Fault analysis method and device for multi-machine system of wind-storage integrated grid-connected converter

Abstract

The present invention relates to the field of new energy technology, and discloses a wind-storage integrated grid-type converter multi-machine system fault analysis method and device, the wind-storage integrated grid-type converter multi-machine system fault analysis method comprises: obtaining the current fault condition data of the wind-storage integrated grid-type converter multi-machine system; using the K nearest neighbor model to perform fault analysis on the current fault condition data to obtain the current fault condition type; using the K-means clustering algorithm to perform cluster analysis on the current fault condition data to obtain the fault association information between the current fault condition types; adjusting the parameters in the wind-storage integrated grid-type converter multi-machine system based on the current fault condition type and the fault association information. The present invention can solve the problems of low accuracy and low efficiency of fault diagnosis.

Description

Technical Field

[0001] The present invention relates to the field of new energy technology, and in particular to a method and device for analyzing faults in a multi-machine system of a wind-storage integrated grid-type converter. Background Art

[0002] With the change of the world energy pattern, photovoltaic power generation and wind power generation have become the hot spots for in-depth research and vigorous development in various countries. my country has a vast territory and rich wind and solar resources. A large number of wind farms and photovoltaic power stations have been built, and wind and solar converters integrate the functions of wind power converters and photovoltaic converters.

[0003] The fault analysis and control optimization methods currently used in power systems, especially wind-solar converter multi-machine wind power generation systems, include a variety of algorithms, such as genetic algorithms, simulated annealing algorithms, support vector machines, field signal detection and diagnosis, etc.

[0004] Among them, genetic algorithms and simulated annealing algorithms have problems such as difficulty in determining the objective function, long diagnosis time, and the possibility of losing the optimal solution during the optimization process, resulting in low accuracy of fault diagnosis. The selection of kernel function parameters in the fault diagnosis method based on support vector machine has a great influence on the diagnosis results, and the fault analysis results are inaccurate. Field signal detection diagnosis has a small number of sensors, limited diagnostic capabilities under complex working conditions, and low efficiency of fault diagnosis. Summary of the invention

[0005] In view of this, the present invention provides a fault analysis method and device for a multi-machine system of a wind-storage integrated grid-type converter to solve the problems of low accuracy and low efficiency of fault diagnosis.

[0006] In the first aspect, the present invention provides a method for fault analysis of a multi-machine system of a wind-storage integrated grid-type converter, and the method for fault analysis of a multi-machine system of a wind-storage integrated grid-type converter includes: obtaining current fault condition data of the wind-storage integrated grid-type converter multi-machine system; performing fault analysis on the current fault condition data using a K-nearest neighbor model to obtain the current fault condition type; performing cluster analysis on the current fault condition data using a K-means clustering algorithm to obtain fault correlation information between the current fault condition types; and adjusting parameters in the wind-storage integrated grid-type converter multi-machine system based on the current fault condition type and the fault correlation information.

[0007] In this implementation, the K nearest neighbor model is used to perform fault analysis on the current fault condition data, which can intelligently identify and predict the types of faults that may occur in the system, realizing the automation and intelligence of fault analysis; on this basis, the K-means clustering algorithm is used to further analyze the correlation between different faults, and to explore the common causes of faults or specific causes under specific conditions. The integrated use of the K nearest neighbor and K-means clustering algorithms has exerted a synergistic effect, improved the overall efficiency of fault analysis and processing, and realized an integrated solution from fault identification, cause analysis to control optimization, solving the problems of low accuracy and low efficiency of fault diagnosis, and can improve the stability and reliability of the wind-storage integrated grid-type converter multi-machine system.

[0008] In an optional embodiment, before using the K nearest neighbor model to perform fault analysis on the current fault condition data to obtain the current fault condition type, the method also includes: obtaining historical fault condition data and corresponding historical fault condition types; dividing the historical fault condition data and the corresponding historical fault condition types into a training set and a test set; using the training set to train the K nearest neighbor model; using the trained K nearest neighbor model to read the historical fault condition data in the test set, and outputting the test fault condition type; when the test fault condition type and the historical fault condition type in the test set are different, adjusting the parameters of the K nearest neighbor model based on the difference information between the test fault condition type and the historical fault condition type in the test set, and training the K nearest neighbor model again; when the test fault condition type and the historical fault condition type in the test set are the same, outputting the trained K nearest neighbor model.

[0009] In this implementation, the K nearest neighbor model is trained using historical fault data and further tested using the historical fault data. In-depth analysis of the historical fault data can more accurately identify the cause of the fault and improve the accuracy of fault diagnosis.

[0010] In an optional implementation, a K-nearest neighbor model is used to perform fault analysis on current fault condition data to obtain the current fault condition type, including: calculating the Euclidean distance between the current fault condition data and each group of historical fault condition data; sorting the historical fault condition data based on the Euclidean distance to determine a preset number of historical fault condition data with the smallest Euclidean distance; obtaining a preset number of historical fault condition types corresponding to a preset number of historical fault condition data; and taking the fault condition type with the largest number among the preset number of historical fault condition types as the current fault condition type.

[0011] In an optional embodiment, after obtaining the current fault condition type, it also includes: operating the wind-storage integrated grid-type converter multi-machine system model based on the current fault condition type to obtain detected fault condition data, and the wind-storage integrated grid-type converter multi-machine system model is used to simulate the operation of the wind-storage integrated grid-type converter multi-machine system; when the detected fault condition data and the current fault condition data are different, the parameters of the K nearest neighbor model are adjusted based on the difference information between the detected fault condition data and the current fault condition data, and the K nearest neighbor model is trained again.

[0012] In an optional embodiment, a K-means clustering algorithm is used to perform cluster analysis on current fault condition data to obtain fault correlation information between current fault condition types, including: operating a wind-storage integrated grid-type converter multi-machine system model based on the current fault condition type to obtain verification fault condition data, the wind-storage integrated grid-type converter multi-machine system model is used to simulate the operation of the wind-storage integrated grid-type converter multi-machine system; when the verification fault condition data is the same as the current fault condition data, a K-means clustering algorithm is used to perform cluster analysis on the current fault condition data to determine current fault condition data with similar characteristics; based on the current fault condition data with similar characteristics, fault correlation information between corresponding current fault condition types is obtained.

[0013] In this implementation, the k-means clustering algorithm conducts in-depth analysis and research on the fault condition data in the wind-storage integrated grid-type converter multi-machine system, clusters data with similar characteristics together, analyzes the intrinsic connections between the current fault condition types, and can improve the efficiency of fault handling.

[0014] In an optional embodiment, after adjusting the parameters in the wind-storage integrated grid-type converter multi-machine system based on the current fault condition type and fault-related information, it also includes: running the wind-storage integrated grid-type converter multi-machine system model based on the adjusted parameters to obtain adjusted condition data; comparing the adjusted condition data with the non-fault condition data to determine the stability of the wind-storage integrated grid-type converter multi-machine system.

[0015] In an optional embodiment, the steps of constructing a wind-storage integrated grid-type inverter multi-machine system model include: obtaining operating parameters of the wind-storage integrated grid-type inverter multi-machine system, the operating parameters including node information and line parameters; using the Pandapower function package to construct a wind-storage integrated grid-type inverter multi-machine system model based on the operating parameters.

[0016] In this implementation, by combining the Pandapower data package for system modeling with data analysis of the K nearest neighbor and K means clustering algorithms, a complete set of fault analysis and collaborative control optimization processes is formed, which improves the accuracy of fault diagnosis and the level of intelligent system control.

[0017] In an optional embodiment, the wind-storage integrated grid-type inverter multi-machine system fault analysis method also includes: running the wind-storage integrated grid-type inverter multi-machine system model based on historical fault condition types to obtain simulated fault condition data; adjusting the parameters of the wind-storage integrated grid-type inverter multi-machine system model based on the difference information between the simulated fault condition data and the historical fault condition data.

[0018] In a second aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the fault analysis method for a multi-machine system of a wind-storage integrated grid-type converter according to the above-mentioned first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0019] In a third aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the method for fault analysis of a multi-machine system of a wind-storage integrated grid-type converter according to the first aspect or any corresponding embodiment thereof.

[0020] In a fourth aspect, the present invention provides a computer program product, comprising computer instructions for causing a computer to execute the method for analyzing a multi-machine system of a wind-storage integrated grid-type converter according to the first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0022] Figure 1 This is a flow chart of a method for analyzing a multi-machine system fault of a wind-storage integrated grid-type converter according to an embodiment of the present invention;

[0023] Figure 2 is a schematic diagram of a KNN model according to an embodiment of the present invention;

[0024] Figure 3is a flow chart of another method for analyzing faults of a multi-machine system of a wind-storage integrated grid-type converter according to an embodiment of the present invention;

[0025] Figure 4 is a structural block diagram of a fault analysis device for a multi-machine system of a wind-storage integrated grid-type converter according to an embodiment of the present invention;

[0026] Figure 5 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0027] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are 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 those skilled in the art without creative work are within the scope of protection of the present invention.

[0028] According to an embodiment of the present invention, an embodiment of a fault analysis method for a multi-machine system of a wind-storage integrated grid-type inverter is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0029] In this embodiment, a method for analyzing faults in a multi-machine system of a wind-storage integrated grid-connected converter is provided. Figure 1 FIG. 1 is a flow chart of a method for analyzing a fault of a multi-machine system of a wind-storage integrated grid-type converter according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0030] Step S101, obtaining current fault condition data of a wind-storage integrated grid-connected converter multi-machine system.

[0031] The wind-storage integrated grid-type converter multi-machine system will generate different fault condition data during normal operation and fault operation. Among them, the fault condition data is the operating data of the wind-storage integrated grid-type converter multi-machine system when it is operating according to the operating parameters of each node device. The operating data includes the voltage amplitude and phase angle of the node device. However, due to the mutual influence of each power-saving device, the fault condition data cannot directly indicate the corresponding fault condition.

[0032] Specifically, when a fault occurs in the wind-storage integrated grid-type converter multi-machine system, the current fault condition data generated during the operation of the wind-storage integrated grid-type converter multi-machine system is obtained. The current fault condition data is used to represent the operation status of the wind-storage integrated grid-type converter multi-machine system. Among them, the current fault condition data is multiple.

[0033] Step S102: Use the K nearest neighbor model to perform fault analysis on the current fault condition data to obtain the current fault condition type.

[0034] The current fault condition data is input into the trained KNN (k-nearest neighbor) model, the current fault condition data is analyzed and identified, the specific condition that causes the wind-storage integrated grid-type converter multi-machine system fault is determined, and the current fault condition type is output. Among them, when the wind-storage integrated grid-type converter multi-machine system fails, there is at least one type of fault. In one implementation, different current fault condition data correspond to different current fault condition types.

[0035] Specifically, see Figure 2 , Figure 2 is a schematic diagram of a KNN model according to an embodiment of the present invention. The KNN model includes a function module, an initialization module, a fit module and a prediction module, wherein the prediction module is the core module of the KNN model.

[0036] Among them, the function module builds a fault condition identification accuracy verification function. The verification function is used to test the analysis results of the KNN model on the fault condition of the wind-storage integrated grid-connected converter multi-machine system.

[0037] The initialization module is used to initialize the k value before performing fault condition analysis.

[0038] Among them, the fit module is used to store the historical fault condition data and historical fault condition types of the wind-storage integrated grid-type converter multi-machine system under fault conditions.

[0039] Among them, the prediction module is used to read the current fault condition data of the wind-storage integrated grid-type converter multi-machine system, analyze it, and output the current fault condition type.

[0040] Step S103, using the K-means clustering algorithm to perform cluster analysis on the current fault condition data, and obtain fault association information between the current fault condition types.

[0041] Among them, the K-means clustering algorithm is a K-means algorithm, which is an iterative clustering analysis algorithm.

[0042] The K-means algorithm is used to perform cluster analysis on the current fault condition data, calculate the data point distances between the current fault condition data, determine the current fault condition data with similar characteristics, and cluster the current fault condition data with similar characteristics together to form different clusters.

[0043] Understandably, some fault modes may form tight clusters in the clustering, indicating that the current fault condition data have similar fault characteristics and possible fault causes.

[0044] According to the relationship between the current fault condition data, the fault correlation information between the current fault condition types is analyzed.

[0045] Step S104: adjusting parameters in the wind-storage integrated grid-connected converter multi-machine system based on the current fault condition type and fault association information.

[0046] According to the determined current fault condition type and fault correlation information, the common cause of the fault of the wind-storage integrated grid-type converter multi-machine system or the specific cause under specific conditions is determined, the corresponding node device is found in the wind-storage integrated grid-type converter multi-machine system, and the parameters of the node device are adjusted to obtain the adjusted wind-storage integrated grid-type converter multi-machine system to eliminate the fault of the wind-storage integrated grid-type converter multi-machine system.

[0047] The fault analysis method for the wind-storage integrated grid-type converter multi-machine system provided in this embodiment uses the K nearest neighbor model to perform fault analysis on the current fault condition data, which can intelligently identify and predict the types of faults that may occur in the system, and realize the automation and intelligence of fault analysis; on this basis, the K-means clustering algorithm is used to further analyze the correlation between different faults, and to explore the common causes of the faults or specific causes under specific conditions. The integrated use of the K nearest neighbor and K-means clustering algorithms has exerted a synergistic effect, improved the overall efficiency of fault analysis and processing, and realized an integrated solution from fault identification, cause analysis to control optimization, solving the problems of low accuracy and low efficiency of fault diagnosis, and can improve the stability and reliability of the wind-storage integrated grid-type converter multi-machine system.

[0048] In this embodiment, a method for analyzing faults in a multi-machine system of a wind-storage integrated grid-connected converter is provided. Figure 3 FIG. 1 is a flow chart of another method for analyzing a fault of a multi-machine system of a wind-storage integrated grid-type converter according to an embodiment of the present invention. Figure 3 As shown, the process includes the following steps:

[0049] Step S301, building a wind-storage integrated grid-connected converter multi-machine system model.

[0050] The operating parameters of the wind-storage integrated grid-type converter multi-machine system are obtained, and the operating parameters include node information and line parameters. Specifically, the operating parameters may include node information, wind turbine power generation, load consumption, line parameters, etc.

[0051] Using the Pandapower function package, a wind-storage integrated grid-connected converter multi-machine system model is constructed based on operating parameters. The wind-storage integrated grid-connected converter multi-machine system model is used to simulate the operation of the wind-storage integrated grid-connected converter multi-machine system.

[0052] Step S302, obtaining historical fault condition data and corresponding historical fault condition types.

[0053] Among them, the historical fault condition data includes the historical voltage amplitude and historical phase angle of the system nodes.

[0054] Step S303, running the wind-storage integrated grid-connected converter multi-machine system model based on the historical fault condition types to obtain simulated fault condition data.

[0055] Based on the historical fault condition types, the wind-storage integrated grid-type converter multi-machine system model is operated to obtain the simulated fault condition data of the system nodes, where the simulated fault condition data includes the simulated voltage amplitude and simulated phase angle of the system nodes.

[0056] Step S304, determining whether the simulated fault condition data is the same as the historical fault condition data.

[0057] The simulated fault condition data is compared with the historical fault condition data to determine the correctness of the wind-storage integrated grid-type converter multi-machine system model. When the simulated fault condition data is the same as the historical fault condition data, it means that the constructed wind-storage integrated grid-type converter multi-machine system model can accurately simulate the formal wind-storage integrated grid-type converter multi-machine system. When the simulated fault condition data is different from the historical fault condition data, it means that the constructed wind-storage integrated grid-type converter multi-machine system model is a correct model and cannot accurately simulate the formal wind-storage integrated grid-type converter multi-machine system.

[0058] Specifically, when the simulated fault condition data is the same as the historical fault condition data, step S305 is executed; when the simulated fault condition data is different from the historical fault condition data, the parameters of the wind-storage integrated grid-type converter multi-machine system model are adjusted based on the difference information between the simulated fault condition data and the historical fault condition data, and then the process returns to step S302.

[0059] Step S305, build a K nearest neighbor model and determine the training set and test set.

[0060] The historical fault condition data and the corresponding historical fault condition types are obtained, and the historical fault condition data and the corresponding historical fault condition types are divided into a training set and a test set.

[0061] The training set and test set contain two sets of data respectively, one set of historical fault condition data, including the voltage amplitude, phase angle and other data of the system nodes, and the other set includes the corresponding historical fault condition types.

[0062] Step S306: train the K nearest neighbor model using the training set.

[0063] The initial KNN model is used to read the historical fault condition data in the training set, obtain the voltage amplitude, phase angle and other data of the system nodes, make a judgment on the fault conditions experienced by the historical fault condition data, and obtain the training fault condition types.

[0064] The training fault condition types are compared with the historical fault condition types corresponding to the historical fault condition data in the training set, and the parameters of the initial KNN model are adjusted to obtain the trained KNN model.

[0065] Step S307, using the test set to test the K nearest neighbor model, and outputting the type of test fault condition.

[0066] The trained KNN model is used to read the historical fault condition data in the test set and output the test fault condition type.

[0067] Step S308, determining whether the test fault condition type is the same as the historical fault condition type in the test set.

[0068] The test fault condition type is compared with the historical fault condition type corresponding to the historical fault condition data in the test set to verify the accuracy of the KNN model. When the test fault condition type is the same as the historical fault condition type in the test set, it means that the detection result of the KNN model is accurate; when the test fault condition type is different from the historical fault condition type in the test set, it means that the detection result of the KNN model is inaccurate.

[0069] Specifically, when the test fault condition type and the historical fault condition type in the test set are the same, execute step S309; ​​when the test fault condition type and the historical fault condition type in the test set are different, adjust the parameters of the KNN model based on the difference information between the test fault condition type and the historical fault condition type in the test set, and return to step S306 to train the KNN model again.

[0070] Among them, the K nearest neighbor model is trained using historical fault data, and is further tested using historical fault data. In-depth analysis of historical fault data can more accurately identify the cause of the fault and improve the accuracy of fault diagnosis.

[0071] Step S309: Use the K nearest neighbor model to perform fault analysis on the current fault condition data to obtain the current fault condition type.

[0072] Specifically, the Euclidean distance between the current fault condition data and each group of historical fault condition data is calculated; the historical fault condition data is sorted based on the Euclidean distance, and a preset number of historical fault condition data with the smallest Euclidean distance is determined. A preset number of historical fault condition types corresponding to the preset number of historical fault condition data are obtained; and the fault condition type with the largest number among the preset number of historical fault condition types is taken as the current fault condition type.

[0073] In one implementation, the Euclidean distance between the current fault condition data and each set of historical fault condition data is calculated, and the Euclidean distance is sorted from small to large using the argsort function of NumPy, and the historical fault condition data corresponding to the first k Euclidean distances are taken, and the historical fault condition types corresponding to the k historical fault condition data are obtained. The Counter class in the collection module is used to count the historical fault condition types with the most occurrences, and the name and number of occurrences of the historical fault condition types with the most occurrences are obtained through the most_common method, and the historical fault condition type is output as the current fault condition type.

[0074] Step S310, running the wind-storage integrated grid-connected converter multi-machine system model based on the current fault condition type to obtain detection fault condition data.

[0075] Based on the current fault condition type, the wind-storage integrated grid-type converter multi-machine system model is operated to obtain the detection fault condition data of the system nodes, where the detection fault condition data includes the detection voltage amplitude and detection phase angle of the system nodes.

[0076] Step S311, determining whether the detected fault condition data is the same as the current fault condition data.

[0077] Compare the detected fault condition data with the current fault condition data to determine the correctness of the KNN model detection result. When the detected fault condition data is the same as the current fault condition data, it means that the KNN model detection result is highly correct and can make correct fault analysis and diagnosis. When the detected fault condition data is different from the current fault condition data, it means that the KNN model detection result is low in correctness and cannot make correct fault analysis and diagnosis.

[0078] Specifically, when the detected fault condition data is the same as the current fault condition data, step S312 is executed; when the detected fault condition data is different from the current fault condition data, the parameters of the KNN model are adjusted based on the difference information between the detected fault condition data and the current fault condition data, and return to step S306 to train the KNN model again.

[0079] Step S312: perform cluster analysis on the current fault condition data using the K-means algorithm to obtain fault correlation information between the current fault condition types.

[0080] Based on the current fault condition types, the wind-storage integrated grid-type converter multi-machine system model is operated to obtain the verified fault condition data. When the verified fault condition data is the same as the current fault condition data, the K-means algorithm is used to perform cluster analysis on the current fault condition data to determine the current fault condition data with similar characteristics; based on the current fault condition data with similar characteristics, the fault correlation information between the corresponding current fault condition types is obtained.

[0081] Understandably, some fault data may form tight clusters in the clustering, indicating that they have similar fault characteristics and possible fault causes. For example, the data points of two fault conditions are clustered together, indicating that the two fault conditions may be caused by a chain reaction, and the control algorithm can be further optimized based on this point.

[0082] A K-means algorithm is built to perform cluster analysis on fault data to obtain the correlation between different faults, and to find out the common causes of the faults or specific causes under specific conditions.

[0083] Among them, the k-means clustering algorithm has conducted in-depth analysis and research on the fault condition data in the wind-storage integrated grid-type converter multi-machine system, clustered data with similar characteristics, analyzed the internal connection between the current fault condition types, and improved the efficiency of fault handling. The integrated use of KNN and K-means algorithms has played a synergistic effect, improved the overall efficiency of fault analysis and handling, and realized an integrated solution from fault identification, cause analysis to control optimization.

[0084] Step S213, adjusting the parameters of the wind-storage integrated grid-connected converter multi-machine system based on the current fault condition type and fault association information.

[0085] According to the determined current fault condition type and fault correlation information, the common cause of the fault of the wind-storage integrated grid-type converter multi-machine system or the specific cause under specific conditions is determined, the corresponding node device is found in the wind-storage integrated grid-type converter multi-machine system, and the parameters of the node device are adjusted to obtain the adjusted wind-storage integrated grid-type converter multi-machine system to eliminate the fault of the wind-storage integrated grid-type converter multi-machine system.

[0086] Step S214, running the wind-storage integrated grid-type converter multi-machine system model based on the adjusted parameters to obtain adjusted operating condition data, comparing the adjusted operating condition data with the non-fault operating condition data, and judging the stability of the wind-storage integrated grid-type converter multi-machine system.

[0087] The wind-storage integrated grid-type converter multi-machine system model is run based on the adjusted parameters to obtain adjusted operating condition data, which is used to characterize the operating conditions of the wind-storage integrated grid-type converter multi-machine system after the fault is eliminated.

[0088] The adjustment operating condition data is compared with the non-fault operating condition data. When the adjustment operating condition data is the same as the non-fault operating condition data, it means that the stability of the current wind-storage integrated grid-type converter multi-machine system is high and there is no equipment failure; when the adjustment operating condition data is different from the non-fault operating condition data, it means that the stability of the current wind-storage integrated grid-type converter multi-machine system is low and there may be equipment failure.

[0089] This application combines Pandapower data packets to perform system modeling and data analysis of K-nearest neighbor and K-means clustering algorithms to form a complete set of fault analysis and collaborative control optimization processes, which improves the accuracy of fault diagnosis and the intelligent level of system control. At the same time, through cluster analysis of historical fault data, the present invention can predict possible future faults and take corresponding preventive measures, thereby reducing the probability of faults and improving the stability and reliability of the system.

[0090] The collaborative control strategy proposed in the present invention has good adaptability and can cope with various complex working conditions and changeable operating environments in the wind-storage integrated grid-type converter multi-machine system, improving the flexibility and robustness of the system. The accurate fault prediction and diagnosis capabilities make system maintenance more targeted, avoiding unnecessary maintenance work, thereby reducing the maintenance cost of the system. The method of the present invention can be extended to other new energy power systems, promote further research and innovation in related technical fields, integrate advanced data analysis technology, and promote the development of new energy power systems in the direction of intelligence and automation. It provides data-driven decision support for system operation and maintenance, enhancing the scientificity and rationality of decision-making.

[0091] In this embodiment, a wind-storage integrated grid-type converter multi-machine system fault analysis device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and will not be repeated hereafter. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation in hardware, or a combination of software and hardware, is also possible and conceivable.

[0092] This embodiment provides a fault analysis device for a multi-machine system of a wind-storage integrated grid-type converter, such as Figure 4 As shown, including:

[0093] The acquisition module 401 is used to obtain the current fault condition data of the wind-storage integrated grid-connected converter multi-machine system.

[0094] The first analysis module 402 uses a K-nearest neighbor model to perform fault analysis on the current fault condition data to obtain the current fault condition type.

[0095] The second analysis module 403 performs cluster analysis on the current fault condition data using a K-means clustering algorithm to obtain fault association information between the current fault condition types.

[0096] The adjustment module 404 adjusts the parameters in the wind-storage integrated grid-connected converter multi-machine system based on the current fault condition type and fault association information.

[0097] The further functional description of each of the above modules is the same as that of the above corresponding embodiments and will not be repeated here.

[0098] The wind-storage integrated grid-type inverter multi-machine system fault analysis device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0099] The embodiment of the present invention also provides a computer device having the above Figure 4 The fault analysis device for a multi-machine system of a wind-storage integrated grid-type converter is shown.

[0100] See also Figure 5 , Figure 5 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 5As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 5 A processor 10 is taken as an example.

[0101] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0102] The memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0103] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0104] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0105] The computer device also includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30 and the output device 40 may be connected via a bus or other means. Figure 5 The example of connecting through bus is taken in the following.

[0106] The input device 30 can receive input digital or character information, and generate key signal input related to the user settings and function control of the computer device, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator bar, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The above-mentioned display device includes but is not limited to a liquid crystal display, a light emitting diode, a display and a plasma display. In some optional embodiments, the display device may be a touch screen.

[0107] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0108] A part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the existence of the computer program instruction in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc., and accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium accessible to the computer.

[0109] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A method for fault analysis of a multi-machine system of a wind-storage integrated grid-connected converter, characterized in that: The method comprises: Obtain current fault condition data of wind-storage integrated grid-connected converter multi-machine system; Performing fault analysis on the current fault condition data using a K-nearest neighbor model to obtain the type of the current fault condition; Based on the current fault condition type, a wind-storage integrated grid-type converter multi-machine system model is operated to obtain verification fault condition data, wherein the wind-storage integrated grid-type converter multi-machine system model is used to simulate the operation of the wind-storage integrated grid-type converter multi-machine system; When the verification fault condition data is the same as the current fault condition data, cluster analysis is performed on the current fault condition data using a K-means clustering algorithm to determine the current fault condition data having similar characteristics; Based on the current fault condition data having similar characteristics, acquiring fault association information between corresponding current fault condition types; Determine the cause of the fault of the wind-storage integrated grid-type converter multi-machine system based on the current fault condition type and the fault association information, and adjust the parameters in the wind-storage integrated grid-type converter multi-machine system; Wherein, the adjusting of the parameters in the wind-storage integrated grid-type converter multi-machine system comprises: finding the corresponding node device in the wind-storage integrated grid-type converter multi-machine system, and adjusting the parameters of the node device; Based on the adjusted parameters, the wind-storage integrated grid-type converter multi-machine system model is operated to obtain adjustment operating condition data; The adjusted operating condition data is compared with the non-fault operating condition data to determine the stability of the wind-storage integrated grid-type converter multi-machine system.

2. The method for fault analysis of a multi-machine system of a wind-storage integrated grid-connected converter according to claim 1 is characterized in that: Before performing fault analysis on the current fault condition data using the K nearest neighbor model to obtain the current fault condition type, the following step is also included: Obtain historical fault condition data and corresponding historical fault condition types; Dividing the historical fault condition data and the corresponding historical fault condition types into a training set and a test set; Using the training set to train the K nearest neighbor model; Using the trained K nearest neighbor model to read the historical fault condition data in the test set, and output the test fault condition type; When the test fault condition type is different from the historical fault condition type in the test set, adjusting the parameters of the K nearest neighbor model based on the difference information between the test fault condition type and the historical fault condition type in the test set, and training the K nearest neighbor model again; When the test fault condition type is the same as the historical fault condition type in the test set, the trained K nearest neighbor model is output.

3. The fault analysis method for a multi-machine system of a wind-storage integrated grid-connected converter according to claim 2 is characterized in that: The K nearest neighbor model is used to perform fault analysis on the current fault condition data to obtain the current fault condition types including: Calculating the Euclidean distance between the current fault condition data and each group of historical fault condition data; Sorting the historical fault operating condition data based on the Euclidean distance, and determining a preset number of the historical fault operating condition data with the smallest Euclidean distance; Acquire a preset number of historical fault operating condition types corresponding to a preset number of historical fault operating condition data; The fault operating condition type with the largest number among the preset number of historical fault operating condition types is used as the current fault operating condition type.

4. The method for fault analysis of a multi-machine system of a wind-storage integrated grid-type converter according to claim 2 is characterized in that: After obtaining the current fault condition type, the following steps are further included: Based on the current fault condition type, the wind-storage integrated grid-type converter multi-machine system model is operated to obtain detection fault condition data; When the detected fault condition data and the current fault condition data are different, the parameters of the K nearest neighbor model are adjusted based on the difference information between the detected fault condition data and the current fault condition data, and the K nearest neighbor model is trained again.

5. The method for fault analysis of a multi-machine system of a wind-storage integrated grid-connected converter according to claim 4 is characterized in that: The steps of constructing a wind-storage integrated grid-connected converter multi-machine system model include: Obtaining operating parameters of the wind-storage integrated grid-type converter multi-machine system, wherein the operating parameters include node information and line parameters; The Pandapower function package is used to construct the wind-storage integrated grid-connected converter multi-machine system model based on the operating parameters.

6. The method for fault analysis of a multi-machine system of a wind-storage integrated grid-connected converter according to claim 5 is characterized in that: The method further comprises: Based on the historical fault condition types, the wind-storage integrated grid-connected converter multi-machine system model is run to obtain simulated fault condition data; The parameters of the wind-storage integrated grid-type converter multi-machine system model are adjusted based on the difference information between the simulated fault condition data and the historical fault condition data.

7. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the fault analysis method for a multi-machine system of a wind-storage integrated grid-type converter according to any one of claims 1 to 6 by executing the computer instructions.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the method for analyzing a multi-machine system fault of a wind-storage integrated grid-type converter according to any one of claims 1 to 6.

9. A computer program product, characterized in that It includes computer instructions, which are used to enable a computer to execute the fault analysis method of a multi-machine system of a wind-storage integrated grid-type converter as described in any one of claims 1 to 6.

Images