A fault diagnosis method, device, equipment and medium for an onshore wind farm

Abstract

The present invention relates to the technical field of wind turbines, and discloses a fault diagnosis method, device, equipment and medium for an onshore wind farm. After the monitoring data at the current moment is input into the digital twin system, the digital twin system simulates the operation process of the onshore wind farm at the current moment to obtain simulation data. Then, it is determined whether a fault occurs in the onshore wind farm based on the simulation data and the monitoring data. When it is determined that a fault occurs, the digital twin system is used to analyze the monitoring data and simulation data corresponding to the time when the fault occurs, so as to obtain the cause of the fault. The digital twin system provided by this scheme is a coupling system that has both simulation and data analysis. More comprehensive and rich simulation data are obtained through simulation. When a fault occurs, by analyzing the comprehensive and rich simulation data and monitoring data, it is possible to better consider the various influences and correlations, so as to determine a more accurate cause of the fault.

Description

Technical Field

[0001] The present invention relates to the technical field of wind turbine generators, and in particular to a fault diagnosis method, device, equipment and medium for an onshore wind farm. Background Art

[0002] The large-scale development of wind resources and the growth of wind turbine capacity have greatly increased the proportion of wind power generation. Therefore, the demand for wind power operation and maintenance is also increasing. The current operation and maintenance of wind power stations mainly rely on fault repair and regular maintenance, but with the development of artificial intelligence technology, some power stations have begun to use algorithm warning and diagnosis technology, which can reduce some power losses and improve the operation and maintenance efficiency of personnel. However, this method is a passive maintenance strategy with a high false alarm rate.

[0003] Therefore, a fault diagnosis method with higher accuracy is urgently needed at this stage. Summary of the invention

[0004] In view of this, the present invention provides a fault diagnosis method, device, equipment and medium for an onshore wind farm to solve the current problem of low fault accuracy.

[0005] In a first aspect, the present invention provides a fault diagnosis method for an onshore wind farm, the method comprising:

[0006] Obtain the monitoring data corresponding to the onshore wind farm at the current moment; input the monitoring data into the pre-built digital twin system, use the digital twin system to simulate the operation process of the onshore wind farm, and obtain simulation data; determine whether the onshore wind farm has a fault based on the simulation data and monitoring data; when a fault occurs in the onshore wind farm, use the digital twin system to analyze the cause of the fault based on the simulation data and monitoring data corresponding to the time when the fault occurred.

[0007] The fault diagnosis method for an onshore wind farm provided in this embodiment, after the monitoring data at the current moment is input into the digital twin system, the digital twin system simulates the operation process of the onshore wind farm at the current moment to obtain simulation data. Then, it is determined whether a fault has occurred in the onshore wind farm based on the simulation data and the monitoring data. When it is determined that a fault has occurred, the monitoring data and the simulation data corresponding to the time of the fault are analyzed by the digital twin system to obtain the cause of the fault. The digital twin system provided in this solution is a coupled system that has both simulation and data analysis. More comprehensive and rich simulation data are obtained through simulation. When a fault occurs, by analyzing the comprehensive and rich simulation data and monitoring data, it is possible to better consider the impact and correlation of various aspects, thereby determining a more accurate cause of the fault.

[0008] In an optional implementation, the digital twin system is constructed as follows:

[0009] Obtain wind farm wind turbine information of the onshore wind farm; based on the wind farm wind turbine information, use preset tools to build a digital twin system corresponding to the onshore wind farm.

[0010] In an optional implementation, the digital twin system includes a device operation simulation kernel and a grid connection simulation kernel. The monitoring data is input into the pre-built digital twin system. The operation process of the onshore wind farm is simulated using the simulation kernel in the digital twin system to obtain simulation data, including:

[0011] The monitoring data is input into the equipment operation simulation kernel, and the equipment operation simulation kernel is used to simulate the operation process of each device in the onshore wind farm to obtain operation simulation data; the operation simulation data is input into the grid-connected simulation kernel, and the grid-connected process of wind power is simulated using the grid-connected simulation kernel to obtain grid-connected simulation data; the simulation data includes operation simulation data and grid-connected simulation data.

[0012] The fault diagnosis method for an onshore wind farm provided in this embodiment utilizes two simulation kernels in the digital twin system, namely, the equipment operation simulation kernel and the grid-connected simulation kernel, to simulate the equipment operation process and the grid-connected process respectively. Through the above-mentioned targeted simulation process, the simulation effect can be made closer to the actual situation, and the accuracy of the simulation data is guaranteed, thereby indirectly ensuring the accuracy of the fault diagnosis results.

[0013] In an optional implementation, determining whether a fault occurs in an onshore wind farm based on simulation data and monitoring data includes:

[0014] The simulation data is compared with a first fault threshold corresponding to an indicator to which the simulation data belongs, to obtain a first comparison result; the monitoring data is compared with a second fault threshold corresponding to an indicator to which the monitoring data belongs, to obtain a second comparison result; and whether a fault occurs in the onshore wind farm is determined based on the first comparison result and the second comparison result.

[0015] In an optional implementation, the digital twin system is used to analyze the cause of the failure, including:

[0016] The autoencoder and random forest algorithm are used to analyze the simulation data and monitoring data corresponding to the time when the fault occurs to obtain the cause of the fault.

[0017] In an optional implementation, the operation simulation data includes torque, output voltage and output current.

[0018] In an optional implementation, the grid-connected simulation data includes a grid-connected voltage and a grid-connected current.

[0019] In a first aspect, the present invention provides a fault diagnosis device for an onshore wind farm, the device comprising:

[0020] An acquisition module is used to obtain the monitoring data corresponding to the onshore wind farm at the current moment; a simulation module is used to input the monitoring data into a pre-built digital twin system, and use the digital twin system to simulate the operation process of the onshore wind farm to obtain simulation data; a judgment module is used to judge whether a fault occurs in the onshore wind farm based on the simulation data and monitoring data; an analysis module is used to use the digital twin system to analyze the cause of the fault when a fault occurs in the onshore wind farm based on the simulation data and monitoring data corresponding to the time of the fault.

[0021] In an optional implementation, the module for constructing the digital twin system in the simulation module includes:

[0022] The acquisition submodule is used to obtain the wind farm wind turbine information of the onshore wind farm; the construction submodule is used to build the digital twin system corresponding to the onshore wind farm based on the wind farm wind turbine information using preset tools.

[0023] In an optional implementation, the digital twin system in the simulation module includes a device operation simulation kernel and a grid-connected simulation kernel, and the simulation module includes:

[0024] The first simulation submodule is used to input the monitoring data into the equipment operation simulation kernel, and use the equipment operation simulation kernel to simulate the operation process of each device in the onshore wind farm to obtain operation simulation data; the second simulation submodule is used to input the operation simulation data into the grid-connected simulation kernel, and use the grid-connected simulation kernel to simulate the grid-connected process of wind power to obtain grid-connected simulation data; the simulation data includes operation simulation data and grid-connected simulation data.

[0025] In an optional implementation, the judgment module includes:

[0026] The first comparison submodule is used to compare the simulation data with the first fault threshold corresponding to the indicator to which the simulation data belongs, so as to obtain a first comparison result; the second comparison submodule is used to compare the monitoring data with the second fault threshold corresponding to the indicator to which the monitoring data belongs, so as to obtain a second comparison result; the judgment submodule is used to judge whether a fault occurs in the onshore wind farm based on the first comparison result and the second comparison result.

[0027] In an optional embodiment, the analysis module includes:

[0028] The analysis submodule is used to analyze the simulation data and monitoring data corresponding to the time when the fault occurs by using the autoencoder and random forest algorithm to obtain the cause of the fault.

[0029] In an optional implementation, the operation simulation data in the first simulation submodule includes torque, output voltage and output current.

[0030] In a third aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the onshore wind farm fault diagnosis method of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0031] In a fourth 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 onshore wind farm fault diagnosis method of the first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] 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.

[0033] Figure 1 is a schematic flow chart of a fault diagnosis method for an onshore wind farm according to an embodiment of the present invention;

[0034] Figure 2 is a flow chart of another onshore wind farm fault diagnosis method according to an embodiment of the present invention;

[0035] Figure 3 is a schematic flow chart of another onshore wind farm fault diagnosis method according to an embodiment of the present invention;

[0036] Figure 4 is a structural block diagram of a fault diagnosis device for an onshore wind farm according to an embodiment of the present invention;

[0037] 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

[0038] 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.

[0039] Supervisory Control And Data Acquisition (SCADA) is a standard system for wind turbines. It provides rich data information such as speed, torque, temperature, voltage, current and power. However, due to the influence of environmental factors and working condition information, direct analysis cannot accurately identify fault characteristics for abnormal warning. There are still problems in the identification of data abnormal values ​​and the abnormal warning model that efficiently identifies fault characteristics, resulting in the inability to accurately locate faults. At present, the fault warning and operation maintenance of wind power stations use the method of SCADA and deep learning to discover component abnormalities, but this method cannot locate the source of the fault. If the parameters are selected based on manual experience, then in the process of SCADA data analysis, it is easy to have a problem of poor correlation between the manually selected parameters and the fault, resulting in too many false alarms or missed alarms. Therefore, in order to improve the accuracy of fault diagnosis, an embodiment of the present invention provides a fault diagnosis method for an onshore wind farm. First, the operation process of the wind farm is simulated through a digital twin system. When a fault occurs in the wind farm based on the simulation data and monitoring data, the simulation data and monitoring data corresponding to the fault time are analyzed through the digital twin system to determine the cause of the fault and realize accurate diagnosis of the fault.

[0040] According to an embodiment of the present invention, an embodiment of a fault diagnosis method for an onshore wind farm 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.

[0041] In this embodiment, a fault diagnosis method for an onshore wind farm is provided, which can be used for computer equipment. Figure 1 is a flow chart of a fault diagnosis method for an onshore wind farm according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0042] Step S101, obtaining monitoring data corresponding to the onshore wind farm at the current moment.

[0043] Specifically, the monitoring data can be collected by the host computer. It should be noted that the monitoring data in this embodiment is not all the data in the onshore wind farm, but some dynamic data during the operation of the onshore wind farm, such as temperature, wind speed, power and other data.

[0044] Step S102: input the monitoring data into a pre-built digital twin system, and use the digital twin system to simulate the operation process of the onshore wind farm to obtain simulation data.

[0045] Specifically, after the monitoring data is input into the digital twin system, the digital twin system will adjust the corresponding data of the corresponding wind turbine according to the monitoring data, so that the operation process of the onshore wind farm in the digital twin system is consistent with the actual operation. At this time, the digital twin system has completed the simulation of the operation process of the onshore wind farm and obtained the simulation data. The simulation data includes all the data in the onshore wind farm, which is more comprehensive and richer than the monitoring data. For example, the simulation data includes the status data and operation data of each wind turbine in the data.

[0046] Step S103: determining whether a fault occurs in the onshore wind farm based on the simulation data and the monitoring data.

[0047] Specifically, after obtaining the simulation data and monitoring data, the simulation data and monitoring data are matched with the fault interval / fault threshold corresponding to the indicator to which each data belongs, and whether the onshore wind farm has a fault is determined based on the matching result. It should be noted that the fault interval / fault threshold corresponding to each indicator can be obtained by simulating multiple groups of fault monitoring data through the digital twin system and then statistically analyzing them.

[0048] Step S104: When a fault occurs in the onshore wind farm, the digital twin system is used to analyze the cause of the fault based on the simulation data and monitoring data corresponding to the time when the fault occurs.

[0049] Specifically, in addition to the simulation part, the digital twin system also includes a data analysis part. When it is determined that a fault has occurred in an onshore wind farm, the data analysis part of the digital twin system is used to analyze the simulation data and monitoring data corresponding to the time when the fault occurred, so as to obtain the cause of the fault.

[0050] The fault diagnosis method for an onshore wind farm provided in this embodiment, after the monitoring data at the current moment is input into the digital twin system, the digital twin system simulates the operation process of the onshore wind farm at the current moment to obtain simulation data. Then, it is determined whether a fault has occurred in the onshore wind farm based on the simulation data and the monitoring data. When it is determined that a fault has occurred, the monitoring data and the simulation data corresponding to the time of the fault are analyzed by the digital twin system to obtain the cause of the fault. The digital twin system provided in this solution is a coupled system that has both simulation and data analysis. More comprehensive and rich simulation data are obtained through simulation. When a fault occurs, by analyzing the comprehensive and rich simulation data and monitoring data, it is possible to better consider the impact and correlation of various aspects, thereby determining a more accurate cause of the fault.

[0051] In this embodiment, a fault diagnosis method for an onshore wind farm is provided, which can be used in the above-mentioned mobile terminal, such as a mobile phone, a tablet computer, etc. Figure 2 is a flow chart of a fault diagnosis method for an onshore wind farm according to an embodiment of the present invention. Figure 2 As shown, the process includes the following steps:

[0052] Step S201, obtain the monitoring data corresponding to the onshore wind farm at the current moment. Figure 1 Step S101 of the illustrated embodiment will not be described in detail here.

[0053] Step S202: input the monitoring data into a pre-built digital twin system, and use the digital twin system to simulate the operation process of the onshore wind farm to obtain simulation data.

[0054] Specifically, in the above step S202, the digital twin system is constructed as follows:

[0055] First, obtain the wind turbine information of the onshore wind farm.

[0056] Specifically, the wind farm wind turbine information includes wind farm information and wind turbine information, wherein the wind farm information includes wind turbine distribution information and environmental information; the wind turbine information includes unit basic information, unit operation information and grid connection information.

[0057] Then, based on the wind farm wind turbine information, the preset tools are used to build the digital twin system corresponding to the onshore wind farm.

[0058] Specifically, based on the wind farm wind turbine information, the digital twin system is constructed using the visual simulation tool Simulink in MATLAB, so that the digital twin system can effectively simulate the actual onshore wind farm. It should be specifically noted that the digital twin system includes the equipment operation simulation kernel and the grid connection simulation kernel.

[0059] Specifically, the above step S202 includes:

[0060] Step S2021: input the monitoring data into the equipment operation simulation kernel, and use the equipment operation simulation kernel to simulate the operation process of each equipment in the onshore wind farm to obtain operation simulation data.

[0061] Specifically, the equipment operation simulation kernel is a model that simulates the pneumatic-mechanical-electrical energy conversion process between the blades, gearbox and generator of the wind turbine unit and the operating status of the components.

[0062] Specifically, the simulation process of the device running the simulation kernel is implemented in the following way:

[0063] The load force of the gearbox caused by the blades satisfies the following formula:

[0064] [M]A+[C]V+[K]L=F

[0065] Among them, M is the mass matrix, unit is kg; C is the damping matrix, unit is kg / s; K is the stiffness matrix, unit is kg / s 2 ; A is the acceleration of the gearbox movement, unit: m / s 2 ; is the speed of the gearbox movement, unit is m / s; L is the displacement of the gearbox movement, unit is m.

[0066] F•S a = n

[0067] Among them, S a is the displacement exerted by the gear on the motor, S a Obtained from monitoring equipment, T n is the torque.

[0068] The motor input mechanical power is converted into electrical power, satisfying the following formula:

[0069]

[0070] Among them, UI is the output power of the generator, k is the coefficient taking into account the motor iron loss, I rms2 is the box current, and R is the phase impedance.

[0071] Specifically, in this embodiment, the operation simulation data includes torque, output voltage and output current.

[0072] Step S2022, inputting the running simulation data into the grid-connected simulation kernel, using the grid-connected simulation kernel to simulate the wind power grid-connected process, and obtaining the grid-connected simulation data; the simulation data includes the running simulation data and the grid-connected simulation data.

[0073] Specifically, the operation simulation data is input into the grid-connected simulation kernel, and the grid-connected simulation kernel performs a grid-connected simulation process on the part where the output power of the generator in the wind turbine is connected to the power grid based on the input operation simulation data.

[0074] Specifically, the grid-connected simulation kernel determines the grid-connected simulation data in the following manner.

[0075] U d =R s i d +pL d i d -w r L q i q

[0076] U q =R s i q +pL q i q -w r Ld i d

[0077] Among them, U d , U q is the stator d and q axis output voltage, i d 、i q is the stator d and q axis current, L d , L q is the inductance of the d and q axes, R s is the stator resistance, w r is the rotor electrical angular velocity, and p is the differential operator.

[0078] Specifically, in this embodiment, the grid-connected simulation data includes a grid-connected voltage and a grid-connected current.

[0079] Step S203: Determine whether a fault occurs in the onshore wind farm based on the simulation data and monitoring data. Figure 1 Step S103 of the illustrated embodiment will not be described in detail here.

[0080] Step S204: When a fault occurs in the onshore wind farm, the digital twin system is used to analyze the cause of the fault based on the simulation data and monitoring data corresponding to the time when the fault occurs. Figure 1 Step S104 of the illustrated embodiment will not be described in detail here.

[0081] The fault diagnosis method for an onshore wind farm provided in this embodiment utilizes two simulation kernels in the digital twin system, namely, the equipment operation simulation kernel and the grid-connected simulation kernel, to simulate the equipment operation process and the grid-connected process respectively. Through the above-mentioned targeted simulation process, the simulation effect can be made closer to the actual situation, and the accuracy of the simulation data is guaranteed, thereby indirectly ensuring the accuracy of the fault diagnosis results.

[0082] In this embodiment, a fault diagnosis method for an onshore wind farm is provided, which can be used in the above-mentioned mobile terminal, such as a mobile phone, a tablet computer, etc. Figure 3 is a flow chart of a fault diagnosis method for an onshore wind farm according to an embodiment of the present invention. Figure 3 As shown, the process includes the following steps:

[0083] Step S301, obtaining monitoring data corresponding to the onshore wind farm at the current moment.

[0084] Step S302: Input the monitoring data into the pre-built digital twin system, and use the digital twin system to simulate the operation process of the onshore wind farm to obtain simulation data. Figure 2 Step S202 of the illustrated embodiment will not be described in detail here.

[0085] Step S303: determining whether a fault occurs in the onshore wind farm based on the simulation data and the monitoring data.

[0086] Specifically, the above step S303 includes:

[0087] Step S3031, comparing the simulation data with a first fault threshold corresponding to an indicator to which the simulation data belongs, to obtain a first comparison result.

[0088] For example, in a certain embodiment, the simulation data is 30°C, and the indicator to which the simulation data belongs is temperature, and the first fault threshold corresponding to the temperature is 25°C, where 25°C is the highest temperature at which the device maintains normal operation. If the simulation data is greater than the first fault threshold by comparing the two, it can be determined that the device is abnormal.

[0089] Step S3032: compare the monitoring data with a second fault threshold corresponding to the indicator to which the monitoring data belongs, and obtain a second comparison result.

[0090] For example, in a certain embodiment, the monitoring data is 100A, and the indicator to which the monitoring data belongs is the unit current, and the second fault threshold corresponding to the unit current is 75A, where 75A is the highest current for the unit equipment to operate healthily. By comparing the monitoring data with the second fault threshold, if the monitoring data is greater than the second fault threshold, the unit current is too large, which can be understood as an abnormality in the unit equipment.

[0091] Step S3033: determining whether a fault occurs in the onshore wind farm based on the first comparison result and the second comparison result.

[0092] Specifically, when at least one of the first comparison result and the second comparison result is abnormal, it can be determined that a fault occurs in the onshore wind farm.

[0093] Exemplarily, according to the above two embodiments, the first comparison result is that an abnormality exists, and the second comparison result is that an abnormality exists. Therefore, it can be determined that a fault has occurred in the onshore wind farm.

[0094] Step S304: When a fault occurs in the onshore wind farm, the cause of the fault is analyzed using the digital twin system based on the simulation data and monitoring data corresponding to the time when the fault occurs.

[0095] Specifically, the autoencoder and random forest algorithm are used to analyze the simulation data and monitoring data corresponding to the time when the fault occurs to obtain the cause of the fault. After the cause of the fault is determined, corresponding warnings and maintenance are carried out based on the cause of the fault.

[0096] Specifically, the simulation data and monitoring data are input into the autoencoder, which normalizes the data and outputs the simulation data and monitoring data in the same data form. The random forest algorithm is then used to analyze and predict the normalized simulation data and monitoring data to obtain the cause of the fault.

[0097] Specifically, based on the autoencoder method, data reconstruction, feature data extraction and compilation are performed on the simulation data and monitoring data. The process is implemented by the following formula:

[0098] From the input layer to the hidden layer, the input data x k The encoding process is as follows:

[0099] h=σ(W1x k +1)

[0100] The decoding process from the hidden layer to the output layer is as follows:

[0101]

[0102] Among them, σ() is the compilation process function, W1, W2, b1 and b2 are linear coefficients.

[0103] Specifically, when using the random forest method for data analysis, an optimal model is trained for each set of resampled data sets to obtain j models.

[0104] Let x i is an N-dimensional variable of a sub-dataset randomly sampled with replacement, i = 1, 2, 3…, j. Based on the similarity of the sub-datasets in the replacement sampling and the same model used, each model has approximately equal bias and variance, and the distribution of the model is also approximately the same but not independent. Therefore:

[0105]

[0106] Among them, E is the function of training samples.

[0107] In this embodiment, a fault diagnosis device for an onshore wind farm is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. 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 of hardware, or a combination of software and hardware, is also possible and conceivable.

[0108] This embodiment provides a fault diagnosis device for an onshore wind farm, such as Figure 4 As shown, including:

[0109] The acquisition module 401 is used to acquire the monitoring data corresponding to the onshore wind farm at the current moment.

[0110] The simulation module 402 is used to input the monitoring data into the pre-built digital twin system, and use the digital twin system to simulate the operation process of the onshore wind farm to obtain simulation data.

[0111] The judgment module 403 is used to judge whether a fault occurs in the onshore wind farm based on the simulation data and the monitoring data.

[0112] The analysis module 404 is used to analyze the cause of the fault by using the digital twin system based on the simulation data and monitoring data corresponding to the time when the fault occurs in the onshore wind farm.

[0113] In some optional implementations, the modules for constructing the digital twin system in the simulation module 402 include:

[0114] The acquisition submodule is used to obtain wind farm wind turbine information of the onshore wind farm.

[0115] The construction submodule is used to build a digital twin system corresponding to the onshore wind farm based on the wind farm wind turbine information using preset tools.

[0116] In some optional implementations, the digital twin system in the simulation module includes a device operation simulation kernel and a grid-connected simulation kernel, and the simulation module includes:

[0117] The first simulation submodule is used to input the monitoring data into the equipment operation simulation kernel, and use the equipment operation simulation kernel to simulate the operation process of each equipment in the onshore wind farm to obtain operation simulation data.

[0118] The second simulation submodule is used to input the operation simulation data into the grid-connected simulation kernel, and use the grid-connected simulation kernel to simulate the grid-connected process of wind power to obtain grid-connected simulation data; the simulation data includes operation simulation data and grid-connected simulation data.

[0119] In some optional implementations, the judgment module includes:

[0120] The first comparison submodule is used to compare the simulation data with a first fault threshold corresponding to an indicator to which the simulation data belongs, to obtain a first comparison result.

[0121] The second comparison submodule is used to compare the monitoring data with a second fault threshold corresponding to the indicator to which the monitoring data belongs, so as to obtain a second comparison result.

[0122] The judgment submodule is used to judge whether a fault occurs in the onshore wind farm based on the first comparison result and the second comparison result.

[0123] In some optional embodiments, the analysis module comprises:

[0124] The analysis submodule is used to analyze the simulation data and monitoring data corresponding to the time when the fault occurs by using the autoencoder and random forest algorithm to obtain the cause of the fault.

[0125] In some optional implementations, the operation simulation data in the first simulation submodule includes torque, output voltage and output current.

[0126] In some optional implementations, the grid-connected simulation data in the second simulation submodule includes a grid-connected voltage and a grid-connected current.

[0127] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0128] The fault diagnosis device for an onshore wind farm 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.

[0129] The embodiment of the present invention also provides a computer device having the above Figure 4 The fault diagnosis device of the onshore wind farm is shown.

[0130] 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 5 As 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] The computer device further comprises a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0136] 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.

[0137] 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 fault diagnosis method for an onshore wind farm, characterized in that: The method comprises: Obtain the monitoring data corresponding to the onshore wind farm at the current moment; Inputting the monitoring data into a pre-built digital twin system, and using the digital twin system to simulate the operation process of the onshore wind farm to obtain simulation data; Determining whether a fault occurs in the onshore wind farm based on the simulation data and the monitoring data; When a fault occurs in the onshore wind farm, the cause of the fault is analyzed using the digital twin system based on the simulation data and monitoring data corresponding to the moment of the fault occurrence; The digital twin system includes a device operation simulation kernel and a grid connection simulation kernel. The monitoring data is input into the pre-built digital twin system, and the operation process of the onshore wind farm is simulated using the simulation kernel in the digital twin system to obtain simulation data, including: Input the monitoring data into the equipment operation simulation kernel, and use the equipment operation simulation kernel to simulate the operation process of each device in the onshore wind farm to obtain operation simulation data; wherein the operation simulation kernel is used to simulate the energy conversion between the blades, gearbox and generator of the wind turbine unit and the operation status of the components; The operation simulation data is input into the grid-connected simulation kernel, and the grid-connected simulation kernel is used to simulate the grid-connected process of wind power to obtain grid-connected simulation data; wherein the grid-connected simulation kernel is used to perform grid-connected simulation on the part of the generator output power in the wind turbine group connected to the power grid based on the input operation simulation data; The simulation data includes the operation simulation data and the grid-connected simulation data.

2. The method according to claim 1, characterized in that The digital twin system is constructed as follows: Obtaining wind farm wind turbine information of the onshore wind farm; Based on the wind farm wind turbine information, a preset tool is used to construct the digital twin system corresponding to the onshore wind farm, wherein the preset tool is a visual simulation tool.

3. The method according to claim 1, characterized in that The determining whether a fault occurs in the onshore wind farm based on the simulation data and the monitoring data includes: Compare the simulation data with a first fault threshold corresponding to an indicator to which the simulation data belongs, to obtain a first comparison result; Compare the monitoring data with a second fault threshold corresponding to the indicator to which the monitoring data belongs, to obtain a second comparison result; wherein the first fault threshold and the second fault threshold are obtained by simulating multiple groups of fault monitoring data through a digital twin system and performing statistics; Whether a fault occurs in the onshore wind farm is determined based on the first comparison result and the second comparison result.

4. The method according to claim 1 or 3, characterized in that: The using the digital twin system to analyze the cause of the fault includes: The autoencoder and random forest algorithm are used to analyze the simulation data and monitoring data corresponding to the moment when the fault occurs, so as to obtain the cause of the fault.

5. The method according to claim 1, characterized in that The operation simulation data includes torque, output voltage and output current.

6. The method according to claim 1, characterized in that The grid-connected simulation data includes grid-connected voltage and grid-connected current.

7. A fault diagnosis device for an onshore wind farm, characterized in that: The device comprises: An acquisition module is used to acquire the monitoring data corresponding to the onshore wind farm at the current moment; A simulation module, used for inputting the monitoring data into a pre-built digital twin system, and using the digital twin system to simulate the operation process of the onshore wind farm to obtain simulation data; A judgment module, used for judging whether a fault occurs in the onshore wind farm based on the simulation data and the monitoring data; an analysis module, configured to analyze the cause of the fault by using the digital twin system based on the simulation data and monitoring data corresponding to the time when the fault occurs, when the onshore wind farm fails; The digital twin system in the simulation module includes a device operation simulation kernel and a grid-connected simulation kernel, and the simulation module includes: The first simulation submodule is used to input the monitoring data into the equipment operation simulation kernel, and use the equipment operation simulation kernel to simulate the operation process of each device in the onshore wind farm to obtain operation simulation data; wherein the operation simulation kernel is used to simulate the energy conversion between the blades, gearbox and generator of the wind turbine unit and the operation status of the components; The second simulation submodule is used to input the operation simulation data into the grid-connected simulation kernel, and use the grid-connected simulation kernel to simulate the grid-connected process of wind power to obtain grid-connected simulation data; the simulation data includes the operation simulation data and the grid-connected simulation data; wherein, the grid-connected simulation kernel is used to perform grid-connected simulation on the part of the generator output power in the wind turbine group that is connected to the power grid based on the input operation simulation data.

8. The device according to claim 7, characterized in that The modules for building digital twin systems in the simulation module include: An acquisition submodule, used to acquire wind farm wind turbine information of the onshore wind farm; A construction submodule is used to construct the digital twin system corresponding to the onshore wind farm based on the wind farm wind turbine information using a preset tool, wherein the preset tool is a visual simulation tool.

9. The device according to claim 7, characterized in that The judging module comprises: A first comparison submodule, used for comparing the simulation data with a first fault threshold corresponding to an indicator to which the simulation data belongs, to obtain a first comparison result; A second comparison submodule is used to compare the monitoring data with a second fault threshold corresponding to the indicator to which the monitoring data belongs, to obtain a second comparison result; wherein the first fault threshold and the second fault threshold are obtained by simulating multiple groups of fault monitoring data through a digital twin system and performing statistics; A judgment submodule is used to judge whether a fault occurs in the onshore wind farm based on the first comparison result and the second comparison result.

10. The device according to claim 7 or 9, characterized in that The analysis module comprises: The analysis submodule is used to analyze the simulation data and monitoring data corresponding to the time when the fault occurs by using the autoencoder and the random forest algorithm to obtain the cause of the fault.

11. The device according to claim 7, characterized in that The operation simulation data in the first simulation submodule includes torque, output voltage and output current.

12. 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 diagnosis method for an onshore wind farm according to any one of claims 1 to 6 by executing the computer instructions.

13. 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 fault diagnosis method for an onshore wind farm according to any one of claims 1 to 6.

Images