Wind power plant monitoring method and device, electronic equipment and storage medium

Abstract

The invention discloses a wind power plant monitoring method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring current radar monitoring flow field data and current SCADA data of a wind power plant to be monitored; inputting current radar monitoring flow field data into the pre-trained neural network to obtain a current three-dimensional transient flow field of the wind power plant to be monitored; wherein the pre-trained neural network is obtained by training based on a pre-established flow field simulation library; the pre-established flow field simulation library is established based on at least one group of simulation data; each group of simulation data comprises unit design parameters, unit operation parameters and terrain parameters of the sample wind power plant and flow field simulation values under different working condition parameters; and according to the current three-dimensional transient flow field and the current SCADA data, analyzing an abnormal condition of the wind power plant to be monitored so as to carry out abnormity optimization. According to the technical scheme, the operation environment of the unit can be comprehensively analyzed, and the low-efficiency reason of the wind power plant unit can be quickly judged.

Description

Technical Field

[0001] This invention relates to the field of wind power technology, and in particular to a wind farm monitoring method, device, electronic equipment, and storage medium. Background Technology

[0002] In the field of intelligent operation and maintenance of wind farms, the load control and safety assessment of equipment are generally based solely on the nacelle wind speed and the operating status detected by the monitoring equipment of various components of the wind turbine, which are accessed by the wind turbine SCADA (Supervisory Control And Data Acquisition) system.

[0003] Using only SCADA data to analyze the operating status of wind turbine units makes it difficult to intuitively and quickly determine the reasons for unit inefficiency, and also makes it impossible to analyze the unit's operating environment. Summary of the Invention

[0004] This invention provides a wind farm monitoring method, device, electronic equipment, and storage medium to comprehensively analyze the operating environment of the units and quickly determine the causes of wind farm unit inefficiency.

[0005] According to one aspect of the present invention, a wind farm monitoring method is provided, comprising:

[0006] Acquire the current radar monitoring flow field data and current SCADA data of the wind farm to be monitored;

[0007] The current radar-monitored flow field data is input into a pre-trained neural network to obtain the current three-dimensional transient flow field of the wind farm to be monitored; wherein, the pre-trained neural network is trained based on a pre-established flow field simulation library; the pre-established flow field simulation library is established based on at least one set of simulation data; each set of simulation data includes the turbine design parameters, turbine operating parameters, terrain parameters, and flow field simulation values ​​under different operating conditions of the sample wind farm;

[0008] Based on the current three-dimensional transient flow field and the current SCADA data, analyze the abnormal conditions of the wind farm to be monitored in order to perform anomaly optimization.

[0009] According to another aspect of the present invention, a wind farm monitoring device is provided, comprising:

[0010] The data acquisition module is used to acquire the current radar monitoring flow field data and current SCADA data of the wind farm to be monitored.

[0011] The flow field reconstruction module is used to input the current radar-monitored flow field data into a pre-trained neural network to obtain the current three-dimensional transient flow field of the wind farm to be monitored; wherein, the pre-trained neural network is trained based on a pre-established flow field simulation library; the pre-established flow field simulation library is established based on at least one set of simulation data; each set of simulation data includes the turbine design parameters, turbine operating parameters, terrain parameters, and flow field simulation values ​​under different operating conditions of the sample wind farm;

[0012] The anomaly analysis module is used to analyze the anomalies of the wind farm to be monitored based on the current three-dimensional transient flow field and the current SCADA data, so as to perform anomaly optimization.

[0013] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0014] At least one processor; and

[0015] A memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the wind farm monitoring method according to any embodiment of the present invention.

[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the wind farm monitoring method according to any embodiment of the present invention.

[0018] The technical solution of this invention involves acquiring current radar-monitored flow field data and current SCADA data of the wind farm to be monitored; inputting the current radar-monitored flow field data into a pre-trained neural network to obtain the current three-dimensional transient flow field of the wind farm to be monitored; wherein, the pre-trained neural network is trained based on a pre-established flow field simulation library; the pre-established flow field simulation library is established based on at least one set of simulation data; each set of simulation data includes the turbine design parameters, turbine operating parameters, terrain parameters, and flow field simulation values ​​under different operating conditions of the sample wind farm; based on the current three-dimensional transient flow field and the current SCADA data, the abnormal conditions of the wind farm to be monitored are analyzed for anomaly optimization; the neural network is trained based on the flow field simulation values, and the flow field is reconstructed based on the radar-monitored flow field data after training; thereby, the reconstructed flow field and the collected SCADA data are used to monitor the abnormal conditions of the wind farm to be monitored. This solves the problem in the prior art that only uses wind turbine SCADA data to analyze the operating status of wind turbine units, making it difficult to intuitively and quickly determine the cause of unit inefficiency, and also unable to analyze the unit's operating environment problems. This provides a comprehensive analysis of the unit's operating environment and a rapid determination of the cause of wind farm unit inefficiency.

[0019] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1a This is a flowchart of a wind farm monitoring method provided in Embodiment 1 of the present invention;

[0022] Figure 1b This is a complete schematic diagram of a wind farm monitoring method provided in this embodiment;

[0023] Figure 2 This is a schematic diagram of the structure of a wind farm monitoring device provided in Embodiment 2 of the present invention;

[0024] Figure 3 This is a schematic diagram of the structure of an electronic device that implements the wind farm monitoring method of this invention. Detailed Implementation

[0025] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0026] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0027] Example 1

[0028] Figure 1a This is a flowchart of a wind farm monitoring method provided in Embodiment 1 of the present invention. This embodiment is applicable to monitoring the power generation of a wind farm. The method can be executed by a wind farm monitoring device, which can be implemented in hardware and / or software. The wind farm monitoring device can be configured in the main control device of the wind farm. Figure 1a As shown, the method includes:

[0029] S110. Obtain the current radar monitoring flow field data and current SCADA data of the wind farm to be monitored.

[0030] The wind farm to be monitored can be any wind power plant whose power generation needs to be monitored. Current radar monitoring flow field data can refer to flow field data such as wind speed and direction, and can be collected by radar equipment installed at the wind farm. Current SCADA data can include current turbine operating data, such as yaw angle, speed, and pitch angle, and can be collected by various sensors installed on the turbine.

[0031] S120. Input the current radar monitoring flow field data into the pre-trained neural network to obtain the current three-dimensional transient flow field of the wind farm to be monitored; wherein, the pre-trained neural network is trained based on a pre-established flow field simulation library; the pre-established flow field simulation library is established based on at least one set of simulation data; each set of simulation data includes the unit design parameters, unit operating parameters, terrain parameters and flow field simulation values ​​under different operating conditions of the sample wind farm.

[0032] In this embodiment, the flow field can be reconstructed using a pre-trained neural network based on the current radar-monitored flow field data to obtain the current three-dimensional transient flow field. This embodiment can pre-establish a flow field simulation library under different operating conditions based on the turbines and terrain of the wind farm to be monitored, thereby training the neural network's flow field reconstruction capability based on the flow field simulation values ​​in the library.

[0033] In this embodiment, the relationship between the wind farm and the flow field truth database can be one-to-one, meaning each wind farm has a specific flow field simulation database. Unit design parameters can refer to the geometric shape and parameter information of all equipment, including the turbine blades, hub, nacelle, tower, and radiator. Unit operating parameters can refer to parameters such as yaw angle, speed, and pitch angle of the wind turbine within the cut-in and cut-out wind speed ranges and operating wind speed ranges. Terrain parameters can refer to parameters such as geographical location and terrain undulation. Operating condition parameters can include parameters such as wind speed, wind direction, turbulence value, and temperature.

[0034] In one alternative implementation, a pre-established flow field simulation library can be created in the following way:

[0035] The process involves acquiring the turbine parameters and terrain parameters of the wind farm to be monitored. The turbine parameters include turbine design parameters and turbine operating parameters. Based on the turbine parameters, flow field simulations are performed on the wind farm under different operating conditions corresponding to the terrain parameters to obtain the corresponding true values ​​of the flow field. The operating conditions include wind speed, wind direction, turbulence, and temperature. A pre-established flow field simulation library is built for the wind farm to be monitored based on the turbine parameters, terrain parameters, different operating conditions, and the true values ​​of the flow field corresponding to each operating condition.

[0036] In this embodiment, a high-precision CFD (Computational Fluid Dynamics) simulation library or LES (Large Eddy Simulation) simulation library can be established. Specifically, the wind farm's turbine design parameters, operating parameters, and terrain parameters can be input to perform large-scale simulations of the wind farm under specific site conditions. The covered operating conditions can include, for example, all wind speed ranges below the 50-year return period maximum wind speed, wind directions from 0-360°, inlet turbulence intensity range from 5% to the extreme turbulence maximum, and temperature ranges including the 50-year return period maximum and minimum temperatures.

[0037] In this embodiment, the pre-established flow field simulation library can be a flow field simulation library for the wind farm to be monitored. This means that a separate flow field library can be established for each wind farm. The advantage of this setup is that it improves the precision of the flow field simulation library.

[0038] In one alternative implementation, the pre-trained neural network can be trained as follows: current sample data is obtained from a pre-established flow field simulation library; wherein the current sample data includes current sample flow field simulation values; based on the current sample flow field simulation values, flow field reconstruction is performed using an initial neural network to obtain current sample flow field reconstruction values; a first type of error is determined between the current sample flow field reconstruction values ​​and the current sample flow field simulation values, and a second type of error is determined between the current sample flow field reconstruction values ​​and a specified physical equation; a specified physical equation is used to describe fluid motion; the network parameters of the initial neural network are optimized according to the first and second type of errors; and the pre-trained neural network is obtained after training the initial neural network using sample data from the pre-established flow field simulation library.

[0039] This embodiment can use the PINN (Physics-Informed Neural Networks) method to obtain a pre-trained neural network. Based on the PINN, after obtaining the reconstructed flow field value from the current sample flow field simulation value, the network parameters can be optimized using two types of errors. This setting can improve the accuracy of the neural network. The specified physical equation in this embodiment can be, for example, the Navier-Stokes equations.

[0040] Optionally, based on the current sample flow field simulation value, the flow field reconstruction value of the current sample can be obtained by reconstructing the flow field through an initial neural network. This may include: extracting feature data of the current sample flow field simulation value through an initial neural network; performing scale stretching on the feature data to obtain stretched feature data; and performing feature learning on the stretched feature data to obtain the current sample flow field reconstruction value.

[0041] This embodiment can introduce a scale stretching layer into the general PINN method to construct multi-scale flow features based on feature data, thereby increasing the amount of feature data.

[0042] Optionally, determining the first type of error between the current sample flow field reconstruction value and the current sample flow field simulation value may include: comparing the current sample flow field reconstruction value with the current sample flow field simulation value to obtain the first type of error; determining the second type of error between the current sample flow field reconstruction value and the specified physical equation may include: fitting the current sample flow field reconstruction value to the specified physical equation and determining the second type of error based on the fitting result.

[0043] In this embodiment, a first type of error can be constructed based on the error between the reconstructed flow field value and the sample flow field value, and a second type of error can be constructed based on the fitting error between the reconstructed flow field value and the Navier-Stokes equations.

[0044] S130. Based on the current three-dimensional transient flow field and the current SCADA data, analyze the abnormal conditions of the wind farm to be monitored in order to perform anomaly optimization.

[0045] This embodiment introduces SCADA feedback to analyze the unit's operating status in a timely manner, such as speed, pitch angle analysis, yaw analysis, and power generation analysis, thereby enabling anomaly diagnosis. For example, it can provide early warning of dangerous conditions and locate inefficient generating units.

[0046] Optionally, analyzing anomalies in the wind farm to be monitored for anomaly optimization may include optimizing the pre-trained neural network based on the analysis results.

[0047] Optionally, analyzing abnormal conditions in the wind farm to be monitored for anomaly optimization may include optimizing the turbine control strategy of the wind farm to be monitored based on the analysis results.

[0048] In this embodiment, a nacelle anemometer can be installed in the wind turbine nacelle as a wind measuring device. This device can be used to measure the wind direction and speed in the direction of incoming airflow in front of the wind turbine, as well as the temperature above the nacelle. The wind turbine tower and blades can be equipped with load monitoring devices to measure the stress on the wind turbine blades and the cumulative fatigue load.

[0049] The simulation results of the flow field cannot be completely accurate. If there is a large deviation between the actual measurement (flow field data in SCADA data) and the reconstructed flow field value, or if most units have deviations, the cause of the anomaly can be located in the neural network.

[0050] If the direction of the incoming flow from a certain unit in the reconstructed flow field deviates significantly from the wind direction measured by the anemometer in the engine room, such as more than 5° (or a larger quantitative indicator), check the approximate direction of the incoming wind under similar operating conditions of that unit in the simulation library. If it is similar to the reconstructed flow field, it proves that the neural network is performing well.

[0051] To check for problems in the simulation model, you can specifically locate the roughness model and whether the input is reasonable, and check whether the terrain geometry parameters are input reasonably, etc., one by one.

[0052] If the approximate direction of the downflow under similar operating conditions in the flow field simulation library is similar to that in the cabin simulation data, then the input of the neural network model should be checked first, for example, whether the training sample size is too small or the feature engineering is inadequate.

[0053] Attributing anomalies to the unit itself can occur when actual monitoring data is relatively accurate, but the unit's operating conditions do not match the reconstructed flow field. For example, some nacelle anemometers located above the nacelle may inaccurately measure the wind speed in front of the nacelle. The reconstructed flow field indicates that the wind speed in front of the turbine is 15 meters per second, meaning the turbine should be operating at full capacity. However, SCADA data shows that the turbine is not operating at low speed. In such cases, the anomaly can be attributed to the unit itself.

[0054] This embodiment accurately identifies downstream turbulent kinetic energy surge regions by reconstructing the three-dimensional transient flow field in real time, dynamically adjusting the upstream wind turbine yaw angle to reduce turbine wake losses and safety risks. By combining the reconstructed flow field characteristics with SCADA data, it quickly locates the root causes of power generation inefficiencies (such as abnormal control strategies or abnormal power curves). It can dynamically display the flow field conditions of various unit components, such as whether there are high-risk load conditions in the blade root region and flange region vorticity, and then determine whether to manually activate load reduction commands to reduce structural fatigue damage, especially under low-temperature conditions. It can optimize the unit control strategy to improve the overall availability and power generation of the entire plant.

[0055] To enable those skilled in the art to better understand the technical solution of this embodiment, Figure 1b This is a complete schematic diagram of a wind farm monitoring method provided in this embodiment. By acquiring the turbine parameters and terrain parameters of the wind farm, high-precision CFD simulations are performed under operating conditions based on these parameters to establish a true flow field database for different operating conditions. A neural network is used to extract features and process the true flow field data for learning and training. Physical model constraints are introduced to construct a loss equation (including radar measurement error and NS equation fitting error). The trained neural network obtains the reconstructed flow field value (i.e., the three-dimensional transient flow field) based on the turbine operating data. SCADA feedback is used for analyzing abnormal operating conditions, diagnosing anomalies or adjusting strategies, optimizing and adjusting the neural network model, and adjusting the simulation operating attitude.

[0056] The technical solution of this invention involves acquiring current radar-monitored flow field data and current SCADA data of the wind farm to be monitored; inputting the current radar-monitored flow field data into a pre-trained neural network to obtain the current three-dimensional transient flow field of the wind farm to be monitored; wherein, the pre-trained neural network is trained based on a pre-established flow field simulation library; the pre-established flow field simulation library is established based on at least one set of simulation data; each set of simulation data includes the turbine design parameters, turbine operating parameters, terrain parameters, and flow field simulation values ​​under different operating conditions of the sample wind farm; based on the current three-dimensional transient flow field and the current SCADA data, the abnormal conditions of the wind farm to be monitored are analyzed for anomaly optimization; the neural network is trained based on the flow field simulation values, and the flow field is reconstructed based on the radar-monitored flow field data using the trained neural network; thereby, the technical means of monitoring abnormal conditions of the wind farm to be monitored is achieved by using the reconstructed flow field and monitoring data. This solves the problem in the prior art where only wind turbine SCADA data is used to analyze the operating status of wind turbine units, making it difficult to intuitively and quickly determine the cause of unit inefficiency, and also unable to analyze the unit's operating environment problems. This provides a comprehensive analysis of the unit's operating environment and a rapid determination of the cause of wind farm unit inefficiency.

[0057] Example 2

[0058] Figure 2 This is a schematic diagram of a wind farm monitoring device provided in Embodiment 2 of the present invention. Figure 2 As shown, the device includes: a data acquisition module 210, a flow field reconstruction module 220, and an anomaly analysis module 230. Wherein:

[0059] Data acquisition module 210 is used to acquire the current radar monitoring flow field data and current SCADA data of the wind farm to be monitored;

[0060] The flow field reconstruction module 220 is used to input the current radar monitoring flow field data into a pre-trained neural network to obtain the current three-dimensional transient flow field of the wind farm to be monitored; wherein, the pre-trained neural network is trained based on a pre-established flow field simulation library; the pre-established flow field simulation library is established based on at least one set of simulation data; each set of simulation data includes the turbine design parameters, turbine operating parameters, terrain parameters, and flow field simulation values ​​under different operating conditions of the sample wind farm;

[0061] The abnormal situation analysis module 230 is used to analyze the abnormal situation of the wind farm to be monitored based on the current three-dimensional transient flow field and the current SCADA data in order to perform abnormal optimization.

[0062] The technical solution of this invention involves acquiring current radar monitoring flow field data and current SCADA data of the wind farm to be monitored; inputting the current radar monitoring flow field data into a pre-trained neural network to obtain the current three-dimensional transient flow field of the wind farm to be monitored; wherein, the pre-trained neural network is trained based on a pre-established flow field simulation library; the pre-established flow field simulation library is established based on at least one set of simulation data; each set of simulation data includes the turbine design parameters, turbine operating parameters, terrain parameters, and flow field simulation values ​​under different operating conditions of the sample wind farm; based on the current three-dimensional transient flow field and the current SCADA data, the abnormal situation of the wind farm to be monitored is analyzed for abnormal optimization; the neural network is trained based on the flow field simulation values, and the flow field is reconstructed based on the radar monitoring flow field data using the trained neural network; thereby, the reconstructed flow field and actual monitoring data are used to monitor the power generation of the wind farm to be monitored. This solves the problem in the prior art that only uses wind turbine SCADA data to analyze the operating status of wind turbine units, making it difficult to intuitively and quickly determine the cause of unit inefficiency, and also unable to analyze the unit's operating environment problems. This provides a comprehensive analysis of the unit's operating environment and a rapid determination of the cause of wind farm unit inefficiency.

[0063] Optionally, the wind farm monitoring device further includes a neural network training module, comprising:

[0064] The sample data acquisition unit is used to acquire current sample data from the pre-established flow field simulation library; wherein, the current sample data includes the current sample flow field simulation value;

[0065] The flow field reconstruction unit is used to reconstruct the current sample flow field based on the current sample flow field simulation value and obtain the current sample flow field reconstruction value through an initial neural network.

[0066] An error determination unit is used to determine a first type of error between the current sample flow field reconstruction value and the current sample flow field simulation value, and to determine a second type of error between the current sample flow field reconstruction value and a specified physical equation; the specified physical equation is used to describe fluid motion.

[0067] A network optimization unit is configured to optimize the network parameters of the initial neural network based on the first type of error and the second type of error.

[0068] The pre-trained neural network acquisition unit is used to obtain the pre-trained neural network after the initial neural network has been trained using sample data from a pre-established flow field simulation library.

[0069] Optional, flow field reconstruction unit, specifically can be used for:

[0070] Feature data of the current sample flow field simulation value is extracted using an initial neural network;

[0071] The feature data is stretched to obtain stretched feature data;

[0072] Feature learning is performed on the stretched feature data to obtain the current sample flow field reconstruction value.

[0073] Optional, the error determination unit can be used for:

[0074] The first type of error is obtained by comparing the reconstructed value of the current sample flow field with the simulated value of the current sample flow field.

[0075] The current sample flow field reconstruction value is fitted to the specified physical equation, and the second type of error is determined based on the fitting result.

[0076] Optionally, the pre-established flow field simulation library is the flow field simulation library of the wind farm to be monitored;

[0077] The wind farm monitoring device also includes a flow field simulation library establishment module, used for:

[0078] Obtain the turbine parameters and terrain parameters of the wind farm to be monitored; wherein, the turbine parameters include turbine design parameters and turbine operating parameters;

[0079] Based on the unit parameters, flow field simulations are performed on the wind farm to be monitored under different operating conditions corresponding to the terrain parameters to obtain the corresponding true values ​​of the flow field; wherein, the operating conditions include wind speed, wind direction, turbulence and temperature;

[0080] Based on the unit parameters, the terrain parameters, the different operating condition parameters, and the true values ​​of each flow field corresponding to the different operating condition parameters, a pre-established flow field simulation library is established for the wind farm to be monitored.

[0081] Optional, the anomaly analysis module 230 can be used for:

[0082] The pre-trained neural network is optimized based on the analysis results.

[0083] Optional, the anomaly analysis module 230 can be used for:

[0084] Based on the analysis results, the unit control strategy of the wind farm to be monitored is optimized.

[0085] The wind farm monitoring device provided in this embodiment of the invention can execute the wind farm monitoring method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0086] Example 3

[0087] Figure 3A schematic diagram of an electronic device 300 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers or various forms of mobile devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0088] like Figure 3 As shown, the electronic device 300 includes at least one processor 301 and a memory, such as a read-only memory (ROM) 302 or a random access memory (RAM) 303, communicatively connected to the at least one processor 301. The memory stores computer programs executable by the at least one processor. The processor 301 can perform various appropriate actions and processes based on the computer program stored in the ROM 302 or loaded into the RAM 303 from storage unit 308. The RAM 303 can also store various programs and data required for the operation of the electronic device 300. The processor 301, ROM 302, and RAM 303 are interconnected via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0089] Multiple components in electronic device 300 are connected to I / O interface 305, including: input unit 306, such as keyboard, mouse, etc.; output unit 307, such as various types of displays, speakers, etc.; storage unit 308, such as disk, optical disk, etc.; and communication unit 309, such as network card, modem, wireless transceiver, etc. Communication unit 309 allows electronic device 300 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0090] Processor 301 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 301 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 301 performs the various methods and processes described above, such as wind farm monitoring methods.

[0091] In some embodiments, the wind farm monitoring method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 308. In some embodiments, part or all of the computer program may be loaded into and / or installed on electronic device 300 via ROM 302 and / or communication unit 309. When the computer program is loaded into RAM 303 and executed by processor 301, one or more steps of the wind farm monitoring method described above may be performed. Alternatively, in other embodiments, processor 301 may be configured to perform the wind farm monitoring method by any other suitable means (e.g., by means of firmware).

[0092] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0093] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0094] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0095] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0096] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0097] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0098] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0099] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for monitoring wind farms, characterized in that, include: Acquire the current radar monitoring flow field data and current SCADA data of the wind farm to be monitored; The current radar-monitored flow field data is input into a pre-trained neural network to obtain the current three-dimensional transient flow field of the wind farm to be monitored; wherein, the pre-trained neural network is trained based on a pre-established flow field simulation library; the pre-established flow field simulation library is established based on at least one set of simulation data; each set of simulation data includes the turbine design parameters, turbine operating parameters, terrain parameters, and flow field simulation values ​​under different operating conditions of the sample wind farm; Based on the current three-dimensional transient flow field and the current SCADA data, analyze the abnormal conditions of the wind farm to be monitored in order to perform anomaly optimization.

2. The method according to claim 1, characterized in that, The pre-trained neural network is trained in the following way: Obtain current sample data from the pre-established flow field simulation library; wherein, the current sample data includes the current sample flow field simulation value; Based on the current sample flow field simulation value, the flow field reconstruction value of the current sample flow field is obtained by reconstructing the flow field through the initial neural network; The first type of error between the current sample flow field reconstruction value and the current sample flow field simulation value is determined, and the second type of error between the current sample flow field reconstruction value and the specified physical equation is determined; the specified physical equation is used to describe fluid motion. The network parameters of the initial neural network are optimized based on the first type of error and the second type of error; The pre-trained neural network is obtained after training the initial neural network with sample data from a pre-established flow field simulation library.

3. The method according to claim 2, characterized in that, Based on the current sample flow field simulation values, the flow field reconstruction values ​​are obtained by reconstructing the current sample flow field through an initial neural network, including: Feature data of the current sample flow field simulation value is extracted using an initial neural network; The feature data is stretched to obtain stretched feature data; Feature learning is performed on the stretched feature data to obtain the current sample flow field reconstruction value.

4. The method according to claim 2, characterized in that, Determining the first type of error between the current sample flow field reconstruction value and the current sample flow field simulation value includes: The first type of error is obtained by comparing the reconstructed value of the current sample flow field with the simulated value of the current sample flow field. Determining the Type II error between the current sample flow field reconstruction value and the specified physical equation includes: The current sample flow field reconstruction value is fitted to the specified physical equation, and the second type of error is determined based on the fitting result.

5. The method according to claim 2, characterized in that, The pre-established flow field simulation library is the flow field simulation library of the wind farm to be monitored; The pre-established flow field simulation library is established in the following way: Obtain the turbine parameters and terrain parameters of the wind farm to be monitored; wherein, the turbine parameters include turbine design parameters and turbine operating parameters; Based on the unit parameters, flow field simulations are performed on the wind farm to be monitored under different operating conditions corresponding to the terrain parameters to obtain the corresponding true values ​​of the flow field; wherein, the operating conditions include wind speed, wind direction, turbulence and temperature; Based on the unit parameters, the terrain parameters, the different operating condition parameters, and the true values ​​of each flow field corresponding to the different operating condition parameters, a pre-established flow field simulation library is established for the wind farm to be monitored.

6. The method according to claim 1, characterized in that, Analyze the abnormal conditions of the wind farm to be monitored for anomaly optimization, including: The pre-trained neural network is optimized based on the analysis results.

7. The method according to claim 1, characterized in that, Analyze the abnormal conditions of the wind farm to be monitored for anomaly optimization, including: Based on the analysis results, the unit control strategy of the wind farm to be monitored is optimized.

8. A wind farm monitoring device, characterized in that, include: The data acquisition module is used to acquire the current radar monitoring flow field data and current SCADA data of the wind farm to be monitored. The flow field reconstruction module is used to input the current radar-monitored flow field data into a pre-trained neural network to obtain the current three-dimensional transient flow field of the wind farm to be monitored; wherein, the pre-trained neural network is trained based on a pre-established flow field simulation library; the pre-established flow field simulation library is established based on at least one set of simulation data; each set of simulation data includes the turbine design parameters, turbine operating parameters, terrain parameters, and flow field simulation values ​​under different operating conditions of the sample wind farm; The power generation analysis module is used to analyze the abnormal conditions of the wind farm to be monitored based on the current three-dimensional transient flow field and the current SCADA data, so as to perform anomaly optimization.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the wind farm monitoring method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the wind farm monitoring method according to any one of claims 1-7.

Images