Safety protection test method and system for breakdown of flexible direct-current converter valve arrester

Abstract

The application discloses a safety protection test method and system for breakdown of a flexible direct-current converter valve lightning arrester, and the method comprises the following steps: obtaining test data based on a test scheme-test system and performing data analysis on the test data by using a data analysis model to obtain test prompt information of the test data; determining reference test information matched with the test prompt information; performing test result analysis and processing on the test data based on the reference test information and the test data by using a test result analysis model to obtain a first test result; the data analysis model is obtained by training sample data, the sample data is generated by the test result analysis model, and the data analysis and processing performed by the data analysis model at least includes the test result analysis and processing performed by the test result analysis model; the test prompt information obtained by the data analysis model can be used as a basis to obtain the reference test information, which is used as reference information to assist the test result analysis model in analyzing the test data, and the test result analysis accuracy is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, and in particular to a safety protection test method and system for breakdown of a flexible DC converter valve arrester. BACKGROUND

[0002] The existing flexible DC power transmission system used in power transmission technology usually has characteristics such as high voltage level, large capacity transmission and flexible control. The flexible DC converter valve is the core equipment of the flexible DC power transmission system, and the arrester is one of the key protection devices of the flexible DC converter valve, which is used to prevent damage to system equipment caused by lightning overvoltage. However, in actual operation, the arrester may break down, causing the system to fail to operate normally.

[0003] In related technologies, after completing the simulation test of the breakdown of the arrester, in order to improve the efficiency of analyzing the test results, a pre-trained artificial intelligence model is often used to analyze the test data. However, the test sample data used in model training is limited, which may result in inaccurate analysis of the test results. SUMMARY

[0004] To solve the above technical problems, the embodiments of the present application provide a safety protection test method and system for breakdown of a flexible DC converter valve arrester, which can improve the accuracy of analyzing test results.

[0005] In a first aspect, the embodiments of the present application provide a safety protection test method for breakdown of a flexible DC converter valve arrester, comprising:

[0006] Based on the test data measured by a safety protection test device, data analysis and processing are performed by a data analysis model to obtain test prompt information corresponding to the test data, wherein the safety protection test device is used to simulate breakdown of a flexible DC converter valve arrester;

[0007] determining reference test information matched with the test prompt information;

[0008] Based on the reference test information and the test data, test result analysis and processing are performed by a test result analysis model to obtain a first test result;

[0009] The data analysis model is obtained by training sample data, the sample data is data generated by the test result analysis model, and the data analysis and processing performed by the data analysis model at least includes the test result analysis and processing performed by the test result analysis model.

[0010] Optionally, the reference test information includes first reference test information and second reference test information, and the determination of the reference test information matched with the test prompt information includes:

[0011] dividing the test prompt information into a plurality of prompt information blocks, and performing feature extraction on each prompt information block to obtain corresponding first features and second features, wherein the first features and the second features each represent different test information;

[0012] clustering the first features corresponding to each of the plurality of prompt information blocks to obtain at least one first feature cluster, and clustering the second features corresponding to each of the plurality of prompt information blocks to obtain at least one second feature cluster;

[0013] determining first reference test information based on the at least one first feature cluster, and determining second reference test information based on the at least one second feature cluster.

[0014] Optionally, the determining of the first reference test information based on the at least one first feature cluster and the determining of the second reference test information based on the at least one second feature cluster comprise:

[0015] fusing the first features in each first feature cluster to obtain third features corresponding to each first feature cluster, and fusing the second features in each second feature cluster to obtain fourth features corresponding to each second feature cluster;

[0016] obtaining information matching each third feature in a preset first standard test database as first standard test information of the corresponding first feature cluster, and obtaining information matching each fourth feature in a preset second standard test database as second standard test information of the corresponding second feature cluster;

[0017] fusing the first standard test information of each of the at least one first feature cluster to obtain the first reference test information, and fusing the second standard test information of each of the at least one second feature cluster to obtain the second reference test information.

[0018] Optionally, the performing of the feature extraction on each prompt information block to obtain corresponding first features and second features comprises:

[0019] performing encoding on each prompt information block by an encoder to obtain corresponding first features and second features.

[0020] Optionally, the sample data comprises sample prompt information and sample test results, and the training process of the data analysis model comprises:

[0021] obtaining a data analysis model to be trained, and sample test data and corresponding test result labels thereof;

[0022] inputting the sample test data into the test result analysis model to obtain the sample prompt information and the sample test result output by the test result analysis model;

[0023] training the data analysis model based on the test result label, the sample prompt information and the sample test result to obtain the data analysis model.

[0024] Optionally, the test result analysis model comprises a large model, and the test result analysis processing is performed on the test result analysis model based on the test data and the test information to obtain a first test result, comprising:

[0025] determining model prompt information for the large model based on the test information;

[0026] inputting the model prompt information and the test data into the large model, so that the large model performs reasoning based on the test data under the guidance of the model prompt information, thereby completing the test result analysis processing and obtaining a first test result.

[0027] Optionally, the method further comprises:

[0028] obtaining test description information associated with the test data input by a user;

[0029] The determination of the model prompt information for the large model based on the test information comprises:

[0030] performing cleaning processing on the test information based on the test description information to obtain the model prompt information.

[0031] Optionally, the method further comprises:

[0032] detecting the correlation between the test data and the first test result by using the data analysis model;

[0033] determining a second test result based on the detected correlation information.

[0034] Optionally, the determination of the second test result based on the detected correlation information comprises:

[0035] in a case where the correlation information meets a preset correlation condition, taking the first test result as the second test result;

[0036] in a case where the correlation information does not meet the preset correlation condition, feeding back the correlation information to the data analysis model, so that the data analysis model updates the test prompt information based on the correlation information;

[0037] The updated test prompt information is used as new test prompt information to re-perform the step of determining the reference test information matched with the test prompt information until the re-obtained correlation information meets the preset correlation condition.

[0038] In a second aspect, the embodiments of the present application provide a safety protection test system for breakdown of a flexible DC converter valve arrester, comprising:

[0039] The data analysis module is configured to perform data analysis processing on the test data measured by the safety protection test device based on a data analysis model to obtain test prompt information corresponding to the test data, wherein the safety protection test device is configured to simulate breakdown of the flexible DC converter valve arrester.

[0040] The reference test information determination module is configured to determine reference test information matched with the test prompt information.

[0041] The first test result acquisition module is configured to perform test result analysis processing on the reference test information and the test data based on a test result analysis model to obtain a first test result.

[0042] The data analysis model is obtained by training sample data, the sample data is generated by the test result analysis model, and the data analysis processing performed by the data analysis model at least includes the test result analysis processing performed by the test result analysis model.

[0043] In summary, the embodiments of the present application have at least the following beneficial effects:

[0044] By using the embodiments of the present application, the test prompt information corresponding to the test data measured by the safety protection test device is obtained by performing data analysis processing on the test data based on a data analysis model, wherein the safety protection test device is configured to simulate breakdown of the flexible DC converter valve arrester; the reference test information matched with the test prompt information is determined; the first test result is obtained by performing test result analysis processing on the reference test information and the test data based on a test result analysis model; wherein the data analysis model is obtained by training sample data, the sample data is generated by the test result analysis model, and the data analysis processing performed by the data analysis model at least includes the test result analysis processing performed by the test result analysis model. The test prompt information obtained by the data analysis model can be used as a reference to obtain the reference test information to assist the test result analysis model in analyzing the test data, thereby improving the accuracy of the test result analysis. BRIEF DESCRIPTION OF DRAWINGS

[0045] Figure 1is a flowchart of a safety protection test method for breakdown of a flexible DC converter valve arrester provided by an embodiment of the present application;

[0046] Figure 2 is a structural diagram of a safety protection test system for breakdown of a flexible DC converter valve arrester provided by an embodiment of the present application;

[0047] Figure 3 is a structural diagram of a safety protection test device provided by an embodiment of the present application;

[0048] Figure 4 is a circuit diagram of a safety protection test device provided by an embodiment of the present application;

[0049] Figure 5 is a test point diagram of a safety protection test device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0050] The technical solutions in the embodiments of the present application will be clearly and completely described in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0051] In the description of the present application, the terms "first", "second", "third", etc. are only for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined with "first", "second", "third", etc. can explicitly or implicitly include one or more of the features. In the description of the present application, the meaning of "multiple" is two or more, unless otherwise specified. In the description of the present application, the term "includes" and its variants are open inclusion, that is, "includes but is not limited to". The term "based on" is "at least partially based on". The term "according to" is "at least partially according to". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one other embodiment"; the term "some embodiments" means "at least some embodiments".

[0052] In the description of the present application, it should be noted that, unless otherwise explicitly specified and limited, the terms "mounting", "connection", "connection" should be understood in a broad sense, for example, it can be fixed connection, or detachable connection, or integrally connected; it can be mechanical connection, or electrical connection; it can be directly connected, or indirectly connected through intermediate medium, or the communication inside two elements. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0053] In the description of the present application, it should be noted that, unless otherwise defined, all technical and scientific terms used in the present application have the same meanings as commonly understood by one of ordinary skill in the art to which this technology belongs. The terms used in the specification of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application, and the above terms can be specifically understood by one of ordinary skill in the art.

[0054] In a first aspect, see Figure 1 , a flowchart of a safety protection test method for flexible DC converter valve arrester breakdown provided by an embodiment of the present application is shown, which comprises steps S101-S103, and specifically as follows:

[0055] S101, based on the test data measured by the safety protection test device, data analysis and processing are performed through a data analysis model to obtain test prompt information corresponding to the test data, wherein the safety protection test device is used to simulate flexible DC converter valve arrester breakdown.

[0056] In one example, the safety protection test method can be applied to the cloud, which can be deployed with a data analysis model and / or a test result analysis model (if the cloud does not deploy the corresponding model, the cloud can call a device deployed with the corresponding model to realize the calling of the model), at this time, the cloud can establish a communication connection with the safety protection test device to obtain the measured test data from the safety protection test device. In addition, the safety protection test device can also be configured to send the measured test data to the cloud in response to the measurement of the test data.

[0057] S102, determining reference test information matched with the test prompt information.

[0058] In one example, step S102 can include: according to the test prompt information, retrieving at least part of the reference test information in a historical test database, and / or according to the test prompt information, retrieving at least part of the reference test information in a preset standard test database.

[0059] The standard test database can store standard test information, and the test corresponding to the standard test information can be a test completed by a standard safety protection test device according to a standard test process and / or a standard test environment. In this way, at least part of the reference test information retrieved by the present embodiment can be used to prompt the model to compare at least one of the following: the difference between the safety protection test device and the standard safety protection test device, the difference between the test process indicated by the measured test data and the standard test process, and the difference between the test environment indicated by the measured test data and the standard test environment.

[0060] The historical test database can store data of historical tests for simulating lightning arrester breakdown. In this way, the data obtained from each historical test can be fully utilized as reference test information, and the waste of computing power caused by retraining the model every time the data obtained from the historical test is obtained can be avoided.

[0061] In step S103, based on the reference test information and the test data, the test result analysis model is used to analyze and process the test results to obtain a first test result.

[0062] In one example, step S103 can include directly using the reference test information as an analysis prompt of the test result analysis model, and using the test result analysis model to analyze and process the test data.

[0063] The data analysis model is trained by sample data, and the sample data is generated by the test result analysis model. The data analysis model performs data analysis processing, which at least includes the test result analysis processing performed by the test result analysis model.

[0064] It should be noted that "data analysis processing at least includes test result analysis processing" can be understood as the data analysis model after training can also be used to realize the test result analysis processing performed by the test result analysis model, so that the output of the data analysis model can include corresponding test prompt information.

[0065] In one example, the sample data is suitable for indicating an input-output data pair of the test result analysis model.

[0066] In an optional embodiment, the reference test information includes first reference test information and second reference test information, and the determination of the reference test information matched with the test prompt information includes:

[0067] The test prompt information is divided into a plurality of prompt information blocks, and feature extraction is performed on each prompt information block to obtain corresponding first features and second features, wherein the first features and the second features each represent different test information.

[0068] The first features corresponding to the plurality of prompt information blocks are clustered to obtain at least one first feature cluster, and the second features corresponding to the plurality of prompt information blocks are clustered to obtain at least one second feature cluster.

[0069] determine first reference test information based on the at least one first feature cluster, and determine second reference test information based on the at least one second feature cluster.

[0070] In one example, the test information represented by the first feature is different from the test information represented by the second feature, for example, the test information represented by the first feature can include a test procedure, and the test information represented by the second feature can include a test environment, etc.

[0071] In one example, clustering the first features corresponding to the plurality of prompt information blocks to obtain at least one first feature cluster, and clustering the second features corresponding to the plurality of prompt information blocks to obtain at least one second feature cluster can include: determining the similarity between each first feature, and clustering the first features corresponding to the plurality of prompt information blocks based on the similarity between each first feature to obtain at least one first feature cluster; determining the similarity between each second feature, and clustering the second features corresponding to the plurality of prompt information blocks based on the similarity between each second feature to obtain at least one second feature cluster.

[0072] In one example, the features described in any one or more embodiments of the present application can be represented as feature vectors, and the similarity described in any one or more embodiments of the present application can be calculated by at least one of the following: cosine similarity, Euclidean distance, Manhattan distance, Pearson correlation coefficient, etc. It should be understood that this implementation is only exemplary and does not limit the present application.

[0073] In one example, determining first reference test information based on the at least one first feature cluster, and determining second reference test information based on the at least one second feature cluster can include: inputting the at least one first feature cluster into a large language model to generate corresponding first reference test information; and inputting the at least one second feature cluster into a large language model to generate corresponding second reference test information. In this embodiment, the powerful computing power and semantic understanding ability of the large language model can be used to generate reasonable and comprehensive test information that integrates the information in each feature cluster.

[0074] In one optional implementation, the determining first reference test information based on the at least one first feature cluster, and determining second reference test information based on the at least one second feature cluster includes:

[0075] fusing each first feature in each first feature cluster to obtain a third feature corresponding to each first feature cluster, and fusing each second feature in each second feature cluster to obtain a fourth feature corresponding to each second feature cluster;

[0076] In the preset first standard test database, information matched with each of the third features is obtained as first standard test information of a corresponding first feature cluster, and in the preset second standard test database, information matched with each of the fourth features is obtained as second standard test information of a corresponding second feature cluster.

[0077] The first standard test information of each of the at least one first feature cluster is fused to obtain first reference test information, and the second standard test information of each of the at least one second feature cluster is fused to obtain second reference test information.

[0078] It can be understood that the first standard test database and / or the second standard test database in the embodiment can refer to the description of the standard test database described above, and the difference can be that, taking the test information represented by the first feature including a test procedure and the test information represented by the second feature including a test environment as an example, the test corresponding to the standard test information stored in the first standard test database can be a test completed by a standard safety protection test device according to a standard test procedure, and the test corresponding to the standard test information stored in the second standard test database can be a test completed by a standard safety protection test device according to a standard test environment.

[0079] It can be understood that each of the third features in the embodiment fuses the information of each of the first features in the corresponding first feature cluster, so that the third feature can represent the characteristics of the corresponding first feature cluster, and the first standard test information matched with the third feature corresponds to the characteristics of the corresponding first feature cluster. In addition, the fourth feature is the same, and details are not repeated here.

[0080] In an optional implementation, the feature extraction on each of the prompt information blocks to obtain the corresponding first feature and the second feature includes:

[0081] Each of the prompt information blocks is encoded by an encoder to obtain the corresponding first feature and the second feature.

[0082] In an optional implementation, the sample data includes sample prompt information and sample test results, and the training process of the data analysis model includes:

[0083] Obtaining a data analysis model to be trained, and sample test data and a test result label corresponding to the sample test data;

[0084] Inputting the sample test data into the test result analysis model to obtain the sample prompt information and the sample test results output by the test result analysis model;

[0085] Based on the test result label, the sample prompt information and the sample test result, the data analysis model is trained based on the to-be-trained data analysis model to obtain the data analysis model.

[0086] In one example, based on the test result label, the sample prompt information and the sample test result, the data analysis model is trained based on the to-be-trained data analysis model to obtain the data analysis model, which can include: based on the difference between the test result label and the sample test result, and the association between the sample prompt information and the difference, the to-be-trained data analysis model is trained.

[0087] It should be understood that the model training can be completed by using a general training method, such as gradient descent method, and the like, which is not strictly limited herein.

[0088] In an optional implementation, the test result analysis model includes a large model, and based on the test information and the test data, the test result analysis processing is performed by the test result analysis model to obtain a first test result, which includes:

[0089] Based on the test information, model prompt information for the large model is determined;

[0090] The model prompt information and the test data are input into the large model, so that the large model performs reasoning according to the test data under the guidance of the model prompt information, thereby completing the test result analysis processing and obtaining the first test result.

[0091] In one example, the test information can also be directly used as the model prompt information for the large model.

[0092] In an optional implementation, the method further includes:

[0093] Obtaining test description information associated with the test data input by a user.

[0094] In one example, the test description information can be obtained by a user according to a pre-set test description template, for example, the user fills in the test description template, so that the test description information has a strict and clear semantic and conforms to the test logic. At this time, it is equivalent to not needing to understand the semantic / context of the test description information and not needing to understand the test logic of the test description information, so that the understanding ability of the large model is not needed, and the problem of inaccurate information cleaning caused by model understanding deviation is avoided.

[0095] The model prompt information for the large model is determined based on the test information, which includes:

[0096] Based on the test description information, the test participation information is cleaned to obtain the model prompt information.

[0097] In this embodiment, the cleaning processing can be used to clean the information in the test participation information which is not sufficiently associated with the current test data based on the test description information input by the user, so that only the information with high association with the current test data is retained in the model prompt information, and the association can be obtained by calculating the similarity.

[0098] In one example, based on the test description information, the test participation information is cleaned to obtain the model prompt information, which can include: based on the format of the test description template, the test description information is semantically understood to obtain the semantic understanding result corresponding to the test description information, wherein the semantic understanding result is suitable for indicating the test logic corresponding to the test data; in the test participation information, the information with insufficient similarity with the semantic understanding result is determined and removed from the test participation information to obtain the model prompt information.

[0099] In an optional implementation, the method further includes:

[0100] The test data and the first test result are detected for correlation by the data analysis model;

[0101] Based on the detected correlation information, a second test result is determined.

[0102] In an optional implementation, the determination of the second test result based on the detected correlation information includes:

[0103] In the case where the correlation information meets a preset correlation condition, the first test result is taken as the second test result;

[0104] In the case where the correlation information does not meet the preset correlation condition, the correlation information is fed back to the data analysis model, so that the data analysis model updates the test prompt information according to the correlation information;

[0105] The updated test prompt information is taken as new test prompt information to re-execute the step of determining the test participation information matched with the test prompt information until the re-obtained correlation information meets the preset correlation condition.

[0106] In one example, the preset correlation condition can include that the correlation similarity indicated by the correlation information is lower than a correlation threshold.

[0107] In a second aspect, correspondingly, the embodiments of the present application also provide a safety protection test system for breakdown of a flexible DC converter valve arrester, which can implement all processes of the safety protection test method for breakdown of a flexible DC converter valve arrester provided by the above embodiments.

[0108] Referring to Figure 2 , a structure schematic diagram of a safety protection test system for breakdown of a flexible DC converter valve arrester provided by the embodiments of the present application is shown, and the safety protection test system for breakdown of a flexible DC converter valve arrester comprises:

[0109] A data analysis module 201 is configured to perform data analysis processing on the test data measured by a safety protection test device based on a data analysis model, so as to obtain test prompt information corresponding to the test data, wherein the safety protection test device is configured to simulate breakdown of a flexible DC converter valve arrester.

[0110] A reference test information determination module 202 is configured to determine reference test information matched with the test prompt information.

[0111] A first test result acquisition module 203 is configured to perform test result analysis processing on the reference test information and the test data based on a test result analysis model, so as to obtain a first test result.

[0112] The data analysis model is obtained by training sample data, the sample data is data generated by the test result analysis model, and the data analysis processing performed by the data analysis model at least includes the test result analysis processing performed by the test result analysis model.

[0113] In an optional embodiment, the reference test information comprises first reference test information and second reference test information, and the determination of the reference test information matched with the test prompt information comprises:

[0114] The test prompt information is divided into a plurality of prompt information blocks, and feature extraction is performed on each prompt information block to obtain corresponding first features and second features, wherein the first features and the second features each represent different test information.

[0115] The first features corresponding to the plurality of prompt information blocks are clustered to obtain at least one first feature cluster, and the second features corresponding to the plurality of prompt information blocks are clustered to obtain at least one second feature cluster.

[0116] The first reference test information is determined based on the at least one first feature cluster, and the second reference test information is determined based on the at least one second feature cluster.

[0117] In an optional implementation, the determining, based on the at least one first feature cluster, of first reference test information and the determining, based on the at least one second feature cluster, of second reference test information comprises:

[0118] fusing each first feature in each first feature cluster to obtain a third feature corresponding to each first feature cluster, and fusing each second feature in each second feature cluster to obtain a fourth feature corresponding to each second feature cluster;

[0119] obtaining, in a preset first standard test database, information matched with each third feature as first standard test information of a corresponding first feature cluster, and obtaining, in a preset second standard test database, information matched with each fourth feature as second standard test information of a corresponding second feature cluster;

[0120] fusing the first standard test information of each first feature cluster to obtain first reference test information, and fusing the second standard test information of each second feature cluster to obtain second reference test information.

[0121] In an optional implementation, the feature extraction on each piece of prompt information to obtain corresponding first features and second features comprises:

[0122] encoding, by an encoder, each piece of prompt information to obtain corresponding first features and second features.

[0123] In an optional implementation, the sample data comprises sample prompt information and sample test results, and the training process of the data analysis model comprises:

[0124] obtaining a data analysis model to be trained and sample test data and corresponding test result labels;

[0125] inputting the sample test data into the test result analysis model to obtain sample prompt information and sample test results output by the test result analysis model;

[0126] performing model training on the data analysis model to be trained based on the test result labels, the sample prompt information, and the sample test results, to obtain the data analysis model.

[0127] In an optional implementation, the test result analysis model comprises a large model, and the performing, based on the reference test information and the test data, of test result analysis processing by the test result analysis model to obtain first test results comprises:

[0128] determining, based on the reference test information, model prompt information for the large model;

[0129] inputting the model prompt information and the test data into the large model, so that the large model performs reasoning according to the test data under the guidance of the model prompt information, thereby completing test result analysis processing and obtaining a first test result.

[0130] In an optional implementation, the system further includes:

[0131] a test description information acquisition module configured to acquire test description information associated with the test data input by a user;

[0132] The model prompt information for the large model is determined based on the participation test information, and the determination includes:

[0133] cleaning the participation test information based on the test description information to obtain the model prompt information.

[0134] In an optional implementation, the system further includes:

[0135] a correlation detection module configured to perform correlation detection on the test data and the first test result by using the data analysis model;

[0136] a second test result acquisition module configured to determine a second test result based on the detected correlation information.

[0137] In an optional implementation, the second test result is determined based on the detected correlation information, and the determination includes:

[0138] in a case where the correlation information meets a preset correlation condition, the first test result is taken as the second test result;

[0139] in a case where the correlation information does not meet the preset correlation condition, the correlation information is fed back to the data analysis model, so that the data analysis model updates the test prompt information according to the correlation information;

[0140] the updated test prompt information is taken as new test prompt information, and the step of determining the participation test information matched with the test prompt information is re-executed until the re-obtained correlation information meets the preset correlation condition.

[0141] In addition, in some prior art, flexible HVDC transmission technology is an important means of large-scale new energy transmission. In recent years, the research, design and manufacturing technology of EHV flexible HVDC converter valve is developing continuously, and has reached the level of ±800kV 8GW. The capacity of ±800kV 8GW EHV flexible HVDC transmission technology is comparable to that of conventional HVDC. In terms of operation control, it has the characteristics of 4-quadrant flexible control and does not depend on the voltage support of the AC power grid. However, the conventional HVDC can only achieve 2-quadrant control and depends on the support of the AC power grid.

[0142] The flexible HVDC converter valve is the core equipment of the flexible HVDC transmission system. The converter valve is composed of a plurality of sub-modules. Taking a certain project of ±800kV 8GW as an example, at least several thousand sub-modules are required for the project.

[0143] The number of sub-modules and the selection of sub-module capacitance value will greatly affect the project cost. The configuration of valve arresters can optimize the design of the converter valve, reduce the number of sub-modules and reduce the project cost. However, the breakdown condition and protection of the arrester need to be considered.

[0144] The valve arrester can limit the overvoltage level of the converter valve during energy absorption, and protect the converter valve. If the valve arrester flashes over during energy absorption, it is equivalent to short-circuiting the high and low voltage ends of the converter valve group, which will cause the uncontrolled discharge of the large capacitor in the converter valve sub-module. In the most severe condition, it will cause the explosion of the converter valve, causing equipment loss and leading to the power failure of the transmission system.

[0145] In order to solve the problem that the breakdown of the arrester may cause damage to the flexible HVDC converter valve and further expand the scope of the fault, it is usually necessary to design corresponding protection measures for the arrester breakdown problem to ensure the safety of the sub-modules that need to be protected after the arrester breakdown. However, since the joint test of the transmission system and the arrester is required, at least one of the following difficulties exists:

[0146] 1. The voltage level of the transmission system is high, and the voltage level of the arrester is usually several hundred kilovolts or even higher. It is difficult and dangerous to coordinate the two large high-voltage devices together for testing. At this time, scheme 1 can be adopted: the flexible HVDC converter valve group is disassembled, and one or more converter valve sub-modules are used as the basic test unit to simulate the transient breakdown test of the arrester.

[0147] 2. When conducting joint testing, the characteristics and mutual influence of the arrester and the transmission system need to be considered to ensure that the test conditions can truly simulate the actual operating conditions, which poses a high challenge to the design and technical requirements of the test scheme. At this time, scheme 2 can be adopted: through multiple rounds of electromagnetic-mechanical simulation, the boundary conditions of the test are considered comprehensively, and the simulation test is carried out under severe test conditions to verify the effectiveness of the protection measures.

[0148] 3、The structure of the power transmission system and the arrester is complex, which makes it difficult to install and remove the tested equipment, which not only increases the time and cost of the test, but also may cause damage to the arrester and the power transmission system; at this time, the above-mentioned scheme 1 can be adopted.

[0149] 4、The test site and test equipment are required to be high, and professional test equipment with high voltage bearing capacity is required. At this time, the above-mentioned scheme 1 can be adopted.

[0150] However, the above-mentioned schemes 1 and 2 have many difficulties in simulating the safety protection verification experiment of accidental breakdown of the arrester, so it is particularly important to study a safety protection test device for simulating breakdown of the arrester of the ultra-high voltage flexible DC converter valve. The safety protection test device is designed to evaluate whether the protection means set after the breakdown of the arrester in the ultra-high voltage flexible DC power transmission system can effectively protect the flexible DC converter valve from being affected through simulation test under laboratory conditions.

[0151] Therefore, referring to Figure 3 and Figure 4 , the present application gives an example of a safety protection test device for simulating breakdown of the arrester of the ultra-high voltage flexible DC converter valve. The device can be used to simulate the working condition of accidental breakdown of the arrester during the voltage rising process of the valve group when the flexible DC valve is charged, so as to verify whether the protection means set for this working condition can effectively protect the converter valve from being damaged. The safety protection test device comprises:

[0152] a tested module 301;

[0153] a pre-charging circuit module 302, both ends of which are electrically connected to the first end and the second end of the tested module;

[0154] an arrester protection simulation module 303, comprising a first switch and a protection circuit connected in series, both ends of the first switch and the protection circuit connected in series being electrically connected to the first end and the second end of the tested module;

[0155] a discharge circuit module 304, both ends of which are electrically connected to the first end and the second end of the tested module; and

[0156] a controller 305, which is communicatively connected to the tested module, the pre-charging circuit module, the arrester protection simulation module and the discharge circuit module, and is configured to:

[0157] in response to a pre-charging instruction, control the pre-charging circuit module to output current to the tested module, and when it is determined that the voltage of the tested module reaches a first preset voltage, control the pre-charging circuit module to stop outputting current;

[0158] In a case where it is determined that the voltage of the test module reaches the first preset voltage, the discharging circuit module is controlled to output current to the test module in response to a discharging instruction, and when it is determined that the voltage of the test module reaches a second preset voltage, the first switch is controlled to be turned on, so that at least part of the current output by the discharging circuit module flows into the protection circuit, where the second preset voltage is greater than the first preset voltage.

[0159] Thus, the embodiment can reduce the test difficulty and time consumed for the safety protection test of the lightning arrester breakdown, improve the test safety, and control the safety protection test device to perform the related test through the controller, so that more accurate test data (such as circuit information in each module) can be measured more efficiently and conveniently during the test, to facilitate subsequent data processing.

[0160] Further description of the safety protection test device is given below.

[0161] In one example, the test module 301 can be used to simulate a device to be protected.

[0162] In one example, the pre-charging circuit module 302 is adapted to provide a pre-charging current to make the voltage of the test module reach a first preset voltage; the discharging circuit module 304 is adapted to output current to the test module to increase the voltage of the test module after the voltage of the test module reaches the first preset voltage; and when the voltage of the test module reaches a second preset voltage, the first switch is turned on, so that at least part of the current output by the discharging circuit module flows into the protection circuit.

[0163] In one example, when the first switch is turned on, it can be used to simulate the case of lightning arrester breakdown.

[0164] In one example, the protection circuit can be used to simulate a protection device to be evaluated for protection performance, and the protection performance is adapted to indicate the safety protection capability of the protection device to the test module 301 when the lightning arrester breaks down.

[0165] It is worth noting that the test module 301 used in various embodiments of the present application can include a flexible direct current converter valve in a flexible direct current transmission system, or various modules inside the flexible direct current converter valve, where the flexible direct current converter valve is used in cooperation with a lightning arrester.

[0166] In an alternative embodiment, in combination with Figure 3 and Figure 4 The pre-charging circuit module comprises:

[0167] a first resistor R3 and a second switch QS01 connected in series; and

[0168] A first direct current supply unit, one end of which is electrically connected to the second end of the test module via the series connection of the first resistor R3 and the second switch QS01, and the other end of which is electrically connected to the first end of the test module.

[0169] In one example, the first direct current supply unit comprises a first alternating current power supply AC1 and a first three-phase rectifier bridge circuit 401 adapted to convert alternating current supplied by the first alternating current power supply AC1 into direct current output by the first direct current supply unit.

[0170] In one example, the second switch QS01 can be an isolating knife switch.

[0171] In an alternative embodiment, in combination with Figure 3 and Figure 4 , the discharge circuit module comprises:

[0172] a second direct current supply unit; and

[0173] a first capacitor C1, a first end of which is electrically connected to one end of the second direct current supply unit, a second end of which is electrically connected to the other end of the second direct current supply unit, and a first end of which is electrically connected to the first end of the test module, and a second end of which is electrically connected to the second end of the test module via the series connection of a thyristor, a reactor and a switch.

[0174] In one example, the second direct current supply unit comprises a second alternating current power supply AC2 and a second three-phase rectifier bridge circuit 402 adapted to convert alternating current supplied by the second alternating current power supply AC2 into direct current output by the second direct current supply unit.

[0175] In one example, the first capacitor C1 has a value of 14 mF.

[0176] In an alternative embodiment, in combination with Figure 3 and Figure 4 , the discharge circuit module further comprises:

[0177] a series connection of a second resistor R2 and a third switch K13, wherein a first end of the first capacitor C1 is electrically connected to one end of the second direct current supply unit via the series connection of the second resistor R2 and the third switch K13.

[0178] In one example, the third switch K13 can be an isolating knife switch.

[0179] In this embodiment, the second resistor R2 can function to limit current.

[0180] In an alternative embodiment, in combination with Figure 3 andFigure 4 The discharge circuit module further comprises:

[0181] a first capacitor C1, having a first end and a second end, and being electrically connected between the first end of the first resistor R1 and the second end of the first resistor R1; and

[0182] In one example, the inductor L1 has a value of 2.5 mH.

[0183] In one example, the fourth switch K01 can be an isolation knife switch.

[0184] In an alternative embodiment, in combination with Figure 3 and Figure 4 The discharge circuit module further comprises:

[0185] a third resistor R4, having a first end and a second end, and being electrically connected between the first end of the first capacitor C1 and the second end of the first capacitor C1; and / or,

[0186] at least one first diode D3, each of the first diode D3 having a positive electrode electrically connected to the first end of the first capacitor C1 and a negative electrode electrically connected to the second end of the first capacitor C1.

[0187] In the present embodiment, the third resistor R4 mainly functions as a voltage equalizing resistor.

[0188] In an alternative embodiment, in combination with Figure 3 and Figure 4 The protection circuit comprises at least one inductor L2, and the first switch comprises a second thyristor SCR2.

[0189] In one example, the inductor L2 has a value of 125 μH.

[0190] In an alternative embodiment, in combination with Figure 3 and Figure 4 The test module comprises:

[0191] a second diode D1 and a third diode D2;

[0192] a first IGBT (Insulate-Gate Bipolar Transistor) T1, having a collector electrode electrically connected to the negative electrode of the second diode D1 and an emitter electrode electrically connected to the positive electrode of the second diode D1;

[0193] a second IGBT T2, whose collector is electrically connected to the negative pole of the third diode D2, the emitter of the first IGBT T1 and the positive pole of the second diode D1 respectively, and whose emitter is electrically connected to the positive pole of the third diode D2, wherein the first end of the test module is electrically connected between the emitter of the first IGBT T1 and the collector of the second IGBT T2;

[0194] a fourth resistance R1 and a second capacitor C2 connected in parallel, one end of the fourth resistance R1 and the second capacitor C2 connected in parallel is electrically connected to the collector of the first IGBT T1 and the negative pole of the second diode D1 respectively, the other end of the fourth resistance R1 and the second capacitor C2 connected in parallel is electrically connected to the positive pole of the third diode D2 and the emitter of the second IGBT T2 respectively, and the end of the fourth resistance R1 and the second capacitor C2 connected in parallel and electrically connected to the positive pole of the third diode D2 and the emitter of the second IGBT T2 is used as the first end of the test module.

[0195] The beneficial effects of the above safety protection test device include at least one of the following:

[0196] (1) The embodiment creatively charges the test sub-module with the capacitor group to simulate the situation that the voltage of the sub-module is raised by large current pouring under actual working conditions;

[0197] (2) The embodiment simulates the process that energy is transferred from the sub-module to the surge arrester before and after the breakdown of the surge arrester by using the turn-on and turn-off of the power electronic device;

[0198] (3) The embodiment has a simple circuit and is easy to operate, and whether the safety protection means of the converter valve is effective when the surge arrester breaks down can be determined with very few test resources.

[0199] In one example, referring to Figure 4 It can be considered that the receiving end fault has been locked out, but due to communication delay, the sending end energy is still sent to the receiving end, at this time the direct current of the sending end is continuously rising, which may cause the surge arrester to break down, at this time if the surge arrester breaks down, the reverse recovery of the diode will occur, and the diode reverse recovery is easy to damage under high voltage and large current. In order to avoid this problem, a 25mH reactor (no direction in the figure, actually 25mH is used in engineering, and in order to verify the equivalent of 125uH below, i.e. L2) is connected in series with the surge arrester to limit the di / dt value of the diode (i.e. D1) when the surge arrester breaks down transiently, so as to prevent the diode from being damaged. In order to verify the feasibility of this safety protection scheme, a test is designed to verify it.

[0200] The verification test is carried out according to the following steps:

[0201] (1) In order to avoid the damage of sub-modules caused by accidental breakdown of lightning arresters, the lightning arrester is connected in series with a 25mH reactor to protect the sub-modules. This scheme is equivalent to connecting a 125mH reactor in series with the sub-modules.

[0202] (2) According to the test requirements, the test circuit is built. Figure 4

[0203] (3) According to the test requirements, the test circuit is built. Figure 5 The test circuit is built. dc

[0204] (4) After the test circuit is built, the internal hardware circuit and software system of the test platform are checked, and the high-voltage protection warning area is set.

[0205] (5) The control system (i.e. the controller) sends a closing instruction to QS01 in the pre-charging circuit to pre-charge the test module. When the pre-charging voltage reaches the first preset voltage (e.g. 400V), the charging is stopped. At this time, each board card of the test module is already started and charged.

[0206] (6) The control system sends a closing instruction to K13 in the discharge circuit module to pre-charge C1 in the discharge circuit module. When the pre-charging voltage reaches 6kV, the charging is stopped. At this time, the energy stored in C1 is sufficient to charge the test module to above 4kV.

[0207] (7) After the above charging is completed, K13 and QS01 are disconnected, and K01 is closed.

[0208] (8) After the above operation is completed, the first capacitor C1 charges the test module. The control system sends a conduction command to SCR1. At this time, C1 charges C2 of the test module through L1 and D1, which simulates the process of continuously rising DC voltage of the ultra-high voltage flexible DC converter valve.

[0209] (9) When the voltage of the test module rises to the preset verification voltage (i.e. the second preset voltage) 3900V, the thyristor (i.e. SCR2) simulating the breakdown of the lightning arrester is turned on. The charging current of the test module will at least partially transfer to the thyristor simulating the breakdown of the lightning arrester. At this time, the equivalent working condition is that the charging current transfers from the test module to the lightning arrester when the actual lightning arrester breaks down.

[0210] ​​(10) After the above test steps, wait for the discharge of the device to complete, analyze the test waveform, check the sub-module state, and determine whether the protection means of the reactor can effectively deal with the accidental breakdown condition of the surge arrester by checking whether the electrical stress borne by the diode is within a safe range during the process of charging current transferred from the sub-module to the reactor after the surge arrester is connected in series with the reactor.

[0211] To sum up, the embodiments of the present application have at least the following beneficial effects:

[0212] By using the embodiments of the present application, the test prompt information corresponding to the test data is obtained through data analysis and processing based on the test data measured by the safety protection test device for simulating the breakdown of the flexible DC converter valve surge arrester, the reference test information matched with the test prompt information is determined, and the first test result is obtained through test result analysis and processing based on the reference test information and the test data by using the test result analysis model. The data analysis model is obtained by training sample data, the sample data is generated by the test result analysis model, and the data analysis and processing performed by the data analysis model at least includes the test result analysis and processing performed by the test result analysis model. The test prompt information obtained by the data analysis model can be used as a reference to obtain the reference test information for assisting the test result analysis model in analyzing the test data, thereby improving the accuracy of the test result analysis.

[0213] Through the description of the above embodiments, those skilled in the art can clearly understand that the present application can be implemented by means of software and necessary hardware platforms, and of course, it can also be implemented entirely by hardware. Based on such understanding, all or part of the technical solutions of the present application that contribute to the background art can be embodied in the form of a software product, which can be stored in a storage medium such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in various embodiments or some parts of the embodiments of the present application.

[0214] The above is the preferred embodiment of the present application, and it should be noted that for those skilled in the art, without departing from the principles of the present application, a number of improvements and refinements can be made, which are also considered within the scope of protection of the present application.

Claims

1. A method for safety protection test of breakdown of a flexible HVDC converter valve arrester, characterized in that, The method is suitable for a cloud, a communication connection between the cloud and a safety protection test device is established, the safety protection test device is configured to send measured test data to the cloud in response to the measured test data, and the method comprises: Based on the test data measured by the safety protection test device, data analysis processing is performed through a data analysis model to obtain test prompt information corresponding to the test data, wherein the safety protection test device is used to simulate breakdown of a flexible HVDC valve lightning arrester; Determine the test information matched with the test prompt information; Based on the test information and the test data, test result analysis processing is performed through a test result analysis model to obtain a first test result, wherein the test information is used to prompt the model to compare at least one of the following: differences between a test process indicated by the measured test data and a standard test process, and differences between a test environment indicated by the measured test data and a standard test environment; The data analysis model is obtained through sample data training, the sample data is generated by the test result analysis model, and the data analysis processing performed by the data analysis model at least includes the test result analysis processing performed by the test result analysis model; The test information includes first test information and second test information, the determination of the test information matched with the test prompt information comprises: dividing the test prompt information into a plurality of prompt information blocks, and respectively extracting features of each prompt information block to obtain corresponding first features and second features, wherein the first features and the second features each represent different test information; clustering the first features corresponding to each of the plurality of prompt information blocks to obtain at least one first feature cluster, and clustering the second features corresponding to each of the plurality of prompt information blocks to obtain at least one second feature cluster; determining the first test information based on the at least one first feature cluster, and determining the second test information based on the at least one second feature cluster; The method further comprises: obtaining test description information associated with the test data and input by a user, wherein the test description information is obtained by the user according to a pre-set test description template. The test result analysis model comprises a large model, and the test result analysis processing is performed on the test result analysis model based on the test information and the test data to obtain a first test result, which comprises: determining model prompt information for the large model based on the test information; and inputting the model prompt information and the test data into the large model, so that the large model performs reasoning according to the test data under the guidance of the model prompt information, thereby completing the test result analysis processing and obtaining the first test result. The method further comprises: obtaining test description information associated with the test data and input by a user, wherein the test description information is obtained by the user according to a pre-set test description template. The method further comprises: obtaining test description information associated with the test data and input by a user, wherein the test description information is obtained by the user according to a pre-set test description template. The method further comprises: obtaining test description information associated with the test data and input by a user, wherein the test description information is obtained by the user according to a pre-set test description template. The method further comprises: obtaining test description information associated with the test data and input by a user, wherein the test description information is obtained by the user according to a pre-set test description template. The method further comprises: obtaining test description information associated with the test data and input by a user, wherein the test description information is obtained by the user according to a pre-set test description template. The method further comprises: obtaining test description information associated with the test data and input by a user, wherein the test description information is obtained by the user according to a pre-set test description template. The method further comprises: obtaining test description information associated with the test data and input by a user, wherein the test description information is obtained by the user according to a pre-set test description template. The method further comprises: obtaining test description information associated with the test data and input by a user, wherein the test description information is obtained by the user according to a pre-set test description template. The method further comprises: obtaining test description information associated with the test data and input by a user, wherein the test description information is obtained by the user according to a pre-set test description template. The method further comprises: obtaining test description information associated with the test data and input by a user, wherein the test description information is obtained by the user according to a pre-set test description template. The method further comprises: obtaining test description information associated with the test data and input by a user, wherein the test description information is obtained by the user according to a pre-set test description template. The method further comprises: obtaining test description information associated with the test data and input by a user, wherein the test description information is obtained by the user according to a pre-set test description template. The method further comprises: obtaining test description information associated with the test data and input by a user, wherein the test description information is obtained by the user according to a pre-set test description template. The method further comprises: obtaining test description information associated with the test data and input by a user, wherein the test description information is obtained by the user according to a pre-set test description template. The method further comprises: obtaining test description information associated with the test data and input by a user, wherein the test description information is obtained by the user according to a pre-set test description template. The method further comprises: obtaining test description information associated with the test data and input by a user, wherein the test description information is obtained by the user according to a pre-set test description template. The method further comprises: obtaining test description information associated with the test data and input by a user, wherein the test description information is obtained by the user according to a pre-set test description template. The method further comprises: obtaining test description information associated with the test data and input by a user, wherein the test description information is obtained by the user according to a pre-set test description template. The method further comprises: obtaining test description information associated with the test data and input by a user, wherein the test description information is obtained by the user according to a pre-set test description template. The method further comprises: obtaining test description information associated with the test data and input by a user, wherein the test description information is obtained by the user according to a pre-set test description template. The method further comprises: obtaining test description information associated with the test data and input by a user, wherein the test description information is obtained by the user according to a pre-set test description template. The method further comprises: obtaining test description information associated with the test data and input by a user, wherein the test description information is obtained by the user according to a pre-set test description template. The method further comprises: obtaining test description information associated with the test data and input by a user, wherein the test description information is obtained by the user according to a pre-set test description template. The method further comprises: obtaining test description information associated with the test data and input by a user, wherein the test description information is obtained by the user according to a pre-set test description template. The method further comprises: obtaining test description information associated with the test data and input by a user, wherein the test description information is obtained by the user according to a pre-set test description template. The method further comprises: obtaining test description information associated with the test data and input by a user, wherein the test description information is obtained by the user according to a pre-set test description template. The method further comprises: obtaining test description information associated with the test data and input by a user, wherein the test description information is obtained by the user according to a pre-set test description template. The method further comprises: obtaining test description information associated with the test data and input by a user, wherein the test description information is obtained by the user according to a pre-set test description template. The method further comprises: obtaining test description information associated with the test data and input by a user, wherein the test description information is obtained by the user according to a pre-set test description template. The method further comprises: obtaining test description information associated with the test data and input by a user, wherein the test description information is obtained by the user according to a pre-set test description template. The method further comprises: obtaining test description information associated with the test data and input by a user, wherein the test description information is obtained by the user according to a pre-set test description template. The method further comprises: obtaining test description information associated with the test data and input by a user, wherein the test description information is obtained by the user according to a pre-set test description template. The method further comprises: obtaining test description information associated with the test data and input by a user, wherein the test description information is obtained by the user according to a pre-set test description template. The method further comprises: obtaining test description information associated with the test data and input by a user, wherein the test description information is obtained by the user according to a pre-set test description template. The method further comprises: obtaining test description information associated with the test data and input by a user, wherein the test description information is obtained by the user according to a pre-set test description template. The method further comprises: obtaining test description information associated with the test data and input by a user, wherein the test description information is obtained by the user according to a pre-set test description template. The method further comprises: obtaining test description information associated with the test data and input by a user, wherein the test description information is obtained by the user according to a pre-set test description template. The method further comprises: obtaining test description information associated with the test data and input by a user, wherein the test description information is obtained by the user according to a pre-set test description template. The method further comprises: obtaining test description information associated with the test data and input by a user, wherein the test description information is obtained by the user according to a pre-set test description template. The method further comprises: obtaining test description information associated with the test data and input by a user, wherein the test description information is obtained by the user according to a pre-set test description template. The method further comprises: obtaining test description information associated with the test data and input by a user, wherein the test description information is obtained by the user according to a pre-set test description template. The method further comprises: obtaining test description information associated with the test data and input by a user, wherein the test description information is obtained by the user according to a pre-set test description template. The method further comprises: obtaining test description information associated with the test data and input by a user, wherein the test description information is obtained by the user according to a pre-set test description template. The method further comprises: obtaining test description information associated with the test data and input by a user, wherein the test description information is obtained by the user according to a pre-set test description template. The method further comprises: obtaining test description information associated with the test data and input by a user, wherein the test description information is obtained by the user according to a pre-set test description template. The method further comprises: obtaining test description information associated with the test data and input by a user, wherein the test description information is obtained by the user according to a pre-set test description template. The method further comprises: obtaining test description information associated with the test data and input by a user, wherein the test description information is obtained by the user according to a pre-set test description template. The method further comprises: obtaining test description information associated with the test data and input by a user, wherein the test description information is obtained by the user according to a pre-set test description template. The method further comprises: obtaining test description information associated with the test data and input by a user, wherein the test description information is obtained by the The lightning arrester protection simulation module (303) comprises a first switch and a protection circuit connected in series, two ends of the first switch and the protection circuit connected in series are electrically connected to the first end and the second end of the test module respectively, the protection circuit comprises at least one inductor (L2), and the first switch comprises a second thyristor (SCR2); The discharge loop module (304) is electrically connected to the first end and the second end of the test module respectively; and The controller (305) is in communication connection with the test module, the pre-charging loop module, the lightning arrester protection simulation module and the discharge loop module respectively, and is configured to: in response to a pre-charging instruction, control the pre-charging loop module to output a current to the test module, when it is determined that the voltage of the test module reaches a first preset voltage, control the pre-charging loop module to stop outputting the current; in the case where it is determined that the voltage of the test module reaches the first preset voltage, in response to a discharge instruction, control the discharge loop module to output a current to the test module, when it is determined that the voltage of the test module reaches a second preset voltage, control the first switch to be turned on, so that at least part of the current output by the discharge loop module flows into the protection circuit, wherein the second preset voltage is greater than the first preset voltage; The discharge loop module (304) comprises: A second direct current supply unit; A first capacitor (C1) having a first end electrically connected to one end of the second direct current supply unit and a second end electrically connected to the other end of the second direct current supply unit; and An electric reactance (L1), a first thyristor (SCR1) and a fourth switch (K01) connected in series, wherein the first end of the first capacitor (C1) is electrically connected to the second end of the test module (301) via the electric reactance (L1), the first thyristor (SCR1) and the fourth switch (K01) connected in series; The test module (301) comprises: A second diode (D1) and a third diode (D2); A first insulated gate bipolar transistor (IGBT) (T1) having a collector electrically connected to the negative electrode of the second diode (D1) and an emitter electrically connected to the positive electrode of the second diode (D1); A second IGBT (T2) having a collector electrically connected to the negative electrode of the third diode (D2), the emitter of the first IGBT (T1) and the positive electrode of the second diode (D1) respectively and an emitter electrically connected to the positive electrode of the third diode (D2), wherein the first end of the test module (301) is electrically connected between the emitter of the first IGBT (T1) and the collector of the second IGBT (T2); and A first diode (D1) and a third diode (D2); A fourth resistor (R1) and a second capacitor (C2) are connected in parallel, one end of the parallel connection of the fourth resistor (R1) and the second capacitor (C2) is electrically connected to the collector of the first IGBT (T1) and the negative electrode of the second diode (D1) respectively, the other end of the parallel connection of the fourth resistor (R1) and the second capacitor (C2) is electrically connected to the positive electrode of the third diode (D2) and the emitter of the second IGBT (T2) respectively, and the end of the parallel connection of the fourth resistor (R1) and the second capacitor (C2) electrically connected to the positive electrode of the third diode (D2) and the emitter of the second IGBT (T2) is used as a first end of the test module (301).

2. The safety protection test method according to claim 1, characterized by, The feature extraction on each prompt information block respectively to obtain corresponding first features and second features comprises: The feature extraction on each prompt information block respectively to obtain corresponding first features and second features comprises:

3. The safety protection test method according to claim 1, characterized by, The sample data comprises sample prompt information and sample test results, and the training process of the data analysis model comprises: Obtaining a data analysis model to be trained and sample test data and corresponding test result labels; Inputting the sample test data into the test result analysis model to obtain the sample prompt information and the sample test results output by the test result analysis model; Based on the test result labels, the sample prompt information and the sample test results, model training is performed on the data analysis model to be trained to obtain the data analysis model.

4. The safety protection test method according to any one of claims 1 to 3, characterized in that, The method further comprises: Correlation detection is performed on the test data and the first test result by the data analysis model; Based on the detected correlation information, a second test result is determined.

5. The safety protection test method according to claim 4, characterized by The determination of the second test result based on the detected correlation information comprises: In a case where the correlation information meets a preset correlation condition, the first test result is taken as the second test result; In a case where the correlation information does not meet the preset correlation condition, the correlation information is fed back to the data analysis model, so that the data analysis model updates the test prompt information according to the correlation information; The updated test prompt information is taken as new test prompt information, and the step of determining the test prompt information matching the test prompt information is re-executed until the re-obtained correlation information meets the preset correlation condition.

6. A system for safety protection testing of breakdown of a flexible HVDC converter valve surge arrester, characterized in that The system is suitable for a cloud, and a communication connection is established between the cloud and a safety protection test device, the safety protection test device is configured to send measured test data to the cloud in response to the measured test data, and the system comprises: A data analysis module is configured to perform data analysis and processing on the test data measured by the safety protection test device based on a data analysis model to obtain test prompt information corresponding to the test data, wherein the safety protection test device is used to simulate breakdown of a flexible DC converter valve lightning arrester; A test information determination module is configured to determine test information matching the test prompt information. The first test result obtaining module is configured to perform test result analysis processing on the test data based on the reference test information, by using a test result analysis model, to obtain a first test result, wherein the reference test information is used to prompt the model to compare at least one of the following: a difference between a test procedure indicated by the measured test data and a standard test procedure, and a difference between a test environment indicated by the measured test data and a standard test environment; The data analysis model is trained by sample data, wherein the sample data is generated by the test result analysis model, and the data analysis processing performed by the data analysis model at least includes the test result analysis processing performed by the test result analysis model; The reference test information includes first reference test information and second reference test information, and the determination of the reference test information matched with the test prompt information includes: dividing the test prompt information into a plurality of prompt information blocks, and performing feature extraction on each prompt information block to obtain corresponding first features and second features, wherein the first features and the second features represent different test information; clustering the first features corresponding to the plurality of prompt information blocks to obtain at least one first feature cluster, and clustering the second features corresponding to the plurality of prompt information blocks to obtain at least one second feature cluster; determining the first reference test information based on the at least one first feature cluster, and determining the second reference test information based on the at least one second feature cluster; The determination of the first reference test information based on the at least one first feature cluster and the determination of the second reference test information based on the at least one second feature cluster include: fusing the first features in each first feature cluster to obtain third features corresponding to each first feature cluster, and fusing the second features in each second feature cluster to obtain fourth features corresponding to each second feature cluster; obtaining information matched with each third feature in a preset first standard test database as first standard test information of the corresponding first feature cluster, and obtaining information matched with each fourth feature in a preset second standard test database as second standard test information of the corresponding second feature cluster, wherein the test information represented by the first features includes a test procedure, the test information represented by the second features includes a test environment, the test corresponding to the standard test information stored in the first standard test database is a test completed by a standard safety protection test device according to a standard test procedure, and the test corresponding to the standard test information stored in the second standard test database is a test completed by a standard safety protection test device according to a standard test environment; fusing the first standard test information of each first feature cluster to obtain the first reference test information, and fusing the second standard test information of each second feature cluster to obtain the second reference test information; The test result analysis model includes a large model. The test result analysis model is used to analyze and process test results based on the test information and the test data, and a first test result is obtained. The model prompt information for the large model is determined based on the test information. The model prompt information and the test data are input into the large model. The large model performs reasoning based on the test data under the guidance of the model prompt information, thereby completing the test result analysis processing and obtaining the first test result. The system further includes: A test description information acquisition module is configured to acquire test description information associated with the test data input by a user. The model prompt information for the large model is determined based on the test information, including: The test information is cleaned based on the test description information, and the model prompt information is obtained. The cleaning process is used to clean the information in the test information that is not sufficiently associated with the test data. The safety protection test device includes: A test module (301) includes a flexible DC converter in a flexible DC power transmission system or various modules inside the flexible DC converter. The flexible DC converter is used in cooperation with a lightning arrester. A pre-charging circuit module (302) is electrically connected to the first end and the second end of the test module. A lightning arrester protection simulation module (303) includes a first switch and a protection circuit in series. The two ends of the series connection of the first switch and the protection circuit are electrically connected to the first end and the second end of the test module. The protection circuit includes at least one inductor (L2). The first switch includes a second thyristor (SCR2). A discharge circuit module (304) is electrically connected to the first end and the second end of the test module. A controller (305) is in communication with the test module, the pre-charging circuit module, the lightning arrester protection simulation module, and the discharge circuit module. The controller is configured to control the pre-charging circuit module to output current to the test module in response to a pre-charging instruction. When the voltage of the test module reaches a first preset voltage, the controller controls the pre-charging circuit module to stop outputting current. In the case where the voltage of the test module reaches the first preset voltage, the controller controls the discharge circuit module to output current to the test module in response to a discharge instruction. When the voltage of the test module reaches a second preset voltage, the controller controls the first switch to conduct, so that at least part of the current output by the discharge circuit module flows into the protection circuit. The second preset voltage is greater than the first preset voltage. The discharge circuit module (304) includes: A second DC power supply unit; A first capacitor (C1) has a first end electrically connected to one end of the second DC power supply unit and a second end electrically connected to the other end of the second DC power supply unit; and The first capacitor (C1) is connected to the second end of the test module (301) through the series connection of the inductor (L1), the first thyristor (SCR1) and the fourth switch (K01); The test module (301) comprises: a second diode (D1) and a third diode (D2); a first IGBT (T1) having a collector connected to the negative electrode of the second diode (D1) and an emitter connected to the positive electrode of the second diode (D1); a second IGBT (T2) having a collector connected to the negative electrode of the third diode (D2), the emitter of the first IGBT (T1) and the positive electrode of the second diode (D1), and an emitter connected to the positive electrode of the third diode (D2), wherein the first end of the test module (301) is connected between the emitter of the first IGBT (T1) and the collector of the second IGBT (T2); and a fourth resistor (R1) and a second capacitor (C2) connected in parallel, one end of the parallel connection of the fourth resistor (R1) and the second capacitor (C2) being connected to the collector of the first IGBT (T1) and the negative electrode of the second diode (D1), respectively, the other end of the parallel connection of the fourth resistor (R1) and the second capacitor (C2) being connected to the positive electrode of the third diode (D2) and the emitter of the second IGBT (T2), respectively, and the end of the parallel connection of the fourth resistor (R1) and the second capacitor (C2) being connected to the positive electrode of the third diode (D2) and the emitter of the second IGBT (T2), which is used as the first end of the test module (301).

Images