A method and device for environmental testing of microgrid

Abstract

The present invention provides a method and device for environmental testing of a microgrid, wherein the method comprises: obtaining a microgrid system parameter set when multiple microgrid systems are running, assigning corresponding data labels with corresponding intermediate parameters according to whether the microgrid system parameters are those before a fault occurs, and obtaining a microgrid system fault prediction model based on data set training, and judging whether a target microgrid system is faulty through a neural network model. The beneficial effects of the present invention are: the prediction of whether a microgrid system is faulty is realized, and the prediction of whether a microgrid system is faulty can be improved before the microgrid system fails, thereby reducing the probability of a microgrid system failure.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence, and in particular to a method and device for environmental testing of a microgrid. Background Art

[0002] A microgrid is a small power system consisting of multiple distributed energy resources (such as solar energy, wind energy, energy storage, etc.) and users (such as households, businesses, communities, etc.). These distributed energy resources can be interconnected to achieve coordinated production, distribution and utilization of energy through intelligent control and management. Microgrids are usually able to operate autonomously, and can also be connected to traditional power grids to achieve two-way energy flow.

[0003] Microgrid systems are usually composed of multiple distributed energy resources and users, involving many parameters and variables, and the testing process is relatively complicated. Environmental testing needs to consider the changes in various parameters under different environmental conditions, involving a large amount of data, and the existing technology does not have a technical solution to predict failures in microgrid systems. Summary of the invention

[0004] The main purpose of the present invention is to provide a microgrid environmental testing method and device, aiming to solve the problem that there is currently no technical solution for predicting failures in a microgrid system.

[0005] The present invention provides a microgrid environmental testing method, comprising:

[0006] Acquire a microgrid system parameter set when multiple microgrid systems are running; wherein the microgrid system parameter set includes t groups of microgrid system parameters, and at least one group of microgrid system parameter sets is a microgrid system parameter before a fault occurs;

[0007] According to the preset formula W e+j =W k+j +E×[W e+j-1 -W k+j-1 ]±B to obtain the change parameter, where E represents the change parameter, W h represents the hth group of microgrid system parameters in the microgrid system parameter set, and B represents a preset error range;

[0008] Calculate the intermediate parameter set for each group of microgrid system parameters

[0009] B i =[(W t，t-1 ), (W t，t-2 ),...,(W t，g )...,(W t，1 )}, where t represents the tth time point, B i represents the intermediate parameter set corresponding to the i-th microgrid system, (W t，g) represents the rate of change of microgrid system parameters between the t-th time point and the g-th time point, t, g, i are positive integers, and t>g;

[0010] Determine whether the microgrid system parameters corresponding to each intermediate parameter set are the microgrid system parameters before the fault occurs;

[0011] According to the judgment result, the intermediate parameter set is assigned a corresponding microgrid system data label to obtain a target parameter set; the microgrid system data label is faulty or not faulty;

[0012] Inputting each group of target parameter sets into a preset neural network model to obtain a microgrid system fault prediction model;

[0013] The microgrid system parameter set of the target microgrid system at t time points before the current time point is obtained through the preset sensors to form a data set to be tested;

[0014] Calculating an intermediate data set of the data set to be tested; wherein the method of calculating the intermediate data set is the same as the method of calculating the intermediate parameter set;

[0015] Inputting the intermediate data set into the microgrid system fault prediction model to obtain the target data label of the target microgrid system;

[0016] It is determined whether the target microgrid system has a fault based on the target data tag.

[0017] Furthermore, the step of inputting each group of the target parameter sets into a preset neural network model to obtain a microgrid system fault prediction model includes:

[0018] A specified number of microgrid system parameter sets are selected as a first data set; one of the microgrid system parameter sets includes a microgrid system parameter and a corresponding microgrid system data label; the first data set is divided into a second data set and a third data set according to a preset ratio;

[0019] Inputting the second data set into a preset neural network model, using the corresponding microgrid system parameters as the input of the preset neural network model, and using the corresponding microgrid system data labels as the output for training, thereby obtaining a temporary microgrid system fault detection model;

[0020] Using the third data set to verify the temporary microgrid system fault detection model to obtain a verification result;

[0021] If the verification result is that the verification is passed, the temporary microgrid system fault detection model is recorded as a microgrid system fault prediction model.

[0022] Further, after the step of determining whether the target microgrid system has a fault based on the target data tag, the method further includes:

[0023] If the judgment result based on the target data label is that the target microgrid system has a fault, then the similarity between the test data set and the microgrid system parameter set whose microgrid system data label is a fault is calculated according to a preset similarity calculation method;

[0024] Select the target microgrid system parameter set according to the similarity;

[0025] Obtaining a fault type of the target microgrid system parameter set;

[0026] A processing method for the target microgrid system is adopted according to the fault type.

[0027] Further, after the step of determining whether the target microgrid system has a fault based on the target data tag, the method further includes:

[0028] If the judgment result based on the target data tag is that the target microgrid system has a fault, the preset circuit system supplies power to the user;

[0029] Acquire the system parameter set at t time points after the replacement through the preset sensor to form a fourth data set;

[0030] Calculating an intermediate fourth data set of the fourth data set; wherein the method of calculating the intermediate fourth data set is the same as the method of calculating the intermediate parameter set;

[0031] Inputting the intermediate fourth data set into the microgrid system fault prediction model to obtain a target data label;

[0032] If the target data tag is no fault, it is determined that the target microgrid system is faulty.

[0033] Furthermore, the step of obtaining a microgrid system parameter set when multiple microgrid systems are running includes:

[0034] Determine the product type and usage type of the target microgrid system to be tested;

[0035] Find multiple other microgrid systems that are similar or close to each other according to the product type and usage type;

[0036] Obtaining a database where the other microgrid system parameters are located;

[0037] The microgrid system parameter set is obtained through the preset crawler script.

[0038] The present invention also provides an environmental testing device for a microgrid, comprising:

[0039] A first acquisition module is used to acquire a microgrid system parameter set when multiple microgrid systems are running; wherein the microgrid system parameter set includes t groups of microgrid system parameters, and at least one group of microgrid system parameter sets is a microgrid system parameter before a fault occurs;

[0040] The second acquisition module is used to obtain the e+j =W k+j +E×[W e+j-1 -W k+j-1 ]±B to obtain the change parameter, where E represents the change parameter, W h represents the hth group of microgrid system parameters in the microgrid system parameter set, and B represents a preset error range;

[0041] The first calculation module is used to calculate the intermediate parameter set B of each group of microgrid system parameters i =[(W t，t-1 ), (W t，t-2 ),...,(W t，g )...,(W t，1 )}, where t represents the tth time point, B i represents the intermediate parameter set corresponding to the i-th microgrid system, (W t，g ) represents the rate of change of microgrid system parameters between the t-th time point and the g-th time point, t, g, i are positive integers, and t>g;

[0042] A first judgment module is used to judge whether the microgrid system parameters corresponding to each intermediate parameter set are the microgrid system parameters before the fault occurs;

[0043] An assignment module is used to assign a corresponding microgrid system data label to the intermediate parameter set according to the judgment result to obtain a target parameter set; the microgrid system data label is fault or no fault;

[0044] A first input module, used for inputting each group of said target parameter sets into a preset neural network model to obtain a microgrid system fault prediction model;

[0045] The third acquisition module is used to obtain the microgrid system parameter set of the target microgrid system at t time points before the current time point through a preset sensor to form a data set to be tested;

[0046] A second calculation module, used for calculating an intermediate data set of the data set to be tested; wherein the method of calculating the intermediate data set is the same as the method of calculating the intermediate parameter set;

[0047] A second input module is used to input the intermediate data set into the microgrid system fault prediction model to obtain a target data label of the target microgrid system;

[0048] The second judgment module is used to judge whether the target microgrid system has a fault based on the target data tag.

[0049] Furthermore, the first input module includes:

[0050] A microgrid system parameter set selection submodule is used to select a specified number of multiple groups of microgrid system parameter sets as a first data set; one of the microgrid system parameter sets includes a microgrid system parameter and a corresponding microgrid system data label; the first data set is divided into a second data set and a third data set according to a preset ratio;

[0051] A second data set input submodule, used to input the second data set into a preset neural network model, use the corresponding microgrid system parameters as the input of the preset neural network model, and use the corresponding microgrid system data labels as the output for training, so as to obtain a temporary microgrid system fault detection model;

[0052] A verification submodule, used to verify the temporary microgrid system fault detection model using the third data set to obtain a verification result;

[0053] The marking submodule is used to record the temporary microgrid system fault detection model as a microgrid system fault prediction model if the verification result is verification passed.

[0054] Furthermore, the microgrid environmental testing device further includes:

[0055] A similarity calculation module, for calculating the similarity between the test data set and the microgrid system parameter set whose microgrid system data label is a fault, according to a preset similarity calculation method, if the judgment result based on the target data label is that the target microgrid system has a fault;

[0056] A target microgrid system parameter set selection module is used to select a target microgrid system parameter set according to the similarity;

[0057] A fault type acquisition module, used to acquire the fault type of the target microgrid system parameter set;

[0058] The processing mode adopting module is used to adopt a processing mode for the target microgrid system according to the fault type.

[0059] Furthermore, the microgrid environmental testing device further includes:

[0060] A replacement module, configured to supply power to the user by a preset circuit system if the result of the determination based on the target data tag is that the target microgrid system has a fault;

[0061] A fourth data set acquisition module, used to acquire a system parameter set at t time points after the replacement through a preset sensor to form a fourth data set;

[0062] an intermediate fourth data set calculation module, used for calculating an intermediate fourth data set of the fourth data set; wherein the method of calculating the intermediate fourth data set is the same as the method of calculating the intermediate parameter set;

[0063] An intermediate fourth data set input module, used for inputting the intermediate fourth data set into the microgrid system fault prediction model to obtain a target data label;

[0064] The target microgrid system fault determination module is used to determine that the target microgrid system has a fault if the target data tag is not faulty.

[0065] Furthermore, the first acquisition module includes:

[0066] A type determination submodule is used to determine the product type and usage type of the target microgrid system to be tested;

[0067] Other microgrid system search submodule, used to search for multiple other similar or close microgrid systems according to the product type and usage type;

[0068] A database acquisition submodule, used to acquire the database where the other microgrid system parameters are located;

[0069] The microgrid system parameter set acquisition submodule is used to obtain the microgrid system parameter set through a preset crawler script.

[0070] The beneficial effects of the present invention are as follows: by acquiring a microgrid system parameter set when multiple microgrid systems are running, using corresponding intermediate parameters and assigning corresponding data labels according to whether they are microgrid system parameters before a fault occurs, and obtaining a microgrid system fault prediction model based on data set training, a neural network model is used to determine whether a target microgrid system is faulty, thereby realizing the prediction of whether a microgrid system is faulty, improving the ability to predict whether a microgrid system has a fault before the microgrid system fails, and thereby reducing the probability of a microgrid system failure. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] Figure 1 It is a flow chart of a microgrid environmental testing method according to an embodiment of the present invention;

[0072] Figure 2 It is a schematic block diagram of the structure of an environmental testing device for a microgrid according to an embodiment of the present invention;

[0073] Figure 3 A schematic block diagram of the structure of a computer device according to an embodiment of the present application.

[0074] 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

[0075] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0076] It should be noted that all directional indications in the embodiments of the present invention (such as up, down, left, right, front, back, etc.) are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly. The connection can be a direct connection or an indirect connection.

[0077] The term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there may be three relationships. For example, A and B can represent three situations: A exists alone, A and B exist at the same time, and B exists alone.

[0078] In addition, in the present invention, descriptions such as "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0079] Reference Figure 1 The present invention provides a microgrid environmental testing method, comprising:

[0080] S1: Acquire a microgrid system parameter set when multiple microgrid systems are running; wherein the microgrid system parameter set includes t groups of microgrid system parameters, and at least one group of microgrid system parameter sets is a microgrid system parameter before a fault occurs;

[0081] S2: According to the preset formula W e+j =W k+j +E×[W e+j-1 -W k+j-1 ]±B to obtain the change parameter, where E represents the change parameter, W hrepresents the hth group of microgrid system parameters in the microgrid system parameter set, and B represents a preset error range;

[0082] S3: Calculate the intermediate parameter set of each group of microgrid system parameters

[0083] B i ={(W t，t-1 ), (W t，t-2 ),...,(W t，g )...,(W t，1 )}, where t represents the tth time point, B i represents the intermediate parameter set corresponding to the i-th microgrid system,

[0084] (W t，g ) represents the rate of change of microgrid system parameters between the t-th time point and the g-th time point, t, g, i are positive integers, and t>g;

[0085] S4: Determine whether the microgrid system parameters corresponding to each intermediate parameter set are the microgrid system parameters before the fault occurs;

[0086] S5: assigning a corresponding microgrid system data label to the intermediate parameter set according to the judgment result to obtain a target parameter set; the microgrid system data label is fault or no fault;

[0087] S6: inputting each group of the target parameter sets into a preset neural network model to obtain a microgrid system fault prediction model;

[0088] S7: Obtain a microgrid system parameter set of the target microgrid system at t time points before the current time point through a preset sensor to form a data set to be tested;

[0089] S8: Calculate an intermediate data set of the data set to be tested; wherein the method of calculating the intermediate data set is the same as the method of calculating the intermediate parameter set;

[0090] S9: inputting the intermediate data set into the microgrid system fault prediction model to obtain the target data label of the target microgrid system;

[0091] S10: Determine whether the target microgrid system has a fault based on the target data tag.

[0092] As described in the above step S1, a microgrid system parameter set is obtained when multiple microgrid systems are running. The microgrid system parameter set when the microgrid system is running is the microgrid system parameter collected by the preset sensor. The preset sensor may include a voltage sensor, a temperature sensor, and a current sensor, etc., to measure the parameters of the power system composed of each distributed energy resource and the user in the microgrid system. Specifically, the voltage of each distributed energy resource can be measured, wherein the microgrid system parameter set includes t groups of microgrid system parameters, and at least one group of microgrid system parameter sets is the microgrid system parameters before the failure occurs. At the same time, the microgrid system parameter set should also include some normal operating microgrid system parameters, so as to facilitate the subsequent assignment of corresponding microgrid system data labels. It should be noted that this application is to predict whether the microgrid system will fail, that is, the current microgrid system operation can still proceed normally, that is, it is impossible to judge the microgrid system failure based on some current data. In addition, the microgrid system parameter set selected here should preferably be of the same type as the target microgrid system to be measured, so as to improve the accuracy of detection.

[0093] As described in step S2 above, according to the preset formula W e+j =W k+j +E×[W e+j-1 -W k+j-1 ]±B to obtain the change parameter, where E represents the change parameter, W h represents the hth group of microgrid system parameters in the microgrid system parameter set, and B represents the preset error range. For the current data, it is impossible to make a direct judgment, so its change parameter can be calculated by the formula, that is, judging from the relationship between the data, and further judging whether the microgrid system has a fault according to the change parameter. In addition, it should be noted that a group of microgrid system parameters may include multiple parameters, so it can perform weighted summation of multiple groups of parameters to obtain the corresponding value for calculation, that is, W h is the value of the weighted sum, of course, W h It can also be a vector corresponding to multiple parameters.

[0094] As described in step S3 above, calculate the intermediate parameter set B of each group of microgrid system parameters i ={(W t，t-1 ), (W t，t-2 ),...,(W t，g )...,(W t，1 )}, where t represents the tth time point, B i represents the intermediate parameter set corresponding to the i-th microgrid system, (W t，z) represents the rate of change of microgrid system parameters between the tth time point and the gth time point, t, g, i are positive integers, and t>g; the intermediate parameter set is composed of time and change parameters, and the rate of change of its change parameters and time can be intuitively seen. Specifically, In this way, the change rate of the microgrid system parameters can be obtained to form an intermediate parameter set.

[0095] As described in the above steps S4-S5, it is determined whether the microgrid system parameters corresponding to each intermediate parameter set are the microgrid system parameters before the fault occurs, and the corresponding microgrid system data labels are assigned to the intermediate parameter sets according to the determination results to obtain the target parameter set; the microgrid system data labels are fault or no fault; specifically, the microgrid system data labels can be set based on whether the data are the microgrid system parameters before the fault occurs, or can be manually determined and assigned corresponding microgrid system data labels to facilitate subsequent training.

[0096] As described in step S6 above, each group of the target parameter sets is input into a preset neural network model to obtain a microgrid system fault prediction model. Specifically, the neural network model can be trained by a supervised training method, and the training method can be implemented by KNN (k-NearestNeighbor, neighbor algorithm) technology.

[0097] As described in the above steps S7-S10, the microgrid system parameter set of the target microgrid system at t time points before the current time point is obtained through the preset sensor to form a data set to be tested; the intermediate data set of the data set to be tested is calculated; wherein, the method of calculating the intermediate data set is the same as the method of calculating the intermediate parameter set; the intermediate data set is input into the microgrid system fault prediction model to obtain the target data label of the target microgrid system; based on the target data label, it is determined whether the target microgrid system has a fault. Wherein, the data parameters obtained by the preset sensor are the same type of parameters as the aforementioned microgrid system parameters, and the intermediate data set of the data set to be tested is calculated; wherein, the method of calculating the intermediate data set is the same as the method of calculating the intermediate parameter set, which will not be repeated here, and then it is input into the microgrid system fault prediction model to determine whether the microgrid system has a fault. Thereby, the prediction of whether the microgrid system has a fault is realized, and the prediction of whether the microgrid system has a fault before the microgrid system fails is improved, thereby reducing the probability of microgrid system failure.

[0098] In one embodiment, the step S6 of inputting each group of the target parameter sets into a preset neural network model to obtain a microgrid system fault prediction model includes:

[0099] S601: Select a specified number of multiple groups of microgrid system parameter sets as a first data set; one of the microgrid system parameter sets includes a microgrid system parameter and a corresponding microgrid system data label; divide the first data set into a second data set and a third data set according to a preset ratio;

[0100] S602: inputting the second data set into a preset neural network model, using the corresponding microgrid system parameters as input of the preset neural network model, and using the corresponding microgrid system data labels as output for training, thereby obtaining a temporary microgrid system fault detection model;

[0101] S603: Verifying the temporary microgrid system fault detection model using the third data set to obtain a verification result;

[0102] S604: If the verification result is verification passed, the temporary microgrid system fault detection model is recorded as a microgrid system fault prediction model.

[0103] As described in the above steps S601-S604, the judgment accuracy of the trained microgrid system fault prediction model on the target microgrid system is improved. That is, it is divided into a second data set and a third data set, the model is trained by the second data set, and the model is tested by the third data set, so that the model has higher analysis accuracy and the detection accuracy of the microgrid system fault prediction model is improved.

[0104] In one embodiment, after the step S10 of determining whether the target microgrid system has a fault based on the target data tag, the method further includes:

[0105] S1101: If the result of the determination based on the target data tag is that the target microgrid system has a fault, then, according to a preset similarity calculation method, the similarity between the test data set and a microgrid system parameter set whose microgrid system data tag is a fault is calculated;

[0106] S1102: Selecting a target microgrid system parameter set according to the similarity;

[0107] S1103: Obtaining the fault type of the target microgrid system parameter set;

[0108] S1104: Adopt a processing method for the target microgrid system according to the fault type.

[0109] As described in the above steps S1101-S1104, the fault type is judged, so that the corresponding processing method can be quickly selected. Specifically, if the judgment result based on the target data label is that the target microgrid system has a fault, then according to the similarity calculation method, the similarity between the test data set and the microgrid system parameter set with the microgrid system data label as a fault is calculated, wherein the similarity calculation method can be any one of the calculation methods such as calculating the Tanimoto coefficient, Cosine similarity, Pearson correlation coefficient, and Euclidean distance. According to the similarity size, a microgrid system parameter set with the largest similarity is selected as the target microgrid system parameter set, and the fault type of the target microgrid system parameter set is obtained; the processing method for the target microgrid system is adopted according to the fault type. The specific processing method is not limited and can be determined by relevant personnel.

[0110] In one embodiment, after the step S10 of determining whether the target microgrid system has a fault based on the target data tag, the method further includes:

[0111] S1111: If the result of the determination based on the target data tag is that the target microgrid system has a fault, the preset circuit system supplies power to the user;

[0112] S1112: Acquire a system parameter set at t time points after the replacement through a preset sensor to form a fourth data set;

[0113] S1113: Calculate an intermediate fourth data set of the fourth data set; wherein the method of calculating the intermediate fourth data set is the same as the method of calculating the intermediate parameter set;

[0114] S1114: inputting the intermediate fourth data set into the microgrid system fault prediction model to obtain a target data label;

[0115] S1115: If the target data tag is not faulty, it is determined that the target microgrid system is faulty.

[0116] As described in the above steps S1111-S1115, since the judgment result of the target data tag is that there is a fault in the target microgrid system, it may also be caused by other reasons. However, in the microgrid system, the most common faults are often microgrid system faults rather than user problems. Therefore, this embodiment needs to replace the microgrid system, re-test the data set, and then obtain the corresponding target data tag according to the above detection method. If the target data tag is not fault-free, it is determined that the target microgrid system is faulty. If the target data tag is a fault, it is necessary to redetermine the reason for the data change and send the changed data to the corresponding staff for re-manual analysis.

[0117] In one embodiment, the step S1 of acquiring a microgrid system parameter set when multiple microgrid systems are running includes:

[0118] S101: Determine the product type and usage type of the target microgrid system to be tested;

[0119] S102: Finding a plurality of other microgrid systems that are similar or close to each other according to the product type and usage type;

[0120] S103: Acquire the database where the other microgrid system parameters are located;

[0121] S104: Obtain a microgrid system parameter set through a preset crawler script.

[0122] As described in the above steps S101-S104, the acquisition of the microgrid system parameter set is realized. In this embodiment, a preferred method for acquiring microgrid system parameters is provided, that is, according to the product type and usage type of the target microgrid system, multiple other microgrid systems that are similar or close are found, and then the database where the other microgrid system parameters are located is used to obtain the microgrid system parameter set through a preset crawler script. The crawler script can specifically be a Sqoop script, which is a tool for transferring data between Hadoop and a database. Therefore, enough data can be obtained through the script for model training.

[0123] Reference Figure 2 The present invention also provides an environmental testing device for a microgrid, comprising:

[0124] The first acquisition module 10 is used to acquire a microgrid system parameter set when multiple microgrid systems are running; wherein the microgrid system parameter set includes t groups of microgrid system parameters, and at least one group of microgrid system parameter sets is a microgrid system parameter before a fault occurs;

[0125] The second acquisition module 20 is used to obtain the e+j =W k+j +E×W e+j-1 -W k+j-1 ]±B to obtain the change parameter, where E represents the change parameter, W h represents the hth group of microgrid system parameters in the microgrid system parameter set, and B represents a preset error range;

[0126] The first calculation module 30 is used to calculate the intermediate parameter set B of each group of microgrid system parameters i ={(W t，t-1 ), (W t，t-2 ),...,(W t，g )...,(W t，1 )}, where t represents the tth time point, Bi represents the intermediate parameter set corresponding to the i-th microgrid system, (W t，g ) represents the rate of change of microgrid system parameters between the t-th time point and the g-th time point, t, g, i are positive integers, and t>g;

[0127] A first judgment module 40 is used to judge whether the microgrid system parameters corresponding to each intermediate parameter set are the microgrid system parameters before the fault occurs;

[0128] An assignment module 50 is used to assign a corresponding microgrid system data label to the intermediate parameter set according to the judgment result to obtain a target parameter set; the microgrid system data label is fault or no fault;

[0129] A first input module 60, for inputting each group of the target parameter sets into a preset neural network model to obtain a microgrid system fault prediction model;

[0130] The third acquisition module 70 is used to obtain the microgrid system parameter set of the target microgrid system at t time points before the current time point through a preset sensor to form a data set to be tested;

[0131] A second calculation module 80 is used to calculate an intermediate data set of the data set to be tested; wherein the method of calculating the intermediate data set is the same as the method of calculating the intermediate parameter set;

[0132] A second input module 90 is used to input the intermediate data set into the microgrid system fault prediction model to obtain a target data label of the target microgrid system;

[0133] The second judgment module 100 is used to judge whether the target microgrid system has a fault based on the target data tag.

[0134] In one embodiment, the first input module 60 comprises:

[0135] A microgrid system parameter set selection submodule is used to select a specified number of multiple groups of microgrid system parameter sets as a first data set; one of the microgrid system parameter sets includes a microgrid system parameter and a corresponding microgrid system data label; the first data set is divided into a second data set and a third data set according to a preset ratio;

[0136] A second data set input submodule, used to input the second data set into a preset neural network model, use the corresponding microgrid system parameters as the input of the preset neural network model, and use the corresponding microgrid system data labels as the output for training, so as to obtain a temporary microgrid system fault detection model;

[0137] A verification submodule, used to verify the temporary microgrid system fault detection model using the third data set to obtain a verification result;

[0138] The marking submodule is used to record the temporary microgrid system fault detection model as a microgrid system fault prediction model if the verification result is verification passed.

[0139] In one embodiment, the microgrid environmental testing device further includes:

[0140] A similarity calculation module, for calculating the similarity between the test data set and the microgrid system parameter set whose microgrid system data label is a fault, according to a preset similarity calculation method, if the judgment result based on the target data label is that the target microgrid system has a fault;

[0141] A target microgrid system parameter set selection module is used to select a target microgrid system parameter set according to the similarity;

[0142] A fault type acquisition module, used to acquire the fault type of the target microgrid system parameter set;

[0143] The processing mode adopting module is used to adopt a processing mode for the target microgrid system according to the fault type.

[0144] In one embodiment, the microgrid environmental testing device further includes:

[0145] A replacement module, configured to supply power to the user by a preset circuit system if the result of the determination based on the target data tag is that the target microgrid system has a fault;

[0146] A fourth data set acquisition module, used to acquire a system parameter set at t time points after the replacement through a preset sensor to form a fourth data set;

[0147] an intermediate fourth data set calculation module, used for calculating an intermediate fourth data set of the fourth data set; wherein the method of calculating the intermediate fourth data set is the same as the method of calculating the intermediate parameter set;

[0148] An intermediate fourth data set input module, used for inputting the intermediate fourth data set into the microgrid system fault prediction model to obtain a target data label;

[0149] The target microgrid system fault determination module is used to determine that the target microgrid system has a fault if the target data tag is not faulty.

[0150] In one embodiment, the first acquisition module 10 includes:

[0151] A type determination submodule is used to determine the product type and usage type of the target microgrid system to be tested;

[0152] Other microgrid system search submodule, used to search for multiple other similar or close microgrid systems according to the product type and usage type;

[0153] A database acquisition submodule, used to acquire the database where the other microgrid system parameters are located;

[0154] The microgrid system parameter set acquisition submodule is used to obtain the microgrid system parameter set through a preset crawler script.

[0155] The beneficial effects of the present invention are as follows: by acquiring a microgrid system parameter set when multiple microgrid systems are running, using corresponding intermediate parameters and assigning corresponding data labels according to whether they are microgrid system parameters before a fault occurs, and obtaining a microgrid system fault prediction model based on data set training, a neural network model is used to determine whether a target microgrid system is faulty, thereby realizing the prediction of whether a microgrid system is faulty, improving the ability to predict whether a microgrid system has a fault before the microgrid system fails, and thereby reducing the probability of a microgrid system failure.

[0156] Reference Figure 3 In an embodiment of the present application, a computer device is also provided. The computer device may be a server, and its internal structure may be as follows: Figure 3 As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor designed by the computer is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store various microgrid system parameters, etc. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the environmental testing method of the microgrid described in any of the above embodiments can be implemented.

[0157] Those skilled in the art will understand that Figure 3 The structure shown in is merely a block diagram of a portion of the structure related to the present application solution and does not constitute a limitation on the computer device to which the present application solution is applied.

[0158] An embodiment of the present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the environmental testing method for the microgrid described in any of the above embodiments can be implemented.

[0159] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media provided in this application and used in the embodiments can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0160] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the existence of other identical elements in the process, device, article or method including the element.

[0161] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present invention shall be included in the scope of the claims of the present invention.

Claims

1. A microgrid environmental testing method, characterized in that: include: Acquire a microgrid system parameter set when multiple microgrid systems are running; wherein the microgrid system parameter set includes t groups of microgrid system parameters, and at least one group of microgrid system parameter sets is a microgrid system parameter before a fault occurs; According to the preset formula W e+j =W k+j +E×[W e+j-1 -W k+j-1 ]±B to obtain the change parameter, where E represents the change parameter, W h represents the hth group of microgrid system parameters in the microgrid system parameter set, and B represents a preset error range; Calculate the intermediate parameter set B of each group of microgrid system parameters i = { (W t，t-1 ), (W t，t-2 ),...,(W t，g )...,(W t，1 ) } , where t represents the tth time point, B i represents the intermediate parameter set corresponding to the i-th microgrid system, (W t，g ) represents the rate of change of microgrid system parameters between the t-th time point and the g-th time point, t, g, i are positive integers, and t>g; Determine whether the microgrid system parameters corresponding to each intermediate parameter set are the microgrid system parameters before the fault occurs; According to the judgment result, the intermediate parameter set is assigned a corresponding microgrid system data label to obtain a target parameter set; the microgrid system data label is faulty or not faulty; Inputting each group of target parameter sets into a preset neural network model to obtain a microgrid system fault prediction model; The microgrid system parameter set of the target microgrid system at t time points before the current time point is obtained through the preset sensors to form a data set to be tested; Calculating an intermediate data set of the data set to be tested; wherein the method of calculating the intermediate data set is the same as the method of calculating the intermediate parameter set; Inputting the intermediate data set into the microgrid system fault prediction model to obtain the target data label of the target microgrid system; Determining whether the target microgrid system has a fault based on the target data tag; The step of inputting each group of the target parameter sets into a preset neural network model to obtain a microgrid system fault prediction model comprises: A specified number of microgrid system parameter sets are selected as the first data set; wherein one of the microgrid system parameter sets includes microgrid system parameters and corresponding microgrid system data tags; Dividing the first data set into a second data set and a third data set according to a preset ratio; Inputting the second data set into a preset neural network model, using the corresponding microgrid system parameters as the input of the preset neural network model, and using the corresponding microgrid system data labels as the output for training, thereby obtaining a temporary microgrid system fault detection model; Using the third data set to verify the temporary microgrid system fault detection model to obtain a verification result; If the verification result is that the verification is passed, the temporary microgrid system fault detection model is recorded as a microgrid system fault prediction model.

2. The microgrid environmental testing method according to claim 1, characterized in that: After the step of determining whether the target microgrid system has a fault based on the target data tag, the method further includes: If the judgment result based on the target data label is that the target microgrid system has a fault, then the similarity between the test data set and the microgrid system parameter set whose microgrid system data label is a fault is calculated according to a preset similarity calculation method; Select the target microgrid system parameter set according to the similarity; Obtaining a fault type of the target microgrid system parameter set; A processing method for the target microgrid system is adopted according to the fault type.

3. The microgrid environmental testing method according to claim 1, characterized in that: After the step of determining whether the target microgrid system has a fault based on the target data tag, the method further includes: If the result of the determination based on the target data tag is that the target microgrid system has a fault, the preset circuit system supplies power to the user; Acquire the system parameter set at t time points after the replacement through the preset sensor to form a fourth data set; Calculating an intermediate fourth data set of the fourth data set; wherein the method of calculating the intermediate fourth data set is the same as the method of calculating the intermediate parameter set; Inputting the intermediate fourth data set into the microgrid system fault prediction model to obtain a target data label; If the target data tag is no fault, it is determined that the target microgrid system is faulty.

4. The microgrid environmental testing method according to claim 1, characterized in that: The step of obtaining a microgrid system parameter set when multiple microgrid systems are running includes: Determine the product type and usage type of the target microgrid system to be tested; Find multiple other microgrid systems that are similar or close to each other according to the product type and usage type; Obtaining a database where the other microgrid system parameters are located; The microgrid system parameter set is obtained through the preset crawler script.

5. A microgrid environmental testing device, characterized in that: include: A first acquisition module is used to acquire a microgrid system parameter set when multiple microgrid systems are running; wherein the microgrid system parameter set includes t groups of microgrid system parameters, and at least one group of microgrid system parameter sets is a microgrid system parameter before a fault occurs; The second acquisition module is used to obtain the e+j =W k+j +E× [ W e+j-1 -W k+j-1 ] ±B obtains the variation parameter, where E represents the variation parameter, W h represents the hth group of microgrid system parameters in the microgrid system parameter set, and B represents a preset error range; The first calculation module is used to calculate the intermediate parameter set B of each group of microgrid system parameters i ={(W t，t-1 ), (W t，t-2 ),...,(W t，g )...,(W t，1 ) } , where t represents the tth time point, B i represents the intermediate parameter set corresponding to the i-th microgrid system, (W t，g ) represents the rate of change of microgrid system parameters between the t-th time point and the g-th time point, t, g, i are positive integers, and t>g; A first judgment module is used to judge whether the microgrid system parameters corresponding to each intermediate parameter set are the microgrid system parameters before the fault occurs; An assignment module is used to assign a corresponding microgrid system data label to the intermediate parameter set according to the judgment result to obtain a target parameter set; the microgrid system data label is fault or no fault; A first input module, used for inputting each group of said target parameter sets into a preset neural network model to obtain a microgrid system fault prediction model; The third acquisition module is used to obtain the microgrid system parameter set of the target microgrid system at t time points before the current time point through a preset sensor to form a data set to be tested; A second calculation module, used for calculating an intermediate data set of the data set to be tested; wherein the method of calculating the intermediate data set is the same as the method of calculating the intermediate parameter set; A second input module is used to input the intermediate data set into the microgrid system fault prediction model to obtain a target data label of the target microgrid system; A second judgment module, used for judging whether the target microgrid system has a fault based on the target data tag; The first input module comprises: A microgrid system parameter set selection submodule is used to select a specified number of multiple groups of microgrid system parameter sets as a first data set; one of the microgrid system parameter sets includes a microgrid system parameter and a corresponding microgrid system data label; the first data set is divided into a second data set and a third data set according to a preset ratio; A second data set input submodule, used to input the second data set into a preset neural network model, use the corresponding microgrid system parameters as the input of the preset neural network model, and use the corresponding microgrid system data labels as the output for training, so as to obtain a temporary microgrid system fault detection model; A verification submodule, used to verify the temporary microgrid system fault detection model using the third data set to obtain a verification result; The marking submodule is used to record the temporary microgrid system fault detection model as a microgrid system fault prediction model if the verification result is verification passed.

6. The microgrid environmental testing device according to claim 5, characterized in that: The environmental testing device of the microgrid further includes: A similarity calculation module, for calculating the similarity between the test data set and the microgrid system parameter set whose microgrid system data label is a fault, according to a preset similarity calculation method, if the judgment result based on the target data label is that the target microgrid system has a fault; A target microgrid system parameter set selection module is used to select a target microgrid system parameter set according to the similarity; A fault type acquisition module, used to acquire the fault type of the target microgrid system parameter set; The processing mode adopting module is used to adopt a processing mode for the target microgrid system according to the fault type.

7. The microgrid environmental testing device according to claim 5, characterized in that: The environmental testing device of the microgrid further includes: A replacement module, configured to supply power to the user by a preset circuit system if the result of the determination based on the target data tag is that the target microgrid system has a fault; A fourth data set acquisition module, used to acquire a system parameter set at t time points after the replacement through a preset sensor to form a fourth data set; an intermediate fourth data set calculation module, used for calculating an intermediate fourth data set of the fourth data set; wherein the method of calculating the intermediate fourth data set is the same as the method of calculating the intermediate parameter set; An intermediate fourth data set input module, used for inputting the intermediate fourth data set into the microgrid system fault prediction model to obtain a target data label; The target microgrid system fault determination module is used to determine that the target microgrid system has a fault if the target data tag is not faulty.

8. The microgrid environmental testing device according to claim 5, characterized in that: The first acquisition module includes: A type determination submodule is used to determine the product type and usage type of the target microgrid system to be tested; Other microgrid system search submodule, used to search for multiple other similar or close microgrid systems according to the product type and usage type; A database acquisition submodule, used to acquire the database where the other microgrid system parameters are located; The microgrid system parameter set acquisition submodule is used to obtain the microgrid system parameter set through a preset crawler script.

Images