A method, device, equipment and medium for monitoring the operating status of a lightning arrester of a wind turbine generator set

Abstract

The present invention discloses a method, device, equipment, and medium for monitoring the operating status of a lightning arrester of a wind turbine generator set, comprising: obtaining historical current operating parameters and historical fault types of the lightning arrester of the wind turbine generator set, and matching the historical current operating parameters and historical fault types according to a time sequence; obtaining a lightning arrester fault diagnosis model for the wind turbine generator set; adjusting the detection period of the lightning arrester of the target wind turbine generator set according to the real-time current operating parameters and predicted fault type of the lightning arrester of the target wind turbine generator set, and performing patrol inspections on the lightning arrester of the target wind turbine generator set according to the adjusted detection period. The present invention belongs to the field of lightning arrester monitoring for wind turbine generator sets. The present invention can flexibly adjust the detection period according to the operating status of the lightning arrester of the wind turbine generator set.

Description

Technical Field

[0001] The present invention relates to the field of wind turbine generator system lightning arrester monitoring, and in particular to a method, device, equipment and medium for monitoring the operating status of a wind turbine generator system lightning arrester. Background Art

[0002] A wind turbine's lightning arrester (also known as a surge protector or overvoltage protector) is a critical device used to protect electrical equipment from transient high voltages, such as voltage surges caused by lightning or other forms of power system disturbances. Its primary function is to limit transient overvoltages and divert surge currents, thereby protecting sensitive equipment connected to it.

[0003] Currently, traditional power equipment inspections typically follow a fixed cycle (such as monthly or quarterly), but these cycles are unable to adapt to the variability of the equipment's actual operating conditions. Therefore, determining a more reasonable inspection cycle for wind turbine lightning arresters is an urgent issue. Summary of the Invention

[0004] The present invention solves the technical problem in the prior art that the fixed inspection cycle cannot adapt to changes in the actual operating state of the lightning arrester by providing a method, device, equipment and medium for monitoring the operating state of the lightning arrester of a wind turbine generator set, and achieves the technical effect of reasonably determining the inspection cycle of the lightning arrester of the wind turbine generator set.

[0005] In a first aspect, the present invention provides a method for monitoring the operating status of a power lightning arrester of a wind turbine generator, comprising:

[0006] Obtain historical current operating parameters and historical fault types of the wind turbine generator's power lightning arrester, and match the historical current operating parameters and historical fault types in time sequence. The current operating parameters include the number of lightning arrester operations, resistive current, and capacitive current. The fault types include internal environmental faults, external lightning faults, and operating load faults.

[0007] The neural network to be trained is trained using historical current operating parameters and historical fault types to obtain a wind turbine generator system lightning arrester fault diagnosis model. The wind turbine generator system lightning arrester fault diagnosis model is used to predict the wind turbine generator system lightning arrester fault type.

[0008] According to the real-time current operating parameters of the power lightning arrester of the target wind turbine generator set and the predicted fault type, the detection period of the power lightning arrester of the target wind turbine generator set is adjusted, and the power lightning arrester of the target wind turbine generator set is inspected according to the adjusted detection period.

[0009] Furthermore, according to the real-time current operating parameters of the power arrester of the target wind turbine generator and the predicted fault type, the detection period of the power arrester of the target wind turbine generator is adjusted, including:

[0010] Obtain the real-time current operating parameters of the lightning arrester of the target wind turbine and input them into the lightning arrester fault diagnosis model of the wind turbine to obtain the corresponding predicted fault type;

[0011] According to the real-time current operating parameters, the predicted fault type and the preset detection period, a target detection period is determined, and the target detection period is used as the adjusted detection period.

[0012] Furthermore, according to the real-time current operating parameters, the predicted fault type and the preset detection period, a target detection period is determined, including:

[0013]

[0014]

[0015] in, is the target detection period, For the preset detection cycle, is the evaluation coefficient corresponding to the fault type, is the capacitive current, is the resistive current, is the evaluation coefficient of the arrester operation times, is the actual number of times the arrester operates, The arrester action times threshold.

[0016] Furthermore, historical current operating parameters and historical fault types are matched according to time sequence, including:

[0017] The resistive current and capacitive current in the historical current operating parameters are processed to obtain the first characterization, including:

[0018]

[0019] in, For the first representation, is the capacitive current, is the resistive current;

[0020] According to the time sequence of obtaining historical current operating parameters and historical fault types, the first characterization, historical fault type and number of arrester actions are matched, and the first characterization, historical fault type and number of arrester actions under the same time sequence are packaged into a data group.

[0021] Furthermore, the neural network to be trained is trained with historical current operating parameters and historical fault types to obtain a power arrester fault diagnosis model for wind turbines, including:

[0022] Inputting a plurality of data groups into a neural network to be trained, and obtaining a plurality of predicted fault types based on the neural network to be trained;

[0023] Adjusting the neural network parameters of the neural network to be trained based on historical fault types and predicted fault types;

[0024] When the preset training requirements are met, the latest neural network parameters are saved, and the neural network to be trained is used as a fault diagnosis model for the power lightning arrester of the wind turbine generator set.

[0025] Furthermore, the loss function of the neural network to be trained includes:

[0026]

[0027] in, is the loss function, is the number of data sets, is the fault type, For the The data group belongs to The label of the fault type, which includes 0 or 1, For the The data group belongs to The probability of class failure.

[0028] Furthermore, the evaluation coefficient corresponding to the fault type is determined, including:

[0029] Determine a first weight according to the fault type;

[0030] determining a second weight according to a sub-fault in the fault type;

[0031] Determining an evaluation coefficient of a sub-fault of a fault type according to the first weight and the second weight includes:

[0032]

[0033] in, is the first weight, is the second weight.

[0034] In a second aspect, the present invention provides a device for monitoring the operating status of a lightning arrester of a wind turbine generator, the device comprising:

[0035] A data acquisition module is used to obtain historical current operating parameters and historical fault types of the power lightning arrester of the wind turbine, and match the historical current operating parameters and historical fault types in a time sequence. The current operating parameters include the number of lightning arrester operations, resistive current, and capacitive current. The fault types include internal environmental faults, external lightning faults, and operating load faults.

[0036] A fault prediction module is used to train a neural network to be trained using historical current operating parameters and historical fault types to obtain a wind turbine generator's lightning arrester fault diagnosis model. The wind turbine generator's lightning arrester fault diagnosis model is used to predict the wind turbine generator's lightning arrester fault type.

[0037] The cycle adjustment module is used to adjust the detection cycle of the power lightning arrester of the target wind turbine generator set according to the real-time current operating parameters and predicted fault type of the power lightning arrester of the target wind turbine generator set, and to inspect the power lightning arrester of the target wind turbine generator set according to the adjusted detection cycle.

[0038] In a third aspect, the present invention provides an electronic device, comprising:

[0039] processor;

[0040] a memory for storing processor-executable instructions;

[0041] The processor is configured to execute to implement a method for monitoring the operating status of a power lightning arrester of a wind turbine generator set as provided in the first aspect.

[0042] In a fourth aspect, the present invention provides a non-temporary computer-readable storage medium. When the instructions in the non-temporary computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute a method for monitoring the operating status of a power lightning arrester of a wind turbine set as provided in the first aspect.

[0043] One or more technical solutions provided in the present invention have at least the following technical effects or advantages:

[0044] The present invention dynamically adjusts the detection cycle based on real-time current operating parameters and predicted fault types. When the arrester is operating in a stable state, the detection cycle is longer, reducing unnecessary inspection workload. When the arrester is operating abnormally, the detection cycle is shortened to ensure that problems can be discovered in a timely manner. By dynamically adjusting the detection cycle, operation and maintenance costs can be minimized while ensuring the reliability of the arrester, the number of unnecessary inspections can be reduced, and human and material resources can be saved. By dynamically adjusting the inspection cycle, the timeliness of fault detection is improved, reducing power outage losses and maintenance costs caused by faults.

[0045] The present invention can quantitatively characterize the fault type of the power arrester of the wind turbine generator through the first characterization and the number of arrester operations, thereby providing an accurate basis for dividing the detection cycle.

[0046] The present invention divides the fault types in more detail and obtains the corresponding first weight and second weight after the division, providing a more accurate basis for dividing the detection cycle. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following is a brief introduction to the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0048] Figure 1 A schematic flow chart of a method for monitoring the operating status of a power lightning arrester of a wind turbine generator system provided by the present invention;

[0049] Figure 2 A flow chart of a method for determining an evaluation coefficient corresponding to a fault type provided by the present invention;

[0050] Figure 3 This is a structural schematic diagram of a device for monitoring the operating status of a power lightning arrester of a wind turbine generator set provided by the present invention. DETAILED DESCRIPTION

[0051] The embodiment of the present invention solves the technical problem in the prior art that a fixed inspection cycle cannot adapt to the actual operating state of the arrester by providing a method for monitoring the operating state of a power arrester of a wind turbine.

[0052] The technical solution of the present invention is to solve the above technical problems, and the overall idea is as follows:

[0053] A method for monitoring the operating status of a lightning arrester of a wind turbine generator set comprises: obtaining historical current operating parameters and historical fault types of the lightning arrester of the wind turbine generator set, and matching the historical current operating parameters and historical fault types in a time sequence, wherein the current operating parameters include the number of lightning arrester operations, resistive current, and capacitive current, and the fault types include internal environmental faults, external lightning faults, and operating load faults; training a neural network to be trained using the historical current operating parameters and historical fault types to obtain a lightning arrester fault diagnosis model for the wind turbine generator set, the lightning arrester fault diagnosis model for the wind turbine generator set being used to predict the fault type of the lightning arrester of the wind turbine generator set; adjusting the detection period of the lightning arrester of the target wind turbine generator set according to the real-time current operating parameters and the predicted fault type of the lightning arrester of the target wind turbine generator set, and performing patrol inspections on the lightning arrester of the target wind turbine generator set according to the adjusted detection period.

[0054] In order to better understand the above technical solution, the above technical solution will be described in detail below with reference to the accompanying drawings and specific implementation methods.

[0055] First, the term "and / or" as used herein simply describes a relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A alone, A and B together, or B alone. Furthermore, the character " / " in this document generally indicates an "or" relationship between the associated objects.

[0056] A wind turbine's lightning arrester (also known as a surge protector or overvoltage protector) is a critical device used to protect electrical equipment from transient high voltages, such as voltage surges caused by lightning or other forms of power system disturbances. Its primary function is to limit transient overvoltages and divert surge currents, thereby protecting sensitive equipment connected to it.

[0057] Wind turbine surge arresters are typically constructed from nonlinear resistor materials, such as metal oxide varistors (MOVs). Under normal operating conditions, these resistors have a very high impedance, allowing little or no current to flow. The main types of surge arresters for wind turbines include gapless metal oxide arresters, gapped arresters, and silicon carbide arresters.

[0058] Arrester operations are the number of times the arrester has been activated (or "tripped") during operation due to detecting a voltage exceeding a set threshold. Each arrester operation is intended to divert the excess voltage to ground, thereby protecting the connected equipment.

[0059] Total current refers to the total current flowing through the arrester, including resistive current and capacitive current. It reflects the total current of the arrester when it is in operation.

[0060] Resistive current is one component of the total current and is mainly related to the internal loss of the arrester. Capacitive current is another component of the total current and is mainly related to the capacitance effect of the arrester.

[0061] The present invention provides Figure 1 The method for monitoring the operating status of a lightning arrester of a wind turbine generator system shown includes steps S11-S13:

[0062] Step S11, obtain the historical current operating parameters and historical fault types of the power lightning arrester of the wind turbine group, and match the historical current operating parameters and historical fault types in time sequence, where the current operating parameters include the number of lightning arrester operations, resistive current and capacitive current, and the fault types include internal environmental faults, external lightning faults and operating load faults.

[0063] Match historical current operating parameters and historical fault types in time sequence, including:

[0064] The resistive current and capacitive current in the historical current operating parameters are processed to obtain the first characterization, including:

[0065]

[0066] in, For the first representation, is the capacitive current, is the resistive current;

[0067] According to the time sequence of obtaining historical current operating parameters and historical fault types, the first characterization, historical fault type and number of arrester actions are matched, and the first characterization, historical fault type and number of arrester actions under the same time sequence are packaged into a data group.

[0068] External lightning failure: Lightning impulse may cause failure of the lightning arrester. Specifically, when the lightning arrester is subjected to the impact of lightning current, its internal temperature will rise sharply, which may cause the performance of the resistor material to deteriorate or even melt. If the number of lightning impulses is too many, the key components such as the internal resistor and anti-corona chain of the lightning arrester may be seriously affected, and the lightning arrester may be directly damaged.

[0069] Internal environmental failures may include internal degradation, internal moisture, contamination of the arrester surface, and degradation of the arrester core heat shrink tubing.

[0070] Operational load failure: The arrester operates beyond its designed load for a long time, causing its performance to gradually deteriorate or even be damaged. The fluctuation of the internal resistance of the arrester increases, thereby accelerating the aging of the material. Alternatively, voltage fluctuations occur during circuit operation, and some lines may experience overvoltage problems due to technical or environmental factors. When the voltage exceeds the tolerance limit of the arrester, an operational load failure occurs.

[0071] After several experiments, the inventors found that the first characterization can indicate some fault types of the power lightning arrester of the wind turbine. For details, please refer to Table 1, which shows the experimental results of the power lightning arrester of a certain brand of wind turbine:

[0072] Table 1

[0073]

[0074] The first characterization of other brands can be determined based on actual experimental conditions.

[0075] Time series refers to the time sequence. According to their corresponding time sequence, the first manifestation, historical fault type and number of arrester operations at the same time are packaged and bundled into a data group.

[0076] The present invention can quantitatively characterize the fault type of the power arrester of the wind turbine generator through the first characterization and the number of arrester operations, providing an accurate basis for dividing the detection cycle later.

[0077] Step S12: training the neural network to be trained with historical current operating parameters and historical fault types to obtain a wind turbine generator arrester fault diagnosis model, which is used to predict the wind turbine generator arrester fault type.

[0078] Specifically, the method includes: inputting several data groups into the neural network to be trained, and obtaining several predicted fault types based on the neural network to be trained; adjusting the neural network parameters of the neural network to be trained based on historical fault types and predicted fault types; when the preset training requirements are met, saving the latest neural network parameters, and using the neural network to be trained as a power lightning arrester fault diagnosis model for wind turbines.

[0079] The loss function of the neural network to be trained, including:

[0080]

[0081] in, is the loss function, is the number of data sets, is the fault type, For the The data group belongs to The label of the fault type, which includes 0 or 1, For the The data group belongs to The probability of class failure.

[0082] The neural network parameters of the neural network to be trained may include: weights, biases, activation function parameters, hyperparameters, learning rate, batch size, number of network layers and number of neurons in each layer, and parameters of the loss function, etc.

[0083] The preset training requirements may include the maximum number of training times or accuracy, etc., which are not limited here.

[0084] Step S13 , adjusting the detection period of the power lightning arrester of the target wind turbine generator set according to the real-time current operating parameters and the predicted fault type of the power lightning arrester of the target wind turbine generator set, and inspecting the power lightning arrester of the target wind turbine generator set according to the adjusted detection period.

[0085] Specifically, it includes: obtaining the real-time current operating parameters of the power lightning arrester of the target wind turbine and inputting them into the power lightning arrester fault diagnosis model of the wind turbine to obtain the corresponding predicted fault type; determining the target detection period based on the real-time current operating parameters, the predicted fault type and the preset detection period, and using the target detection period as the adjusted detection period.

[0086] Determine the target detection period based on the real-time current operating parameters, predicted fault type, and preset detection period, including:

[0087]

[0088]

[0089] in, is the target detection period, For the preset detection cycle, is the evaluation coefficient corresponding to the fault type, is the capacitive current, is the resistive current, is the evaluation coefficient of the arrester operation times, is the actual number of times the arrester operates, The arrester action times threshold.

[0090] The evaluation coefficient corresponding to the fault type can be determined based on the experience of relevant personnel. For example, the operating load fault is 0.4, the external lightning fault is 0.3, no fault is 1, and the degradation of the arrester core heat shrink tube is 0.8. Specifically, the more serious the impact on the operation of the wind turbine power arrester, the lower the evaluation coefficient corresponding to the fault type should be.

[0091] In addition, the present invention also provides Figure 2 Another method for determining an evaluation coefficient corresponding to a fault type is shown, including:

[0092] Determine a first weight according to the fault type;

[0093] determining a second weight according to a sub-fault in the fault type;

[0094] Determining an evaluation coefficient of a sub-fault of a fault type according to the first weight and the second weight includes:

[0095]

[0096] in, is the first weight, is the second weight.

[0097] Fault types are divided into internal environmental faults, external lightning faults, and operating load faults. Based on historical experience, the corresponding first weights of internal environmental faults, external lightning faults, and operating load faults can be assigned to 0.8, 0.4, and 0.3, respectively. If there are no sub-faults (such as internal environmental faults and external lightning faults), the second weight is recorded as 1. If there are sub-faults (such as the contaminated surface of the lightning arrester in the internal environmental fault), the value is assigned according to historical experience.

[0098] The present invention divides the fault types in more detail and obtains the corresponding first weight and second weight after the division, providing a more accurate basis for dividing the detection cycle.

[0099] Currently, traditional power equipment inspections typically use fixed cycles (such as monthly or quarterly), but fixed cycles cannot adapt to changes in the actual operating status of the equipment. The present invention dynamically adjusts the inspection cycle based on real-time current operating parameters and predicted fault types. When the arrester's operating state is stable, the inspection cycle is longer, reducing unnecessary inspection workload; when the arrester's operating state is abnormal, the inspection cycle is shortened to ensure that problems are discovered promptly. By dynamically adjusting the inspection cycle, operating and maintenance costs can be minimized while ensuring the reliability of the arrester. This reduces the number of unnecessary inspections and saves manpower and material resources. By dynamically adjusting the inspection cycle, the timeliness of fault detection can be improved, reducing power outage losses and repair costs caused by faults.

[0100] The present invention reflects the health status of the arrester through the first representation; and comprehensively determines the fault type through the first representation and the number of times the arrester operates.

[0101] This invention introduces a wind turbine arrester fault diagnosis model that analyzes real-time current operating parameters to predict possible fault types (such as internal environmental faults, external lightning faults, and operating load faults). The prediction results are used to influence the calculation of the detection cycle through an evaluation coefficient.

[0102] In summary, the present invention provides a method for monitoring the operating status of a lightning arrester of a wind turbine generator set, the method comprising: obtaining historical current operating parameters and historical fault types of the lightning arrester of the wind turbine generator set, and matching the historical current operating parameters and historical fault types in a time sequence, wherein the current operating parameters include the number of lightning arrester operations, resistive current, and capacitive current, and the fault types include internal environmental faults, external lightning faults, and operating load faults; training a neural network to be trained using the historical current operating parameters and historical fault types to obtain a lightning arrester fault diagnosis model for the wind turbine generator set, the lightning arrester fault diagnosis model for the wind turbine generator set being used to predict the fault type of the lightning arrester of the wind turbine generator set; adjusting the detection period of the lightning arrester of the target wind turbine generator set according to the real-time current operating parameters and predicted fault type of the lightning arrester of the target wind turbine generator set, and inspecting the lightning arrester of the target wind turbine generator set according to the adjusted detection period. The present invention dynamically adjusts the detection period based on the real-time current operating parameters and predicted fault type. When the operating state of the lightning arrester is stable, the detection period is longer, reducing unnecessary inspection workload; when the operating state of the lightning arrester is abnormal, the detection period is shortened, ensuring that problems can be discovered in a timely manner. By dynamically adjusting the detection cycle, the operation and maintenance costs can be minimized while ensuring the reliability of the lightning arrester, the number of unnecessary inspections can be reduced, and human and material resources can be saved. By dynamically adjusting the inspection cycle, the timeliness of fault detection can be improved, and the power outage losses and maintenance costs caused by faults can be reduced. The present invention can quantitatively characterize the fault type of the power lightning arrester of the wind turbine generator through the first characterization and the number of lightning arrester operations, providing an accurate basis for dividing the detection cycle. The present invention divides the fault type in more detail, and obtains the corresponding first weight and second weight after the division, providing a more accurate basis for dividing the detection cycle.

[0103] Based on the same inventive concept, the present invention provides Figure 3 A device for monitoring the operating status of a lightning arrester of a wind turbine generator system is shown, and the device includes:

[0104] The data acquisition module 31 is used to obtain historical current operating parameters and historical fault types of the power lightning arrester of the wind turbine generator, and match the historical current operating parameters and historical fault types in a time sequence, wherein the current operating parameters include the number of lightning arrester operations, resistive current, and capacitive current; and the fault types include internal environmental faults, external lightning faults, and operating load faults;

[0105] a fault prediction module 32 for training a neural network to be trained using historical current operating parameters and historical fault types to obtain a wind turbine generator arrester fault diagnosis model, wherein the wind turbine generator arrester fault diagnosis model is used to predict the wind turbine generator arrester fault type;

[0106] The cycle adjustment module 33 is used to adjust the detection cycle of the power lightning arrester of the target wind turbine generator set according to the real-time current operating parameters of the power lightning arrester of the target wind turbine generator set and the predicted fault type, and to inspect the power lightning arrester of the target wind turbine generator set according to the adjusted detection cycle.

[0107] Based on the same inventive concept, the present invention further provides an electronic device as shown, comprising:

[0108] processor;

[0109] a memory for storing processor-executable instructions;

[0110] The processor is configured to execute and implement a method for monitoring the operating status of a power lightning arrester of a wind turbine generator set as provided above.

[0111] Based on the same inventive concept, the present invention also provides a non-temporary computer-readable storage medium. When the instructions in the non-temporary computer-readable storage medium are executed by the processor of an electronic device, the electronic device can execute a method for monitoring the operating status of a power lightning arrester of a wind turbine set as provided above.

[0112] Since the electronic device described in this embodiment is an electronic device used to implement the information processing method in the embodiment of the present invention, based on the information processing method described in the embodiment of the present invention, those skilled in the art will be able to understand the specific implementation of the electronic device of this embodiment and its various variations. Therefore, how the electronic device implements the method in the embodiment of the present invention will not be described in detail here. As long as the electronic device used by those skilled in the art to implement the information processing method in the embodiment of the present invention falls within the scope of protection of the present invention.

[0113] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0114] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0115] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0116] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0117] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0118] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A method for monitoring the operating status of a lightning arrester of a wind turbine generator, characterized in that: include: Obtain historical current operating parameters and historical fault types of the wind turbine generator's power lightning arrester, and match the historical current operating parameters and historical fault types in time sequence. The current operating parameters include the number of lightning arrester operations, resistive current, and capacitive current. The fault types include internal environmental faults, external lightning faults, and operating load faults. The neural network to be trained is trained using historical current operating parameters and historical fault types to obtain a wind turbine generator power arrester fault diagnosis model, wherein the wind turbine generator power arrester fault diagnosis model is used to predict the fault type of the wind turbine generator power arrester; Adjusting the detection period of the lightning arrester of the target wind turbine generator set according to the real-time current operating parameters and the predicted fault type of the lightning arrester of the target wind turbine generator set, and inspecting the lightning arrester of the target wind turbine generator set according to the adjusted detection period; wherein, the method includes: obtaining the real-time current operating parameters of the lightning arrester of the target wind turbine generator set and inputting them into a lightning arrester fault diagnosis model of the wind turbine generator set to obtain the corresponding predicted fault type; determining a target detection period according to the real-time current operating parameters, the predicted fault type and the preset detection period, and using the target detection period as the adjusted detection period; and further including: in, is the target detection period, For the preset detection cycle, is the evaluation coefficient corresponding to the fault type, is the capacitive current, is the resistive current, is the evaluation coefficient of the arrester operation times, is the actual number of times the arrester operates, The arrester action times threshold.

2. The method for monitoring the operating status of a lightning arrester of a wind turbine generator set according to claim 1, wherein: Match historical current operating parameters and historical fault types in time sequence, including: The resistive current and capacitive current in the historical current operating parameters are processed to obtain the first characterization, including: in, For the first representation, is the capacitive current, is the resistive current; According to the time sequence of obtaining historical current operating parameters and historical fault types, the first characterization, historical fault type and number of arrester actions are matched, and the first characterization, historical fault type and number of arrester actions under the same time sequence are packaged into a data group.

3. The method for monitoring the operating status of a lightning arrester of a wind turbine generator set according to claim 2, wherein: The neural network is trained using historical current operating parameters and historical fault types to obtain a fault diagnosis model for the lightning arrester of the wind turbine, including: Inputting a plurality of data groups into a neural network to be trained, and obtaining a plurality of predicted fault types based on the neural network to be trained; Adjusting the neural network parameters of the neural network to be trained based on historical fault types and predicted fault types; When the preset training requirements are met, the latest neural network parameters are saved, and the neural network to be trained is used as the power lightning arrester fault diagnosis model of the wind turbine generator set.

4. A method for monitoring the operating status of a lightning arrester of a wind turbine generator set according to claim 3, characterized in that: The loss function of the neural network to be trained, including: in, is the loss function, is the number of data sets, is the fault type, For the The data group belongs to The label of the fault type, which includes 0 or 1, For the The data group belongs to The probability of class failure.

5. The method for monitoring the operating status of a lightning arrester of a wind turbine generator set according to claim 1, wherein: Determine the evaluation coefficient corresponding to the fault type, including: Determine a first weight according to the fault type; determining a second weight according to a sub-fault in the fault type; Determining an evaluation coefficient of a sub-fault of a fault type according to the first weight and the second weight includes: in, is the first weight, is the second weight.

6. A wind turbine generator power arrester operating status monitoring device, characterized in that: A method for monitoring the operating status of a power lightning arrester of a wind turbine generator system according to any one of claims 1 to 5, the device comprising: A data acquisition module is used to obtain historical current operating parameters and historical fault types of the power lightning arrester of the wind turbine, and match the historical current operating parameters and historical fault types in a time sequence. The current operating parameters include the number of lightning arrester operations, resistive current, and capacitive current. The fault types include internal environmental faults, external lightning faults, and operating load faults. a fault prediction module, configured to train a neural network to be trained using historical current operating parameters and historical fault types to obtain a wind turbine generator's lightning arrester fault diagnosis model, wherein the wind turbine generator's lightning arrester fault diagnosis model is used to predict the wind turbine generator's lightning arrester fault type; The cycle adjustment module is used to adjust the detection cycle of the power lightning arrester of the target wind turbine group according to the real-time current operating parameters and predicted fault type of the power lightning arrester of the target wind turbine group, and to inspect the power lightning arrester of the target wind turbine group according to the adjusted detection cycle.

7. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute and implement a method for monitoring the operating status of a power lightning arrester of a wind turbine generator set according to any one of claims 1 to 5.

8. A non-transitory computer-readable storage medium, characterized in that When the instructions in the non-transitory computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to implement a method for monitoring the operating status of a power lightning arrester of a wind turbine set according to any one of claims 1 to 5.

Images