High-power high-voltage variable-frequency power supply capacity testing method and system using power grid as load

Abstract

The present invention discloses a method and system for testing the capacity of a high-power, high-voltage, variable-frequency power supply with a power grid as a load, including: obtaining the capacity test process information of the high-power, high-voltage, variable-frequency power supply, dividing the capacity test process into multiple test sub-processes; analyzing the optimal test parameters of each test sub-process, and forming a capacity test knowledge map; obtaining the specification information of the target high-power, high-voltage, variable-frequency power supply, formulating a capacity test plan for capacity testing; obtaining historical use examples of high-power, high-voltage, variable-frequency power supplies of different specifications, analyzing the load changes in actual use according to the historical use examples, and constructing a dynamic response test knowledge map; performing load change simulation based on the dynamic response test knowledge map, and performing performance evaluation according to the load change simulation results. The active load scenario of the high-voltage variable-frequency power supply is simulated with the power grid load, and its capacity and performance are accurately evaluated, thereby improving the accuracy and reliability of the power supply capacity test.

Description

Technical Field

[0001] The present invention relates to the technical field of high-voltage variable-frequency power supply capacity testing, and in particular to a high-power high-voltage variable-frequency power supply capacity testing method and system using a power grid as a load. Background Art

[0002] With the continuous development of power technology and the increasing complexity of power systems, high-power high-voltage variable-frequency power supplies, as one of the key equipment in power systems, are crucial to ensuring the safe and stable operation of the entire power grid. High-power high-voltage variable-frequency power supplies are not only widely used in industrial, commercial and civil fields, but also play an indispensable role in energy, transportation, communications and other fields.

[0003] In the traditional high-power high-voltage variable frequency power supply capacity test method, the static test method is usually used. Although the static test method is simple and easy, it cannot truly reflect the performance of the power supply under the actual working conditions of the power grid. Therefore, how to simulate the real power grid load environment and accurately evaluate its capacity and performance during the test of high-power high-voltage variable frequency power supply has become an urgent problem to be solved in the current power technology field. Summary of the invention

[0004] The present invention overcomes the defects of the prior art and provides a method and system for testing the capacity of a high-power high-voltage variable-frequency power supply with a power grid as a load, the important purpose of which is to improve the accuracy and reliability of the capacity test of the high-power high-voltage variable-frequency power supply.

[0005] To achieve the above-mentioned purpose, the first aspect of the present invention provides a method for testing the capacity of a high-power high-voltage variable-frequency power supply with a power grid as a load, comprising:

[0006] Acquire capacity test process information of a high-power high-voltage variable-frequency power supply, extract test process features according to the capacity test process information, and divide the capacity test process into multiple test sub-processes;

[0007] Using big data methods to obtain historical capacity test instances of high-power and high-voltage variable-frequency power supplies of different specifications, analyzing the optimal test parameters of each test sub-process based on the historical capacity test instances, and forming a capacity test knowledge graph;

[0008] Obtain specification information of the target high-power high-voltage variable-frequency power supply, formulate a capacity test plan in combination with the capacity test knowledge graph, and perform a capacity test on the target high-power high-voltage variable-frequency power supply;

[0009] Obtain historical usage examples of high-power and high-voltage variable-frequency power supplies of different specifications, analyze load changes in actual use according to the historical usage examples, and build a dynamic response test knowledge graph based on the analysis results;

[0010] Based on the dynamic response test knowledge graph, load change simulation is performed on the target high-power high-voltage variable-frequency power supply, and performance evaluation is performed according to the load change simulation results.

[0011] In this solution, the test process feature extraction is performed according to the capacity test process information, and the capacity test process is divided into multiple test sub-processes, specifically including:

[0012] Acquire capacity test process information of a high-power high-voltage variable-frequency power supply, perform feature extraction on the capacity test process information, and obtain capacity test process feature information;

[0013] Based on the capacity test process feature information, de-redundancy operations are performed on each capacity test process feature to generate a number of initial capacity test sub-processes, and test operation features corresponding to each initial capacity test sub-process are respectively extracted;

[0014] The Euclidean distance between the test operation characteristics of the initial capacity test sub-process is calculated, and the initial capacity test sub-process is clustered in combination with the K-means clustering algorithm. Several capacity test sub-processes are generated according to the clustering results.

[0015] In this solution, the big data method is used to obtain historical capacity test instances of high-power and high-voltage variable-frequency power supplies of different specifications, and the optimal test parameters of each test sub-process are analyzed based on the historical capacity test instances, and a capacity test knowledge graph is formed, which specifically includes:

[0016] The historical capacity test instances of high-power and high-voltage variable-frequency power supplies of different specifications are obtained by using big data methods, and the test parameter characteristics and corresponding test process characteristics of each historical capacity test instance are extracted to obtain the characteristic information of the historical capacity test instance;

[0017] Based on the divided capacity test sub-processes, the test parameter characteristics of each historical capacity test instance are divided into corresponding capacity test sub-processes in combination with the historical capacity test instance characteristic information;

[0018] According to the variable frequency power supply specification attributes corresponding to the test parameter characteristics under each capacity test sub-process, the test parameters under each capacity test sub-process are classified according to the corresponding variable frequency power supply specifications to obtain the classification result information;

[0019] According to the classification result information, the April algorithm is used to analyze the optimal test parameters corresponding to each capacity test sub-process, and a frequent item set is generated through the historical test parameters corresponding to each test sub-process;

[0020] Based on the generated frequent item sets, association rules are formed, the support, confidence and lift corresponding to each frequent item set under each association rule are calculated, and each frequent item set is sorted. According to the sorting results, the best test parameters of different power specifications in each capacity test sub-process are selected to obtain the best test parameter information;

[0021] The category division result information and the optimal test parameter information are combined to form an entity triplet of power supply specification, capacity test process and optimal test parameter, and a capacity test knowledge graph is constructed based on the entity triplet.

[0022] In this solution, the target high-power high-voltage variable-frequency power supply specification information is obtained, a capacity test plan is formulated in combination with the capacity test knowledge graph, and a capacity test is performed on the target high-power high-voltage variable-frequency power supply, specifically including:

[0023] Obtaining specification information of the target high-power high-voltage variable-frequency power supply, extracting specification features of the target high-power high-voltage variable-frequency power supply, obtaining optimal test parameters in combination with the capacity test knowledge graph, and formulating a capacity test plan;

[0024] Connect the target high-power high-voltage variable-frequency power supply to the power grid, set the initial parameters of the power grid based on the formulated capacity test plan, and control the target high-power high-voltage variable-frequency power supply to perform electrical synchronization with the power grid;

[0025] After the electrical synchronization operation, the grid connection operation is performed to connect the target high-power high-voltage variable-frequency power supply to the target power grid, and the power grid is used as a load to perform a capacity test on the target high-power high-voltage variable-frequency power supply;

[0026] Acquire the capacity test monitoring information of the target high-power high-voltage variable-frequency power supply, and calculate the capacity test power of the target high-power high-voltage variable-frequency power supply according to the capacity test monitoring information;

[0027] Obtain the rated power of the target high-power high-voltage variable-frequency power supply, calculate the deviation from the capacity test power, compare the calculated deviation value with the preset threshold, and analyze whether the rated power of the target high-power high-voltage variable-frequency power supply is true.

[0028] In this solution, the historical usage examples of high-power and high-voltage variable-frequency power supplies of different specifications are obtained, the load changes in actual use are analyzed according to the historical usage examples, and a dynamic response test knowledge graph is constructed based on the analysis results, which specifically includes:

[0029] Based on historical data retrieval, historical usage instances of high-power and high-voltage variable-frequency power supplies of different specifications are obtained, and load current characteristics and operating time characteristics of each historical usage instance are extracted to obtain characteristic information of the historical usage instance;

[0030] The isolation forest algorithm is introduced to detect anomalies in the load current characteristics of each historical usage instance. The load current feature detection information is obtained by constructing a random binary search tree to detect low-density or isolated data in the feature space.

[0031] Obtaining a load current operation benchmark, calculating a deviation between the load current feature detection information and the operation benchmark, and classifying corresponding load current features according to the calculated deviation to obtain first analysis information;

[0032] constructing a load current change curve corresponding to the historical usage instance according to the historical usage instance characteristic information, and marking the abnormal load current in combination with the first analysis information;

[0033] According to the load current change curve corresponding to each historical usage instance, the marked abnormal load current level and frequency are obtained, and the load change mode of each historical usage instance is classified into three categories: stable load, sudden load and fluctuating load, to obtain first classification information;

[0034] Setting evaluation indicators and evaluation weights, performing dynamic response evaluation on each historical usage instance in combination with the first classification information, evaluating the dynamic response status under different load types, and obtaining dynamic response status information;

[0035] A dynamic response test knowledge graph is constructed based on the dynamic response status information, and the operating parameters of the corresponding historical instances are used as test parameters.

[0036] In this solution, the load change simulation of the target high-power high-voltage variable-frequency power supply is performed based on the dynamic response test knowledge graph, and the performance evaluation is performed according to the load change simulation results, specifically including:

[0037] Acquire test requirement information, formulate a load change simulation plan in combination with the dynamic response knowledge graph, select a load change mode based on the test requirement and define simulation conditions to obtain load simulation plan information;

[0038] Based on the load simulation scheme information, load change simulation is performed on the target high-power high-voltage variable-frequency power supply, load simulation monitoring information is obtained, and data preprocessing is performed on the load simulation monitoring information;

[0039] Constructing a time step, combining the preprocessed load simulation monitoring information with the time step to obtain the load simulation monitoring information based on the time step, introducing a Markov algorithm to perform a state transition probability analysis on the load simulation monitoring information based on the time step, and obtaining a state transition probability value for each preset time step;

[0040] Inputting the state transition probability value of each preset time step into the Bayesian network for training and obtaining training results, obtaining an abnormal factor for load simulation test based on the training results, and generating load simulation anomaly detection information;

[0041] Perform response characteristic analysis based on the load simulation monitoring information, calculate the response characteristic index of the target high-power high-voltage variable-frequency power supply under different load change conditions, and perform performance evaluation in combination with the load simulation abnormality detection information to obtain performance evaluation information;

[0042] A load simulation test report is generated based on the performance evaluation information and the load simulation anomaly detection information.

[0043] A second aspect of the present invention provides a high-power high-voltage variable-frequency power supply capacity test system with a power grid as a load, the system comprising: a memory, a processor, the memory containing a high-power high-voltage variable-frequency power supply capacity test method program with a power grid as a load, the high-power high-voltage variable-frequency power supply capacity test method program with a power grid as a load when executed by the processor implements the following steps:

[0044] Acquire capacity test process information of a high-power high-voltage variable-frequency power supply, extract test process features according to the capacity test process information, and divide the capacity test process into multiple test sub-processes;

[0045] Using big data methods to obtain historical capacity test instances of high-power and high-voltage variable-frequency power supplies of different specifications, analyzing the optimal test parameters of each test sub-process based on the historical capacity test instances, and forming a capacity test knowledge graph;

[0046] Obtain specification information of the target high-power high-voltage variable-frequency power supply, formulate a capacity test plan in combination with the capacity test knowledge graph, and perform a capacity test on the target high-power high-voltage variable-frequency power supply;

[0047] Obtain historical usage examples of high-power and high-voltage variable-frequency power supplies of different specifications, analyze load changes in actual use according to the historical usage examples, and build a dynamic response test knowledge graph based on the analysis results;

[0048] Based on the dynamic response test knowledge graph, load change simulation is performed on the target high-power high-voltage variable-frequency power supply, and performance evaluation is performed according to the load change simulation results.

[0049] The present invention discloses a method and system for testing the capacity of a high-power, high-voltage, variable-frequency power supply with a power grid as a load, including: obtaining the capacity test process information of the high-power, high-voltage, variable-frequency power supply, dividing the capacity test process into multiple test sub-processes; obtaining historical capacity test instances of high-power, high-voltage, variable-frequency power supplies of different specifications, analyzing the optimal test parameters of each test sub-process, and forming a capacity test knowledge map; obtaining target high-power, high-voltage, variable-frequency power supply specification information, formulating a capacity test plan for capacity testing; obtaining historical use instances of high-power, high-voltage, variable-frequency power supplies of different specifications, analyzing the load changes in actual use according to the historical use instances, and constructing a dynamic response test knowledge map; performing load change simulation based on the dynamic response test knowledge map, and performing performance evaluation according to the load change simulation results. Simulate the real power grid load environment, accurately evaluate its capacity and performance, and improve the accuracy and reliability of power supply capacity testing. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions in the embodiments or exemplary embodiments of the present invention, the drawings required for use in the embodiments or exemplary descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained according to the drawings without paying creative work.

[0051] Figure 1 A flow chart of a method for testing the capacity of a high-power, high-voltage, variable-frequency power supply using a power grid as a load provided by an embodiment of the present invention;

[0052] Figure 2 A flow chart of load change simulation for a target high-power high-voltage variable-frequency power supply provided by an embodiment of the present invention;

[0053] Figure 3 A block diagram of a high-power high-voltage variable-frequency power supply capacity test system using a power grid as a load provided by an embodiment of the present invention;

[0054] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0055] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0056] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0057] Figure 1 A flow chart of a method for testing the capacity of a high-power, high-voltage, variable-frequency power supply using a power grid as a load provided by an embodiment of the present invention;

[0058] like Figure 1 As shown, the present invention provides a flow chart of a method for testing the capacity of a high-power high-voltage variable-frequency power supply using a power grid as a load, comprising:

[0059] S102, obtaining capacity test process information of a high-power high-voltage variable-frequency power supply, extracting test process features according to the capacity test process information, and dividing the capacity test process into a plurality of test sub-processes;

[0060] S104, using a big data method to obtain historical capacity test instances of high-power and high-voltage variable-frequency power supplies of different specifications, analyzing the optimal test parameters of each test sub-process based on the historical capacity test instances, and forming a capacity test knowledge graph;

[0061] S106, obtaining specification information of the target high-power high-voltage variable-frequency power supply, formulating a capacity test plan in combination with the capacity test knowledge graph, and performing a capacity test on the target high-power high-voltage variable-frequency power supply;

[0062] S108, obtaining historical usage examples of high-power and high-voltage variable-frequency power supplies of different specifications, analyzing load changes in actual use according to the historical usage examples, and constructing a dynamic response test knowledge graph based on the analysis results;

[0063] S110, performing load change simulation on the target high-power high-voltage variable-frequency power supply based on the dynamic response test knowledge graph, and performing performance evaluation according to the load change simulation results.

[0064] It should be noted that the present invention provides a method and system for testing the capacity of a high-power, high-voltage, variable-frequency power supply with a power grid as a load. First, the capacity test process information of the high-power, high-voltage, variable-frequency power supply is obtained and sorted, including test steps, parameter settings, test environment requirements, etc. The entire capacity test process is divided into multiple test sub-processes, such as initial parameter calibration, full load test, overload test, dynamic response test, etc. Next, the historical capacity test instances of high-power, high-voltage, variable-frequency power supplies of different specifications are obtained by big data methods, so as to analyze and obtain the best test parameters for each test sub-process. For example, the optimal current value of the full load test, the time threshold of the overload test, etc., and a capacity test knowledge graph is constructed. Subsequently, the specification information of the power supply to be tested is obtained, including the rated power, rated voltage, frequency, etc. Combined with the constructed capacity test knowledge graph, a capacity test plan is formulated. According to the plan, the actual capacity test is performed on the target power supply, the test data of the power supply is monitored and recorded, and the authenticity of the calibrated capacity is analyzed. In addition, by analyzing the load change pattern in actual use, we build a dynamic response test knowledge graph, use the dynamic response test knowledge graph to simulate the load change of the target high-power high-voltage variable frequency power supply, simulate various load change conditions, observe and record the dynamic response of the power supply, and evaluate the performance of the power supply, including its response speed, steady-state error, overload protection and other characteristics. The capacity and dynamic performance of the power supply are fully verified to ensure its reliability and stability in actual operation.

[0065] Further, in a preferred embodiment of the present invention, the test process feature extraction is performed according to the capacity test process information, and the capacity test process is divided into multiple test sub-processes, specifically including:

[0066] Acquire capacity test process information of a high-power high-voltage variable-frequency power supply, perform feature extraction on the capacity test process information, and obtain capacity test process feature information;

[0067] Based on the capacity test process feature information, de-redundancy operations are performed on each capacity test process feature to generate a number of initial capacity test sub-processes, and test operation features corresponding to each initial capacity test sub-process are respectively extracted;

[0068] The Euclidean distance between the test operation characteristics of the initial capacity test sub-process is calculated, and the initial capacity test sub-process is clustered in combination with the K-means clustering algorithm. Several capacity test sub-processes are generated according to the clustering results.

[0069] It should be noted that in the test process of high-power high-voltage variable-frequency power supply, the test process usually includes test steps, parameter settings, test environment requirements, etc. By dividing the entire capacity test process into multiple test sub-processes, the specific steps and methods of capacity testing can be better understood.

[0070] Further, in a preferred embodiment of the present invention, the big data method is used to obtain historical capacity test instances of high-power and high-voltage variable-frequency power supplies of different specifications, and the optimal test parameters of each test sub-process are analyzed based on the historical capacity test instances, and a capacity test knowledge graph is formed, which specifically includes:

[0071] The historical capacity test instances of high-power and high-voltage variable-frequency power supplies of different specifications are obtained by using big data methods, and the test parameter characteristics and corresponding test process characteristics of each historical capacity test instance are extracted to obtain the characteristic information of the historical capacity test instance;

[0072] Based on the divided capacity test sub-processes, the test parameter characteristics of each historical capacity test instance are divided into corresponding capacity test sub-processes in combination with the historical capacity test instance characteristic information;

[0073] According to the variable frequency power supply specification attributes corresponding to the test parameter characteristics under each capacity test sub-process, the test parameters under each capacity test sub-process are classified according to the corresponding variable frequency power supply specifications to obtain the classification result information;

[0074] According to the classification result information, the April algorithm is used to analyze the optimal test parameters corresponding to each capacity test sub-process, and a frequent item set is generated through the historical test parameters corresponding to each test sub-process;

[0075] Based on the generated frequent item sets, association rules are formed, the support, confidence and lift corresponding to each frequent item set under each association rule are calculated, and each frequent item set is sorted. According to the sorting results, the best test parameters of different power specifications in each capacity test sub-process are selected to obtain the best test parameter information;

[0076] The category division result information and the optimal test parameter information are combined to form an entity triplet of power supply specification, capacity test process and optimal test parameter, and a capacity test knowledge graph is constructed based on the entity triplet.

[0077] It should be noted that the historical capacity test instances of high-power and high-voltage variable-frequency power supplies of different specifications are obtained by using big data methods, and the test parameter characteristics and corresponding test process characteristics in each historical capacity test instance are extracted. The test parameter characteristics of each historical capacity test instance are classified according to the divided capacity test sub-processes. For example, the current and voltage data in the full-load test are classified into the full-load test sub-process, and the parameters in the overload test are classified into the overload test sub-process. According to the specification attributes of different variable-frequency power supplies, the test parameters under each capacity test sub-process are classified. The parameter characteristics of each specification of variable-frequency power supply under different test processes are clarified to form the classification result information. The April algorithm is used to analyze the test parameters in each capacity test sub-process to find the best test parameters. By analyzing the historical test parameters, frequent item sets are generated, that is, parameter combinations that often appear in multiple tests. Based on these frequent item sets, association rules are constructed, the support, confidence and lift of each association rule are calculated, and these frequent item sets are sorted. According to the sorting results, the best test parameters for different power specifications in each capacity test sub-process are selected to ensure that the selected parameters can provide the best results in actual testing. Combining the category classification result information and the best test parameter information, a triple with power specifications, capacity test process and best test parameters as entities is constructed, and a capacity test knowledge graph is constructed. By associating power specifications, test processes and best test parameters, comprehensive and scientific guidance is provided for actual testing to ensure the accuracy and effectiveness of the test.

[0078] Further, in a preferred embodiment of the present invention, the step of obtaining the specification information of the target high-power high-voltage variable-frequency power supply, formulating a capacity test plan in combination with the capacity test knowledge graph, and performing a capacity test on the target high-power high-voltage variable-frequency power supply specifically includes:

[0079] Obtaining specification information of the target high-power high-voltage variable-frequency power supply, extracting specification features of the target high-power high-voltage variable-frequency power supply, obtaining optimal test parameters in combination with the capacity test knowledge graph, and formulating a capacity test plan;

[0080] Connect the target high-power high-voltage variable-frequency power supply to the power grid, set the initial parameters of the power grid based on the formulated capacity test plan, and control the target high-power high-voltage variable-frequency power supply to perform electrical synchronization with the power grid;

[0081] After the electrical synchronization operation, the grid connection operation is performed to connect the target high-power high-voltage variable-frequency power supply to the target power grid, and the power grid is used as a load to perform a capacity test on the target high-power high-voltage variable-frequency power supply;

[0082] Acquire the capacity test monitoring information of the target high-power high-voltage variable-frequency power supply, and calculate the capacity test power of the target high-power high-voltage variable-frequency power supply according to the capacity test monitoring information;

[0083] Obtain the rated power of the target high-power high-voltage variable-frequency power supply, calculate the deviation from the capacity test power, compare the calculated deviation value with the preset threshold, and analyze whether the rated power of the target high-power high-voltage variable-frequency power supply is true.

[0084] It should be noted that, first, the specification information of the target power supply is obtained, and its specification features are extracted, including key parameters such as rated power, voltage, and frequency. Combined with the capacity test knowledge graph, the optimal test parameters for the power supply are determined, and a detailed capacity test plan is formulated accordingly. Next, the target high-power high-voltage variable-frequency power supply is connected to the power grid. According to the formulated capacity test plan, the initial parameters of the power grid, such as voltage and frequency, are set, and then the variable-frequency power supply is controlled to perform electrical synchronization with the power grid. The purpose of electrical synchronization operation is to ensure that the output of the variable-frequency power supply is consistent with the voltage and frequency of the power grid, thereby avoiding voltage mutations and frequency instability that may occur during the grid connection process. After completing the electrical synchronization operation, the grid connection operation is performed, that is, the target high-power high-voltage variable-frequency power supply is connected to the grid. In this way, the grid acts as a load to perform capacity testing on the target variable-frequency power supply. After grid connection, the output power of the variable-frequency power supply is gradually increased to simulate the operating status under different load conditions, and the output voltage, current, frequency and other parameters of the variable-frequency power supply are monitored in real time. Subsequently, the capacity test monitoring information of the target high-power high-voltage variable-frequency power supply is obtained, and the capacity test power of the target power supply is calculated, that is, the actual output power of the power supply under actual load conditions. Finally, obtain the rated power of the target high-power high-voltage variable frequency power supply and compare it with the capacity test power calculated in the actual test. By calculating the deviation between the two, the deviation value is compared with the preset threshold. If the deviation is within the allowable range, it indicates that the rated power is true; if the deviation exceeds the threshold, the rated power of the target power supply may be inaccurate.

[0085] Further, in a preferred embodiment of the present invention, the acquisition of historical usage examples of high-power and high-voltage variable-frequency power supplies of different specifications, analysis of load changes in actual use according to the historical usage examples, and construction of a dynamic response test knowledge graph based on the analysis results specifically include:

[0086] Based on historical data retrieval, historical usage instances of high-power and high-voltage variable-frequency power supplies of different specifications are obtained, and load current characteristics and operating time characteristics of each historical usage instance are extracted to obtain characteristic information of the historical usage instance;

[0087] The isolation forest algorithm is introduced to detect anomalies in the load current characteristics of each historical usage instance. The load current feature detection information is obtained by constructing a random binary search tree to detect low-density or isolated data in the feature space.

[0088] Obtaining a load current operation benchmark, calculating a deviation between the load current feature detection information and the operation benchmark, and classifying corresponding load current features according to the calculated deviation to obtain first analysis information;

[0089] constructing a load current change curve corresponding to the historical usage instance according to the historical usage instance characteristic information, and marking the abnormal load current in combination with the first analysis information;

[0090] According to the load current change curve corresponding to each historical usage instance, the marked abnormal load current level and frequency are obtained, and the load change mode of each historical usage instance is classified into three categories: stable load, sudden load and fluctuating load, to obtain first classification information;

[0091] Setting evaluation indicators and evaluation weights, performing dynamic response evaluation on each historical usage instance in combination with the first classification information, evaluating the dynamic response status under different load types, and obtaining dynamic response status information;

[0092] A dynamic response test knowledge graph is constructed based on the dynamic response status information, and the operating parameters of the corresponding historical instances are used as test parameters.

[0093] It should be noted that, first, historical usage instances of power supplies of different specifications are obtained through historical data retrieval. The load current characteristics and operating time characteristics of each instance are extracted to form the characteristic information of the historical usage instances. By introducing the isolation forest algorithm, the load current characteristics in these historical instances are detected for abnormality. The isolation forest algorithm detects data with low distribution density or isolation in the feature space by constructing a random binary search tree, thereby identifying abnormal load current characteristics and obtaining load current characteristic detection information. Next, the load current operation benchmark is obtained, and the deviation between the load current characteristic detection information and the operation benchmark is calculated. According to the calculated deviation, the corresponding load current characteristics are graded to obtain the first analysis information, and the abnormal degree of the load current characteristics under different operating conditions is determined. Based on the characteristic information of the historical usage instances, the corresponding load current change curve is constructed. Combined with the first analysis information, the abnormal load current in the change curve is marked, and the abnormal change of the load current in each historical instance is analyzed. Subsequently, the load change mode of each historical usage instance is classified according to the level and frequency of the marked abnormal load current. The load change mode is divided into three categories: stable load, sudden load and fluctuating load, forming the first classification information. The evaluation indicators and evaluation weights are set, and the dynamic response evaluation is performed on each historical usage instance in combination with the first classification information. The evaluation content includes the dynamic response conditions such as the response speed and stability of the power supply under different load types, and the dynamic response condition information is obtained. Finally, based on the dynamic response condition information, a dynamic response test knowledge graph is constructed. The operating parameters of each historical instance are used as test parameters to record the power supply response characteristics and performance under different load conditions.

[0094] Further, in a preferred embodiment of the present invention, the load change simulation of the target high-power high-voltage variable frequency power supply is performed based on the dynamic response test knowledge graph, and the performance evaluation is performed according to the load change simulation result, specifically including:

[0095] Acquire test requirement information, formulate a load change simulation plan in combination with the dynamic response knowledge graph, select a load change mode based on the test requirement and define simulation conditions to obtain load simulation plan information;

[0096] Based on the load simulation scheme information, load change simulation is performed on the target high-power high-voltage variable-frequency power supply, load simulation monitoring information is obtained, and data preprocessing is performed on the load simulation monitoring information;

[0097] Constructing a time step, combining the preprocessed load simulation monitoring information with the time step to obtain the load simulation monitoring information based on the time step, introducing a Markov algorithm to perform a state transition probability analysis on the load simulation monitoring information based on the time step, and obtaining a state transition probability value for each preset time step;

[0098] Inputting the state transition probability value of each preset time step into the Bayesian network for training and obtaining training results, obtaining an abnormal factor for load simulation test based on the training results, and generating load simulation anomaly detection information;

[0099] Perform response characteristic analysis based on the load simulation monitoring information, calculate the response characteristic index of the target high-power high-voltage variable-frequency power supply under different load change conditions, and perform performance evaluation in combination with the load simulation abnormality detection information to obtain performance evaluation information;

[0100] A load simulation test report is generated based on the performance evaluation information and the load simulation anomaly detection information.

[0101] It should be noted that, first, the test requirement information is obtained, and combined with the dynamic response knowledge graph, a suitable load change simulation scheme is formulated by analyzing the previous load change data and power supply response characteristics. According to the specific test requirements, the appropriate load change mode is selected and the simulation conditions are defined to form the load simulation scheme information. According to the formulated load simulation scheme information, the target high-power high-voltage variable frequency power supply is subjected to load change simulation test. During the test, the load simulation monitoring information is obtained in real time, including key parameters such as the output voltage, current, and frequency of the power supply under different load conditions. The obtained load simulation monitoring information is preprocessed, including removing noise and outliers. Next, the time step is constructed, and the preprocessed load simulation monitoring information is combined with the time step to obtain the load simulation monitoring information based on the time step. The Markov algorithm is introduced to perform state transition probability analysis and calculate the state transition probability value of each preset time step. The state transition probability value of each preset time step is input into the Bayesian network for training, and the training results are obtained. Based on the training results, the abnormal factors during the load simulation test are identified, and the load simulation anomaly detection information is generated. The abnormal performance of the power supply under different load conditions is further analyzed. Based on the load simulation monitoring information, the response characteristic analysis is performed to calculate the response characteristic indicators of the target high-power high-voltage variable-frequency power supply under different load change conditions, such as response time, steady-state error, overload capacity, etc. Combined with the load simulation anomaly detection information, the overall performance of the power supply is evaluated to obtain performance evaluation information. Finally, based on the performance evaluation information and load simulation anomaly detection information, a load simulation test report is generated. The performance of the power supply in the load change simulation test, its dynamic response characteristics and reliability are recorded to provide a scientific basis and reference for the practical application of the power supply.

[0102] Figure 2 A flow chart of load change simulation for a target high-power high-voltage variable-frequency power supply provided by an embodiment of the present invention;

[0103] like Figure 2As shown, the present invention provides a flow chart for simulating load changes on a target high-power high-voltage variable-frequency power supply, including:

[0104] S202, obtaining test requirement information, selecting a load change mode and defining simulation conditions, and formulating a load simulation plan in combination with a dynamic response test knowledge graph;

[0105] S204, performing a load change simulation test based on the load simulation scheme, connecting the target high-power variable frequency power supply to the power grid for testing;

[0106] S206, acquiring load simulation monitoring information, performing load simulation anomaly detection according to the load simulation monitoring information, and obtaining load simulation anomaly detection information;

[0107] S208, calculating the response characteristic index of the power supply under different load change conditions based on the load simulation monitoring information, performing performance evaluation, and generating a load simulation test report.

[0108] It should be noted that the dynamic response test mainly tests the performance of the variable frequency power supply when facing rapid load changes, including response speed, voltage and frequency stability, etc. The response speed is evaluated by the time required for the variable frequency power supply to recover from load changes to output stability; the voltage and frequency stability is evaluated by judging whether the fluctuation range of the output voltage and frequency is within the normal range. In this way, a more comprehensive test report for the target power supply can be obtained, and its corresponding dynamic performance and reliability can be analyzed.

[0109] In addition, a high-power high-voltage variable-frequency power supply capacity testing method with a power grid as a load provided by the present invention also includes the following steps:

[0110] Based on historical data retrieval, historical capacity test monitoring information of high-voltage variable-frequency power supplies of different specifications is obtained, and attributes of the historical capacity test monitoring information are extracted to extract the test result attributes of the corresponding high-voltage variable-frequency power supplies to obtain attribute extraction information;

[0111] Based on the attribute extraction information, the historical capacity test monitoring data of each specification of high-voltage variable-frequency power supply is divided into a normal category and an abnormal category to obtain second category division information;

[0112] Perform feature extraction on the second category classification information, extract the historical capacity test monitoring data features of high-voltage variable-frequency power supplies of various specifications corresponding to the normal category and the abnormal category, construct a normal capacity test portrait and an abnormal capacity test portrait, and establish a capacity test database;

[0113] Acquire the current power supply information to be tested to formulate a capacity test plan, generate an initial capacity test plan, simplify the initial capacity test plan, and obtain a simplified capacity test plan;

[0114] Based on the simplified capacity test scheme, a capacity test is performed on the power supply to be tested at the current moment, capacity test monitoring data of each power supply to be tested is obtained, and similarity calculation is performed with the test profile in the capacity test database;

[0115] Whether the calibrated power of the corresponding power supply to be tested is real is judged according to the calculated similarity value, and a preliminary capacity test report of each power supply to be tested at the current moment is generated.

[0116] It should be noted that in the actual power supply capacity test scenario, multiple power supplies may need to be tested. When there are a large number of power supplies, detailed and complete capacity testing of each power supply will greatly increase the test time, thereby affecting work efficiency. In the face of this situation, the test data change characteristics of a certain specification power supply during a complete capacity test can be obtained through historical capacity test data, and the test data change characteristics of normal power supplies of the same specification are mostly the same, so that the capacity test portraits of power supplies of various specifications can be formed, including normal power supplies and abnormal power supplies. At the same time, in order to speed up the test efficiency, it is necessary to simplify the complete test process, and change the test time or frequency of each test sub-process without affecting the integrity of the test process, so as to simplify the total test time of each process, and obtain the test data of the corresponding test sub-process, ensuring the integrity of the test while speeding up the test time. Finally, based on the simplified test scheme, the test data of each power supply to be tested is obtained, and it is analyzed with the test portrait in the database, so that it can quickly determine whether the capacity of the target power supply is normal capacity, improve the detection efficiency, and realize the initial screening of power supplies for large-scale power supply capacity testing, so as to first monitor the abnormal power supply and improve the test efficiency and accuracy.

[0117] Figure 3 A high-power high-voltage variable-frequency power supply capacity test system 3 with a power grid as a load is provided in one embodiment of the present invention. The system includes: a memory 31 and a processor 32. The memory 31 contains a high-power high-voltage variable-frequency power supply capacity test method program with a power grid as a load. When the high-power high-voltage variable-frequency power supply capacity test method program with a power grid as a load is executed by the processor 32, the following steps are implemented:

[0118] Acquire capacity test process information of a high-power high-voltage variable-frequency power supply, extract test process features according to the capacity test process information, and divide the capacity test process into multiple test sub-processes;

[0119] Using big data methods to obtain historical capacity test instances of high-power and high-voltage variable-frequency power supplies of different specifications, analyzing the optimal test parameters of each test sub-process based on the historical capacity test instances, and forming a capacity test knowledge graph;

[0120] Obtain specification information of the target high-power high-voltage variable-frequency power supply, formulate a capacity test plan in combination with the capacity test knowledge graph, and perform a capacity test on the target high-power high-voltage variable-frequency power supply;

[0121] Obtain historical usage examples of high-power and high-voltage variable-frequency power supplies of different specifications, analyze load changes in actual use according to the historical usage examples, and build a dynamic response test knowledge graph based on the analysis results;

[0122] Based on the dynamic response test knowledge graph, load change simulation is performed on the target high-power high-voltage variable-frequency power supply, and performance evaluation is performed according to the load change simulation results.

[0123] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0124] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0125] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0126] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiments; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks or optical disks, and other media that can store program codes.

[0127] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0128] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for testing the capacity of a high-power, high-voltage, variable-frequency power supply using a power grid as a load, characterized in that: include: Acquire capacity test process information of a high-power high-voltage variable-frequency power supply, extract test process features according to the capacity test process information, and divide the capacity test process into multiple test sub-processes; Using big data methods to obtain historical capacity test instances of high-power and high-voltage variable-frequency power supplies of different specifications, analyzing the optimal test parameters of each test sub-process based on the historical capacity test instances, and forming a capacity test knowledge graph; Obtain specification information of the target high-power high-voltage variable-frequency power supply, formulate a capacity test plan in combination with the capacity test knowledge graph, and perform a capacity test on the target high-power high-voltage variable-frequency power supply; Obtain historical usage examples of high-power and high-voltage variable-frequency power supplies of different specifications, analyze load changes in actual use according to the historical usage examples, and build a dynamic response test knowledge graph based on the analysis results; Based on the dynamic response test knowledge graph, load change simulation is performed on the target high-power high-voltage variable-frequency power supply, and performance evaluation is performed according to the load change simulation results; The method of obtaining historical usage examples of high-power and high-voltage variable-frequency power supplies of different specifications, analyzing load changes in actual use according to the historical usage examples, and constructing a dynamic response test knowledge graph based on the analysis results specifically includes: Based on historical data retrieval, historical usage instances of high-power and high-voltage variable-frequency power supplies of different specifications are obtained, and load current characteristics and operating time characteristics of each historical usage instance are extracted to obtain characteristic information of the historical usage instance; The isolation forest algorithm is introduced to detect anomalies in the load current characteristics of each historical usage instance. The load current feature detection information is obtained by constructing a random binary search tree to detect low-density or isolated data in the feature space. Obtaining a load current operation benchmark, calculating a deviation between the load current feature detection information and the operation benchmark, and classifying corresponding load current features according to the calculated deviation to obtain first analysis information; constructing a load current change curve corresponding to the historical usage instance according to the historical usage instance characteristic information, and marking the abnormal load current in combination with the first analysis information; According to the load current change curve corresponding to each historical usage instance, the marked abnormal load current level and frequency are obtained, and the load change mode of each historical usage instance is classified into three categories: stable load, sudden load and fluctuating load, to obtain first classification information; Setting evaluation indicators and evaluation weights, performing dynamic response evaluation on each historical usage instance in combination with the first classification information, evaluating the dynamic response status under different load types, and obtaining dynamic response status information; A dynamic response test knowledge graph is constructed based on the dynamic response status information, and the operating parameters of the corresponding historical instances are used as test parameters.

2. A method for testing the capacity of a high-power high-voltage variable-frequency power supply using a power grid as a load according to claim 1, characterized in that: The extracting test process features according to the capacity test process information and dividing the capacity test process into a plurality of test sub-processes specifically includes: Acquire capacity test process information of a high-power high-voltage variable-frequency power supply, perform feature extraction on the capacity test process information, and obtain capacity test process feature information; Based on the capacity test process feature information, de-redundancy operations are performed on each capacity test process feature to generate a number of initial capacity test sub-processes, and test operation features corresponding to each initial capacity test sub-process are respectively extracted; The Euclidean distance between the test operation characteristics of the initial capacity test sub-process is calculated, and the initial capacity test sub-process is clustered in combination with the K-means clustering algorithm. Several capacity test sub-processes are generated according to the clustering results.

3. The method for testing the capacity of a high-power high-voltage variable-frequency power supply using a power grid as a load according to claim 1, characterized in that: The method of using big data to obtain historical capacity test instances of high-power and high-voltage variable-frequency power supplies of different specifications, analyzing the optimal test parameters of each test sub-process based on the historical capacity test instances, and forming a capacity test knowledge graph specifically includes: The historical capacity test instances of high-power and high-voltage variable-frequency power supplies of different specifications are obtained by using big data methods, and the test parameter characteristics and corresponding test process characteristics of each historical capacity test instance are extracted to obtain the characteristic information of the historical capacity test instance; Based on the divided capacity test sub-processes, the test parameter characteristics of each historical capacity test instance are divided into corresponding capacity test sub-processes in combination with the historical capacity test instance characteristic information; According to the variable frequency power supply specification attributes corresponding to the test parameter characteristics under each capacity test sub-process, the test parameters under each capacity test sub-process are classified according to the corresponding variable frequency power supply specifications to obtain the classification result information; According to the classification result information, the Apriori algorithm is used to analyze the optimal test parameters corresponding to each capacity test sub-process, and a frequent item set is generated through the historical test parameters corresponding to each test sub-process; Based on the generated frequent item sets, association rules are formed, the support, confidence and lift corresponding to each frequent item set under each association rule are calculated, and each frequent item set is sorted. According to the sorting results, the best test parameters of different power specifications in each capacity test sub-process are selected to obtain the best test parameter information; The category division result information and the optimal test parameter information are combined to form an entity triplet of power supply specification, capacity test process and optimal test parameter, and a capacity test knowledge graph is constructed based on the entity triplet.

4. The method for testing the capacity of a high-power high-voltage variable-frequency power supply using a power grid as a load according to claim 1, characterized in that: The obtaining of specification information of the target high-power high-voltage variable-frequency power supply, formulating a capacity test plan in combination with the capacity test knowledge graph, and performing a capacity test on the target high-power high-voltage variable-frequency power supply specifically includes: Obtaining specification information of the target high-power high-voltage variable-frequency power supply, extracting specification features of the target high-power high-voltage variable-frequency power supply, obtaining optimal test parameters in combination with the capacity test knowledge graph, and formulating a capacity test plan; Connect the target high-power high-voltage variable-frequency power supply to the power grid, set the initial parameters of the power grid based on the formulated capacity test plan, and control the target high-power high-voltage variable-frequency power supply to perform electrical synchronization with the power grid; After the electrical synchronization operation, the grid connection operation is performed to connect the target high-power high-voltage variable-frequency power supply to the target power grid, and the power grid is used as a load to perform a capacity test on the target high-power high-voltage variable-frequency power supply; Acquire the capacity test monitoring information of the target high-power high-voltage variable-frequency power supply, and calculate the capacity test power of the target high-power high-voltage variable-frequency power supply according to the capacity test monitoring information; Obtain the rated power of the target high-power high-voltage variable-frequency power supply, calculate the deviation from the capacity test power, compare the calculated deviation value with the preset threshold, and analyze whether the rated power of the target high-power high-voltage variable-frequency power supply is true.

5. The method for testing the capacity of a high-power high-voltage variable-frequency power supply using a power grid as a load according to claim 1, characterized in that: The load change simulation of the target high-power high-voltage variable-frequency power supply is performed based on the dynamic response test knowledge graph, and the performance evaluation is performed according to the load change simulation result, specifically including: Acquire test requirement information, formulate a load change simulation plan in combination with the dynamic response knowledge graph, select a load change mode based on the test requirement and define simulation conditions to obtain load simulation plan information; Based on the load simulation scheme information, load change simulation is performed on the target high-power high-voltage variable-frequency power supply, load simulation monitoring information is obtained, and data preprocessing is performed on the load simulation monitoring information; Constructing a time step, combining the preprocessed load simulation monitoring information with the time step to obtain the load simulation monitoring information based on the time step, introducing a Markov algorithm to perform a state transition probability analysis on the load simulation monitoring information based on the time step, and obtaining a state transition probability value for each preset time step; Inputting the state transition probability value of each preset time step into the Bayesian network for training and obtaining training results, obtaining an abnormal factor for load simulation test based on the training results, and generating load simulation anomaly detection information; Perform response characteristic analysis based on the load simulation monitoring information, calculate the response characteristic index of the target high-power high-voltage variable-frequency power supply under different load change conditions, and perform performance evaluation in combination with the load simulation abnormality detection information to obtain performance evaluation information; A load simulation test report is generated based on the performance evaluation information and the load simulation anomaly detection information.

6. A high-power high-voltage variable-frequency power supply capacity test system with a power grid as a load, characterized in that: The system includes: a memory and a processor, wherein the memory contains a high-power high-voltage variable frequency power supply capacity test method program with a power grid as a load, and the high-power high-voltage variable frequency power supply capacity test method program with a power grid as a load is executed by the processor to implement the following steps: Acquire capacity test process information of a high-power high-voltage variable-frequency power supply, extract test process features according to the capacity test process information, and divide the capacity test process into multiple test sub-processes; Using big data methods to obtain historical capacity test instances of high-power and high-voltage variable-frequency power supplies of different specifications, analyzing the optimal test parameters of each test sub-process based on the historical capacity test instances, and forming a capacity test knowledge graph; Obtain specification information of the target high-power high-voltage variable-frequency power supply, formulate a capacity test plan in combination with the capacity test knowledge graph, and perform a capacity test on the target high-power high-voltage variable-frequency power supply; Obtain historical usage examples of high-power and high-voltage variable-frequency power supplies of different specifications, analyze load changes in actual use according to the historical usage examples, and build a dynamic response test knowledge graph based on the analysis results; Based on the dynamic response test knowledge graph, load change simulation is performed on the target high-power high-voltage variable-frequency power supply, and performance evaluation is performed according to the load change simulation results; The method of obtaining historical usage examples of high-power and high-voltage variable-frequency power supplies of different specifications, analyzing load changes in actual use according to the historical usage examples, and constructing a dynamic response test knowledge graph based on the analysis results specifically includes: Based on historical data retrieval, historical usage instances of high-power and high-voltage variable-frequency power supplies of different specifications are obtained, and load current characteristics and operating time characteristics of each historical usage instance are extracted to obtain characteristic information of the historical usage instance; The isolation forest algorithm is introduced to detect anomalies in the load current characteristics of each historical usage instance. The load current feature detection information is obtained by constructing a random binary search tree to detect low-density or isolated data in the feature space. Obtaining a load current operation benchmark, calculating a deviation between the load current feature detection information and the operation benchmark, and classifying corresponding load current features according to the calculated deviation to obtain first analysis information; constructing a load current change curve corresponding to the historical usage instance according to the historical usage instance characteristic information, and marking the abnormal load current in combination with the first analysis information; According to the load current change curve corresponding to each historical usage instance, the marked abnormal load current level and frequency are obtained, and the load change mode of each historical usage instance is classified into three categories: stable load, sudden load and fluctuating load, to obtain first classification information; Setting evaluation indicators and evaluation weights, performing dynamic response evaluation on each historical usage instance in combination with the first classification information, evaluating the dynamic response status under different load types, and obtaining dynamic response status information; A dynamic response test knowledge graph is constructed based on the dynamic response status information, and the operating parameters of the corresponding historical instances are used as test parameters.

Images