimization space and optimization direction of each anomaly 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 anomaly type.

[0142] According to an embodiment of the present invention, introducing a genetic algorithm, and performing collaborative test optimization parameter search on the genetic algorithm with the optimization space and optimization direction to obtain the preferred safety test parameters of the transformer test station specifically includes:

[0143] Introduce a genetic algorithm, determine the optimization goal of the test parameters, randomly generate a group of initial individuals as a population according to the optimization space and optimization direction, use the impact weight information as the optimization evaluation criterion, and define a fitness function according to the optimization goal and the optimization evaluation criterion;

[0144] Calculate the fitness of each initial individual in the population based on the impact weight information according to the fitness function, and select a preset number of excellent individuals as the parents of the next generation according to the fitness;

[0145] Perform crossover operations on the parent individuals to generate new offspring individuals, perform mutation operations on the offspring individuals after the crossover operations, combine the parent individuals and the mutated offspring individuals to generate the next generation population, and continue the crossover and mutation operations on the next generation population until the optimization goal is reached;

[0146] When the optimization goal is reached, select the optimal individual by evaluating the fitness of the population that has reached the optimization goal, and use the combination of test parameters corresponding to the optimal individual as the preferred safety test parameters for the variable voltage test station.

[0147] It should be noted that, through the genetic algorithm and according to the optimization space and optimization direction, a group of initial individuals are randomly generated as the population. These individuals represent different combinations of test parameters, providing a starting point for the search of the genetic algorithm. According to the influence weight information, a fitness function is defined to evaluate the quality of each individual. The fitness function can comprehensively consider factors such as the type of abnormal situation, the duration of the abnormality, and the degree of the abnormality to ensure that the preferred combination of test parameters can improve the test safety as much as possible; through operations such as selection, crossover, and mutation of the genetic algorithm, the population is continuously iterated, enabling the population to gradually evolve towards more excellent individuals, and better combinations of test parameters can be searched in the parameter space to meet the optimization goal; by introducing the genetic algorithm to optimize the test parameters, the optimal combination of test parameters can be effectively searched, improving the safety and efficiency of the test station and reducing the occurrence and impact of abnormal situations during the test; the group of initial individuals contains multiple individuals, each initial individual represents a combination of a set of test parameters, and the generated combinations of test parameters are within the optimization space.

[0148] The present invention discloses a method and system for monitoring the test safety of a transformer test station. The present invention first obtains the test data of the transformer test station. Through anomaly detection of the test data, an anomaly detection result is obtained. Subsequently, the test safety is evaluated to obtain a safety evaluation result. According to the evaluation result, the optimization space and optimization direction of the test parameters are determined. Further, a genetic algorithm is introduced to perform collaborative search with the optimization space and direction to obtain preferred test parameters, so as to improve the safety and stability of the transformer test station. The present invention can effectively monitor the test safety, improve the ability to optimize the test parameters, and has broad application prospects and economic value.

[0149] In several embodiments provided by 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 merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, 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 with each other can be through some interfaces. The indirect coupling or communication connection of the devices or units can be electrical, mechanical, or other forms.

[0150] The units described above as separate components may or may not be physically separated. The components shown as units may or may not be physical units; they can be located in one place or distributed to multiple network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0151] In addition, each functional unit in the embodiments of the present invention can be all integrated in a processing unit, or each unit can be separately used as a unit, or two or more units can be integrated in one unit; the above-mentioned integrated units can be implemented in the form of hardware, or in the form of hardware plus software functional units.

[0152] Those of ordinary skill in the art can understand that all or part of the steps for implementing the above method embodiments can be completed by hardware related to program instructions. The foregoing program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps including the above method embodiments; and the foregoing storage medium includes: removable storage devices, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disks or optical disks and other various media that can store program codes.

[0153] Alternatively, if the above-mentioned integrated units of the present invention are implemented in the form of software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the embodiments of the present invention essentially or the part that contributes to the prior art can be embodied in the form of a software product. 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 invention. And the foregoing storage medium includes: removable storage devices, ROM, RAM, magnetic disks or optical disks and other various media that can store program codes.

[0154] As described above, it is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claimed rights.

Claims

1. A test safety monitoring method for a transformer test station, characterized in that: The following steps are involved: Acquire test data of a target transformer from a transformer test station, wherein 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 operation; Perform test anomaly detection on the transformer test station according to the test data to obtain anomaly detection results, wherein the anomaly detection results include the type, duration, and degree of anomaly; Evaluate the test safety of the transformer test station according to the abnormality detection result to obtain a safety evaluation result; Determine the optimization space and optimization direction of the transformer test station test parameters based on the safety assessment results; Introducing a genetic algorithm, and using the genetic algorithm in conjunction with the optimization space and optimization direction to search for optimal test parameters, thereby obtaining optimal safety test parameters for a transformer test station; The test abnormality detection is performed on the transformer test station according to the test data to obtain an abnormality detection result, wherein the abnormality detection result includes the type, duration and degree of abnormality of the abnormal situation, specifically: Performing a time series alignment operation on the test data, and performing data cleaning on the test data after the alignment operation, wherein the data cleaning includes data normalization to obtain standardized test data; The box plot anomaly detection method is introduced to calculate the first quartile, second quartile, and third quartile of each test parameter data indicator in the standardized test data to obtain quartile data; Draw a box plot of each test parameter data indicator according to the quartile data to obtain a box plot set; Calculate the distance between each quartile according to the quartile data and the box plot set to obtain the interquartile range, and determine the upper and lower limits of the abnormal value of each test parameter data indicator according to the interquartile range; Check each test parameter data indicator to identify whether there are data points that exceed the upper and lower limits of the outlier value, mark the data points that exceed the upper and lower limits of the outlier value as outliers, and obtain outlier data; Determine the test parameter data index where the abnormal value occurs according to the abnormal value data, and determine the type of abnormal situation according to the test parameter data index where the abnormal value occurs; Determine the time when the abnormal value exceeds the upper and lower limits of the abnormal value according to the abnormal value data and the standardized test data, and obtain the duration of the abnormal situation type; The distance between the abnormal value and the upper and lower limits of the abnormal value in each test parameter data indicator is determined according to the abnormal value data, and the degree of abnormality is determined according to the distance to obtain an abnormality detection result, which includes the type of abnormal situation, the duration of the abnormal situation type, and the degree of abnormality.

2. A test safety monitoring method for a transformer test station according to claim 1, characterized in that: The test data of the target transformer on the transformer test station is obtained, 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 operation, specifically: Acquire test parameter change data of the transformer test station during the test of the target transformer through the industrial control computer of the transformer test station, wherein the test parameters include output voltage, current, power parameters, and output power frequency parameters of the transformer test station; The operating voltage, current, power parameters, input power frequency parameters and power factor of the target transformer during the test are obtained through sensors to obtain the electrical parameter data of the target transformer.

3. The test safety monitoring method of a transformer test station according to claim 1 is characterized in that: The test safety of the transformer test station is evaluated according to the abnormal detection result to obtain a safety evaluation result, which is specifically: Classify the abnormality detection results according to the abnormality type, define the safety index of the evaluation test, the safety index includes the number of abnormalities, the length of the abnormal time series, the abnormality degree value, and define the impact of each abnormality type on the safety of the test to obtain the impact weight information; Calculate the value of each test safety index according to the abnormal detection result and the impact weight information to obtain the calculation result; The calculation results are summarized by weighted summation to obtain a test safety assessment value; The safety assessment results of different safety warning levels are generated according to the safety assessment value, and the safety assessment results include abnormal detection conditions, classification and weight of abnormal conditions, calculation results of various safety assessment indicators, and comprehensive conclusions of the safety assessment.

4. The test safety monitoring method of a transformer test station according to claim 1 is characterized in that: The optimization space and optimization direction of the transformer test station test parameters are determined based on the safety assessment results, specifically: According to the safety assessment results, the impact of each abnormal situation type on the test safety is sorted from large to small to obtain a safety impact list; The optimization space and optimization direction of each abnormal situation type are determined according to the safety impact list and the abnormality degree of each abnormal situation type.

5. The test safety monitoring method of a transformer test station according to claim 3 is characterized in that: The genetic algorithm is introduced to perform collaborative test optimization parameter search with the optimization space and optimization direction to obtain the optimal safety test parameters of the transformer test station, which are specifically: Introducing a genetic algorithm, determining an optimization target for the test parameters, randomly generating a group of initial individuals as a population according to the optimization space and optimization direction, using the impact weight information as an optimization evaluation criterion, and defining a fitness function according to the optimization target and the optimization evaluation criterion; Calculating the 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; Perform crossover operation on parent individuals to generate new offspring individuals, perform mutation operation on offspring individuals after crossover operation, combine parent individuals and mutated offspring individuals to generate next generation population, and continue crossover and mutation operation on next generation population until the optimization goal is achieved; When the optimization target is reached, the best individual is selected by evaluating the fitness of the population that has achieved the optimization target, and the test parameter combination corresponding to the best individual is used as the preferred safety test parameter of the transformer test station.

6. A test safety monitoring system for a transformer test station, characterized in that: The test safety monitoring system of the transformer test station includes a storage and a processor, wherein the storage includes a test safety monitoring method program of the transformer test station, and when the test safety monitoring method program of the transformer test station is executed by the processor, the following steps are implemented: Acquire test data of a target transformer from a transformer test station, wherein 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 operation; Perform test anomaly detection on the transformer test station according to the test data to obtain anomaly detection results, wherein the anomaly detection results include the type, duration, and degree of anomaly; Evaluate the test safety of the transformer test station according to the abnormality detection result to obtain a safety evaluation result; Determine the optimization space and optimization direction of the transformer test station test parameters based on the safety assessment results; Introducing a genetic algorithm, and using the genetic algorithm in conjunction with the optimization space and optimization direction to search for optimal test parameters, thereby obtaining optimal safety test parameters for a transformer test station; The test abnormality detection is performed on the transformer test station according to the test data to obtain an abnormality detection result, wherein the abnormality detection result includes the type, duration and degree of abnormality of the abnormal situation, specifically: Performing a time series alignment operation on the test data, and performing data cleaning on the test data after the alignment operation, wherein the data cleaning includes data normalization to obtain standardized test data; The box plot anomaly detection method is introduced to calculate the first quartile, second quartile, and third quartile of each test parameter data indicator in the standardized test data to obtain quartile data; Draw a box plot of each test parameter data indicator according to the quartile data to obtain a box plot set; Calculate the distance between each quartile according to the quartile data and the box plot set to obtain the interquartile range, and determine the upper and lower limits of the abnormal value of each test parameter data indicator according to the interquartile range; Check each test parameter data indicator to identify whether there are data points that exceed the upper and lower limits of the outlier value, mark the data points that exceed the upper and lower limits of the outlier value as outliers, and obtain outlier data; Determine the test parameter data index where the abnormal value occurs according to the abnormal value data, and determine the type of abnormal situation according to the test parameter data index where the abnormal value occurs; Determine the time when the abnormal value exceeds the upper and lower limits of the abnormal value according to the abnormal value data and the standardized test data, and obtain the duration of the abnormal situation type; The distance between the abnormal value and the upper and lower limits of the abnormal value in each test parameter data indicator is determined according to the abnormal value data, and the degree of abnormality is determined according to the distance to obtain an abnormality detection result, which includes the type of abnormal situation, the duration of the abnormal situation type, and the degree of abnormality.

7. A test safety monitoring system for a transformer test station according to claim 6, characterized in that: The test safety of the transformer test station is evaluated according to the abnormal detection result to obtain a safety evaluation result, which is specifically: Classify the abnormality detection results according to the abnormality type, define the safety index of the evaluation test, the safety index includes the number of abnormalities, the length of the abnormal time series, the abnormality degree value, and define the impact of each abnormality type on the safety of the test to obtain the impact weight information; Calculate the value of each test safety index according to the abnormal detection result and the impact weight information to obtain the calculation result; The calculation results are summarized by weighted summation to obtain a test safety assessment value; The safety assessment results of different safety warning levels are generated according to the safety assessment value, and the safety assessment results include abnormal detection conditions, classification and weight of abnormal conditions, calculation results of various safety assessment indicators, and comprehensive conclusions of the safety assessment.

8. The test safety monitoring system for a transformer test station according to claim 6, characterized in that: The optimization space and optimization direction of the transformer test station test parameters are determined based on the safety assessment results, specifically: According to the safety assessment results, the impact of each abnormal situation type on the test safety is sorted from large to small to obtain a safety impact list; The optimization space and optimization direction of each abnormal situation type are determined according to the safety impact list and the abnormality degree of each abnormal situation type.

9. A test safety monitoring system for a transformer test station according to claim 6, characterized in that: The genetic algorithm is introduced to perform collaborative test optimization parameter search with the optimization space and optimization direction to obtain the optimal safety test parameters of the transformer test station, which are specifically: Introducing a genetic algorithm, determining an optimization target for the test parameters, randomly generating a group of initial individuals as a population according to the optimization space and optimization direction, using the impact weight information as an optimization evaluation criterion, and defining a fitness function according to the optimization target and the optimization evaluation criterion; Calculating the 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; Perform crossover operation on parent individuals to generate new offspring individuals, perform mutation operation on offspring individuals after crossover operation, combine parent individuals and mutated offspring individuals to generate next generation population, and continue crossover and mutation operation on next generation population until the optimization goal is achieved; When the optimization target is reached, the best individual is selected by evaluating the fitness of the population that has achieved the optimization target, and the test parameter combination corresponding to the best individual is used as the preferred safety test parameter of the transformer test station.

Images