Fan blade lightning stroke monitoring system, method, device, equipment, medium and product

Abstract

The invention relates to the technical field of electronics, and discloses a fan blade lightning stroke monitoring system, method, device and equipment, a medium and a product. The system comprises an electric field sensor, an acoustic sensor, a vibration sensor and a lightning stroke monitoring module; sound wave data in the environment where the fan blade is located is collected through the acoustic sensor, vibration data of the fan blade is collected based on the vibration sensor, the lightning stroke condition of the fan blade is recognized through the lightning stroke monitoring module according to the electric field data, the sound wave data and the vibration data, and the lightning stroke recognition result of the fan blade is obtained. High-precision and real-time monitoring of the lightning stroke of the fan blade is realized, and a reliable basis is provided for taking maintenance measures in time.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of electronics, in particular to a fan blade lightning strike monitoring system, method, device, equipment, medium and product. BACKGROUND

[0002] The fan is prone to lightning strikes due to its high structure and open environment during operation. The fan blade, as a key component of the fan, will be damaged by lightning strikes, causing the fan to be out of operation for a long time and seriously affecting the power generation benefit of the wind farm. Therefore, monitoring the lightning damage of the fan blade can help to find problems in the fan and maintain the fan blade as soon as possible. At present, the electrical parameters of each fan are monitored in the background, and the fan blade is maintained when the fan operation is abnormal, which cannot monitor the situation of the fan blade when it is struck by lightning. SUMMARY

[0003] Therefore, the present application provides a fan blade lightning strike monitoring system, method, device, equipment, medium and product to solve the problem that the situation of the fan blade when it is struck by lightning cannot be monitored in time in the related art.

[0004] In a first aspect, the present application provides a fan blade lightning strike monitoring system, comprising: an electric field sensor, an acoustic sensor, a vibration sensor and a lightning strike monitoring module; the electric field sensor is arranged at a first preset position of the fan blade and is used to collect electric field data in the environment of the fan blade; the acoustic sensor is arranged at a second preset position of the fan blade and is used to collect acoustic wave data in the environment of the fan blade; the vibration sensor is arranged at a third preset position of the fan blade and is used to collect vibration data of the fan blade; the lightning strike monitoring module is connected with the electric field sensor, the acoustic sensor and the vibration sensor respectively, and is used to identify the lightning strike situation of the fan blade according to the electric field data, the acoustic wave data and the vibration data to obtain a lightning strike identification result of the fan blade.

[0005] The fan blade lightning strike monitoring system provided by the present application comprises: an electric field sensor, an acoustic sensor, a vibration sensor and a lightning strike monitoring module. The electric field data in the environment of the fan blade is collected by the electric field sensor, the acoustic wave data in the environment of the fan blade is collected by the acoustic sensor, the vibration data of the fan blade is collected based on the vibration sensor, and the lightning strike situation of the fan blade is identified by the lightning strike monitoring module according to the electric field data, the acoustic wave data and the vibration data to obtain a lightning strike identification result of the fan blade, thereby realizing high-precision and real-time monitoring of the lightning strike of the fan blade and providing a reliable basis for timely maintenance measures.

[0006] In an optional embodiment, the system further comprises a warning module; the warning module is connected with the lightning strike monitoring module and is used to generate an alarm information based on the lightning strike identification result.

[0007] In a second aspect, the present application provides a wind turbine blade lightning strike monitoring method, applied to the wind turbine blade lightning strike monitoring system of the first aspect or the corresponding embodiments thereof, the method comprising: acquiring electric field data in an environment where the wind turbine blade is located, sound wave data in the environment where the wind turbine blade is located, and vibration data of the wind turbine blade; performing feature extraction on the electric field data, the sound wave data, and the vibration data respectively to obtain first features of the electric field data, second features of the sound wave data, and third features of the vibration data; inputting the first features, the second features, and the third features into a pre-constructed blade lightning strike probability recognition model to make the blade lightning strike probability recognition model output a target probability of the wind turbine blade suffering from lightning strike; determining whether the wind turbine blade has encountered lightning strike based on the target probability to obtain a lightning strike recognition result of the wind turbine blade.

[0008] The wind turbine blade lightning strike monitoring method provided by the present application performs feature extraction on the electric field data, the sound wave data, and the vibration data respectively to obtain first features of the electric field data, second features of the sound wave data, and third features of the vibration data; inputs the first features, the second features, and the third features into a pre-constructed blade lightning strike probability recognition model to make the blade lightning strike probability recognition model output a target probability of the wind turbine blade suffering from lightning strike; determines whether the wind turbine blade has encountered lightning strike based on the target probability to obtain a lightning strike recognition result of the wind turbine blade. The method provided by the present application extracts features from the electric field data, the sound wave data, and the vibration data, inputs the extracted features into a pre-constructed blade lightning strike probability recognition model to make the blade lightning strike probability recognition model output a target probability of the wind turbine blade suffering from lightning strike, determines whether the wind turbine blade has encountered lightning strike based on the target probability to obtain a lightning strike recognition result of the wind turbine blade, and realizes high-precision and real-time monitoring of wind turbine blade lightning strike, thereby providing a reliable basis for timely maintenance measures.

[0009] In an optional embodiment, the step of determining whether the wind turbine blade has encountered lightning strike based on the target probability to obtain a lightning strike recognition result of the wind turbine blade comprises: if the target probability is greater than a preset threshold, determining that the wind turbine blade has encountered lightning strike; and if the target probability is less than or equal to the preset threshold, determining that the wind turbine blade has not encountered lightning strike.

[0010] In an optional embodiment, the method further comprises: if the wind turbine blade has encountered lightning strike, determining a lightning current characteristic parameter value based on the electric field data, determining a sound pressure level based on the sound wave data, and determining a vibration peak acceleration based on the vibration data; and determining a severity level of the lightning strike encountered by the wind turbine blade based on the lightning current characteristic parameter value, the sound pressure level, and the vibration peak acceleration.

[0011] In an optional implementation, the blade lightning strike probability identification model is constructed by the following steps: obtaining a blade state data set and lightning strike probabilities of each blade state data in the blade state data set, the blade state data being obtained by feature extraction on electric field data in an environment where the fan blade is located, sound wave data in the environment where the fan blade is located, and vibration data of the fan blade; associating each blade state data with the lightning strike probability to obtain an association data set; and training a preset machine learning model using the association data set to obtain the blade lightning strike probability identification model.

[0012] In a third aspect, the present application provides a fan blade lightning strike monitoring device applied to the fan blade lightning strike monitoring system of the first aspect or the corresponding implementation thereof, the device comprising: an acquisition module configured to acquire electric field data in an environment where a fan blade is located, sound wave data in the environment where the fan blade is located, and vibration data of the fan blade; a feature extraction module configured to perform feature extraction on the electric field data, the sound wave data, and the vibration data respectively to obtain first features of the electric field data, second features of the sound wave data, and third features of the vibration data; an identification module configured to input the first features, the second features, and the third features into a pre-constructed blade lightning strike probability identification model to cause the blade lightning strike probability identification model to output a target probability of the fan blade suffering from lightning strike; and a first determination module configured to determine whether the fan blade has encountered lightning strike based on the target probability to obtain a lightning strike identification result of the fan blade.

[0013] In a fourth aspect, the present application 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 computer instructions to perform the fan blade lightning strike monitoring method of the first aspect or any of the corresponding implementations thereof.

[0014] In a fifth aspect, the present application provides a computer readable storage medium storing computer instructions, the computer instructions being configured to cause a computer to perform the fan blade lightning strike monitoring method of the first aspect or any of the corresponding implementations thereof.

[0015] In a sixth aspect, the present application provides a computer program product comprising computer instructions configured to cause a computer to perform the fan blade lightning strike monitoring method of the first aspect or any of the corresponding implementations thereof. BRIEF DESCRIPTION OF DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the specific embodiments or the prior art of the present application, the drawings required to be used in the specific embodiments or the prior art description will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0017] Figure 1 is a principle block diagram of a fan blade lightning strike monitoring system according to an embodiment of the present application; Figure 2 is a flowchart of a fan blade lightning strike monitoring method according to an embodiment of the present application; Figure 3 is a flowchart of a fan blade lightning strike monitoring method according to an embodiment of the present application; Figure 4 is a structural block diagram of a fan blade lightning strike monitoring device according to an embodiment of the present application; Figure 5 is a hardware structure schematic diagram of a computer device of an embodiment of the present application. DETAILED DESCRIPTION

[0018] In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0019] In the related art, the electrical parameters of the operation of each fan are generally monitored in the background. When the operation of the fan is monitored to be abnormal, the fan blade is maintained. The situation of the fan blade when suffering from lightning strike cannot be monitored in time.

[0020] Therefore, an embodiment of the present application provides a fan blade lightning strike monitoring system. The electric field data in the environment where the fan blade is located is collected through an electric field sensor. The sound wave data in the environment where the fan blade is located is collected through an acoustic sensor. The vibration data of the fan blade is collected based on a vibration sensor. The lightning strike situation of the fan blade is identified by a lightning strike monitoring module according to the electric field data, the sound wave data and the vibration data. The lightning strike identification result of the fan blade is obtained. High-precision and real-time monitoring of the lightning strike of the fan blade is realized. A reliable basis is provided for timely maintenance measures.

[0021] In the present embodiment, a fan blade lightning strike monitoring system is provided, Figure 1 is a principle block diagram of a fan blade lightning strike monitoring system according to an embodiment of the present application, asFigure 1 As shown, the system comprises: an electric field sensor 101, an acoustic sensor 102, a vibration sensor 103, and a lightning strike monitoring module 104. The electric field sensor 101 is arranged at a first preset position of the fan blade, and is configured to collect electric field data in an environment where the fan blade is located.

[0022] Exemplarily, the electric field sensor 101 is a device for detecting the electric field intensity and its change in space. In the fan blade lightning strike monitoring system, it provides a key signal for lightning strike event judgment by capturing the instantaneous strong electric field disturbance when lightning strikes. The electric field data can be an electric signal collected by the electric field sensor. The electric field sensor 101 can include but is not limited to a capacitive electric field sensor. The capacitive electric field sensor is composed of a capacitor formed by two polar plates. Under the action of an external electric field, an electric charge proportional to the electric field intensity is induced on the polar plate. The electric field intensity can be deduced by measuring the change of the electric charge. In the embodiment of the present application, the first preset position needs to be close to the lightning-prone area of the blade (such as the blade tip and the edge), while avoiding mechanical damage of the sensor caused by the movement of the blade itself (such as waving and twisting). When installing, the sensor sensing surface is ensured to face the “possible lightning strike path” (such as perpendicular to the blade surface, which is convenient for capturing the space electric field). The specific content of the first preset position is not limited in the embodiment of the present application, and can be determined according to the needs by those skilled in the art.

[0023] The acoustic sensor 102 is arranged at a second preset position of the fan blade, and is configured to collect acoustic data in an environment where the fan blade is located.

[0024] Exemplarily, the acoustic sensor 102 provides a key signal in the “sound dimension” for lightning strike event judgment by capturing the instantaneous impact sound wave when lightning strikes, which is complementary to the electric field (electromagnetic characteristics) and vibration (mechanical impact) signals. The acoustic sensor 102 can include but is not limited to a microphone, a sonar sensor, etc. When lightning occurs, the strong discharge between the cloud layer and the blade will cause violent air ionization and explosion, generating instantaneous strong impact sound waves (thunder). The frequency usually covers a wide frequency range (from low frequency to high frequency), and the intensity is much higher than the environmental noise (such as blade rotation sound, wind sound, equipment running sound, etc.) during normal operation of the fan. The acoustic sensor detects this “specific sound signal” and converts it into an electric signal that can be analyzed, providing a basis for lightning strike judgment. The second preset position needs to be close to the lightning-prone area of the blade (such as the blade tip and the edge), but should not be directly exposed to the airflow impact path of the blade rotation (to reduce wind noise interference); the second preset position can be the blade root or a position close to the blade inside the cabin, which takes into account signal capture and anti-interference (the signal-to-noise ratio of different positions needs to be tested to select the optimal installation point).

[0025] The vibration sensor 103 is arranged at a third preset position of the fan blade, and is configured to collect vibration data of the fan blade.

[0026] Exemplarily, the vibration sensor 103 provides a key signal of "mechanical dimension" for lightning strike event judgment by capturing the instantaneous mechanical impact vibration caused by lightning strike on the blade. The vibration sensor 103 can include but is not limited to a piezoelectric vibration sensor and a capacitive vibration sensor. The third preset position can be a part of the blade that is easy to be struck by lightning and has good vibration transmission (such as a blade tip or a rigid area in the middle of the blade), ensuring that the lightning impact can be effectively transmitted to the sensor (avoiding installation in a flexible area to cause signal attenuation); at the same time, it is far away from the "natural vibration node" of the blade rotation (these positions have weak normal vibration, which can mask the lightning vibration). When installed, it needs to be firmly fixed (such as bolt fastening) to avoid the interference of the vibration of the sensor itself on the measurement. The vibration data can be an electrical signal converted by the vibration sensor through the change of the distance between the plates caused by vibration.

[0027] Specifically, during the manufacturing or maintenance of the fan blade, the electric field sensor, the acoustic sensor and the vibration sensor are accurately installed at the predetermined positions of the blade according to the design requirements. It is ensured that the sensor is installed firmly, has good contact with the surface of the blade, and at the same time, it is ensured that the signal transmission line of the sensor is connected correctly and has good shielding performance, avoiding the influence of external interference on signal acquisition.

[0028] The lightning monitoring module 104 is connected with the electric field sensor 101, the acoustic sensor 102 and the vibration sensor 103 respectively, and is used for identifying the lightning strike condition of the fan blade according to the electric field data, the acoustic wave data and the vibration data, to obtain the lightning strike identification result of the fan blade.

[0029] Exemplarily, in the embodiment of the application, the alarm threshold values corresponding to the electric field data, the acoustic wave data and the vibration data are obtained, and if at least two of the electric field data, the acoustic wave data and the vibration data are greater than the corresponding alarm threshold values, it is determined that the fan blade is struck by lightning.

[0030] The fan blade lightning monitoring system provided by the embodiment includes an electric field sensor, an acoustic sensor, a vibration sensor and a lightning monitoring module. The electric field data in the environment where the fan blade is located is collected by the electric field sensor, the acoustic wave data in the environment where the fan blade is located is collected by the acoustic sensor, the vibration data of the fan blade is collected based on the vibration sensor, and the lightning monitoring module is used to identify the lightning strike condition of the fan blade according to the electric field data, the acoustic wave data and the vibration data, to obtain the lightning strike identification result of the fan blade, so as to realize high-precision and real-time monitoring of the lightning strike of the fan blade and provide a reliable basis for timely maintenance measures.

[0031] In some optional embodiments, the system further includes a warning module; the warning module is connected with the lightning monitoring module and is used for generating alarm information based on the lightning identification result.

[0032] Exemplarily, in the embodiment of the present application, when it is determined that the fan blade is struck by lightning, the pre-warning module is triggered to generate alarm information to inform the operation and maintenance personnel, and the lightning strike condition can be further confirmed in combination with other information, such as meteorological data.

[0033] According to the embodiment of the present application, a fan blade lightning strike monitoring method embodiment 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 the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that here.

[0034] In the embodiment, a fan blade lightning strike monitoring method is also provided, which can be used in the fan blade lightning strike monitoring system described above, Figure 2 is a flowchart of the fan blade lightning strike monitoring method according to the embodiment of the present application, as Figure 2 shown, the flow includes the following steps: Step S201, obtaining electric field data in the environment where the fan blade is located, sound wave data in the environment where the fan blade is located, and vibration data of the fan blade. Exemplarily, for specific descriptions related to the above embodiments, details are not repeated here.

[0035] Step S202, respectively extracting features of the electric field data, the sound wave data and the vibration data to obtain first features of the electric field data, second features of the sound wave data and third features of the vibration data.

[0036] Exemplarily, in the embodiment of the present application, the time domain feature extraction algorithm and the frequency domain feature extraction algorithm are combined to extract features of the electric field data, the sound wave data and the vibration data. The specific way of feature extraction in the embodiment of the present application is not limited, and the person skilled in the art can determine it according to the needs.

[0037] Step S203, inputting the first features, the second features and the third features into a pre-constructed blade lightning strike probability recognition model to make the blade lightning strike probability recognition model output a target probability of the fan blade being struck by lightning.

[0038] Exemplarily, the blade lightning strike probability identification model is used to represent the association between the first feature, the second feature, the third feature and the target probability. In the embodiment of the present application, the blade lightning strike probability identification model can be obtained by constructing a machine learning model. The first feature is extracted by collecting the preset electric field sensor in the blade. When the lightning current passes through, the electric field sensor collects the magnetic field induced current and transmits it to the module to obtain the first feature. The second feature is extracted by collecting the preset acoustic sensor in the blade. The lightning sound wave is collected and converted into a digital signal and transmitted to the module to obtain the second feature. The third feature is extracted by collecting the preset vibration sensor in the blade. The impact generated by the lightning strike is collected by the preset vibration sensor in the blade, and the vibration signal is converted into a digital signal and transmitted to the module to obtain the third feature.

[0039] Step S204, judging whether the fan blade is struck by lightning based on the target probability to obtain the lightning strike identification result of the fan blade.

[0040] Exemplarily, in the embodiment of the present application, if the target probability is greater than the preset probability threshold, it is considered that the fan blade is struck by lightning. The specific content of the preset probability threshold is not limited in the embodiment of the present application, and can be determined by the person skilled in the art according to the requirement.

[0041] The fan blade lightning strike monitoring method provided in the embodiment extracts the features from the electric field data, the sound wave data and the vibration data, inputs the extracted features into the blade lightning strike probability identification model constructed in advance, so that the blade lightning strike probability identification model outputs the target probability of the fan blade struck by lightning. The target probability is used to judge whether the fan blade is struck by lightning, and the lightning strike identification result of the fan blade is obtained. The high-precision and real-time monitoring of the fan blade lightning strike is realized, and reliable basis is provided for timely maintenance measures.

[0042] In the embodiment, a fan blade lightning strike monitoring method is provided, which can be used in the fan blade lightning strike monitoring system described above, Figure 3 is a flowchart of the fan blade lightning strike monitoring method according to the embodiment of the present application, as shown in Figure 3 , the flowchart includes the following steps: Step S301, obtaining the electric field data in the environment where the fan blade is located, the sound wave data in the environment where the fan blade is located and the vibration data of the fan blade. For details, please refer to the step S101 of the embodiment shown in Figure 1 , which will not be repeated here.

[0043] Step S302, respectively extracting the features of the electric field data, the sound wave data and the vibration data to obtain the first feature of the electric field data, the second feature of the sound wave data and the third feature of the vibration data.

[0044] Step S303, inputting the first feature, the second feature, and the third feature into a pre-constructed blade lightning strike probability recognition model, so that the blade lightning strike probability recognition model outputs a target probability of the wind turbine blade suffering from lightning strike.

[0045] In some optional embodiments, the blade lightning strike probability recognition model is constructed through the following steps: Step a1, obtaining a blade state data set and lightning strike probabilities of each blade state data in the blade state data set, the blade state data being obtained by feature extraction on electric field data in an environment where the wind turbine blade is located, sound wave data in the environment where the wind turbine blade is located, and vibration data of the wind turbine blade.

[0046] Illustratively, in the embodiments of the present application, the lightning strike probability corresponding to each blade state data can be determined by analyzing historical data. The electric field data in an environment where the wind turbine blade is located, the sound wave data in the environment where the wind turbine blade is located, and the vibration data of the wind turbine blade are subjected to feature extraction, and the feature extraction results are taken as the blade state data.

[0047] Step a2, associating each blade state data with the lightning strike probability to obtain an association data set.

[0048] Illustratively, the specific association method is not limited in the embodiments of the present application, as long as it is reasonable.

[0049] Step a3, training a pre-set machine learning model using the association data set to obtain the blade lightning strike probability recognition model.

[0050] Illustratively, the pre-set machine learning model is trained using the association data set until the accuracy of the model meets a pre-set requirement to obtain the blade lightning strike probability recognition model. The pre-set requirement can be determined according to requirements, and the embodiments of the present application do not limit this.

[0051] Step S304, determining whether the wind turbine blade suffers from lightning strike based on the target probability to obtain a lightning strike recognition result of the wind turbine blade.

[0052] Specifically, the above step S304 includes: Step S3041, if the target probability is greater than a pre-set threshold, it is determined that the wind turbine blade suffers from lightning strike.

[0053] Step S3042, if the target probability is less than or equal to the pre-set threshold, it is determined that the wind turbine blade does not suffer from lightning strike.

[0054] Illustratively, the pre-set threshold can be determined according to actual requirements, and the embodiments of the present application do not limit this.

[0055] In some optional embodiments, the method further includes: Step b1, if the fan blade is struck by lightning, the characteristic parameter value of lightning current is determined based on the electric field data, the sound pressure level is determined based on the sound wave data, and the peak vibration acceleration is determined based on the vibration data.

[0056] Exemplarily, in the embodiment of the present application, the electric field data includes lightning current values at multiple time nodes, the lightning current characteristic parameter value is determined by analyzing the lightning current values at the multiple time nodes; the core of determining the sound pressure level (SPL) according to the sound wave data is to convert the electric signal (such as voltage) collected by the acoustic sensor into sound pressure, and then calculate its relative quantity (decibel, dB) through the definition formula of the sound pressure level. When determining the peak vibration acceleration (PeakAcceleration) according to the vibration data, the electric signal (such as voltage) collected by the vibration sensor is converted into the acceleration physical quantity, and then the maximum absolute value in the effective time window is extracted to obtain the peak vibration acceleration.

[0057] Step b2, determining the severity level of the fan blade struck by lightning based on the lightning current characteristic parameter value, the sound pressure level and the peak vibration acceleration.

[0058] Exemplarily, in the embodiment of the present application, the specific grade threshold is set in combination with the industry standard and the historical damage data, and the severity level of the fan blade struck by lightning is determined according to the set grade threshold and the lightning current characteristic parameter value, the sound pressure level and the peak vibration acceleration.

[0059] In the embodiment, a fan blade lightning strike monitoring device is also provided, which is used to implement the above-mentioned embodiments and preferred embodiments, and will not be described again. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware, or a combination of software and hardware is also possible and contemplated.

[0060] The embodiment provides a fan blade lightning strike monitoring device, as shown in Figure 4 , comprising: An acquisition module 401 is configured to acquire electric field data in an environment where a fan blade is located, sound wave data in the environment where the fan blade is located, and vibration data of the fan blade. A feature extraction module 402 is configured to perform feature extraction on the electric field data, the sound wave data and the vibration data respectively to obtain a first feature of the electric field data, a second feature of the sound wave data and a third feature of the vibration data. An identification module 403 is configured to input the first feature, the second feature and the third feature into a pre-constructed blade lightning strike probability identification model, so that the blade lightning strike probability identification model outputs a target probability of the fan blade being struck by lightning. The first determination module 404 is configured to determine whether the wind turbine blade is struck by lightning based on the target probability, and obtain a lightning strike identification result of the wind turbine blade.

[0061] In some optional embodiments, the first determination module 404 includes: A first determination sub-module configured to determine that the wind turbine blade is struck by lightning if the target probability is greater than a preset threshold value. A second determination sub-module configured to determine that the wind turbine blade is not struck by lightning if the target probability is less than or equal to the preset threshold value.

[0062] In some optional embodiments, the apparatus further includes: A second determination module configured to determine a lightning current characteristic parameter value based on the electric field data, determine a sound pressure level based on the sound wave data, and determine a vibration peak acceleration based on the vibration data if the wind turbine blade is struck by lightning. A third determination module configured to determine a severity level of the wind turbine blade struck by lightning based on the lightning current characteristic parameter value, the sound pressure level, and the vibration peak acceleration.

[0063] In some optional embodiments, the blade lightning strike probability identification model is obtained by the following steps: Obtaining a blade state data set and a lightning strike probability of each blade state data in the blade state data set, wherein the blade state data is obtained by feature extraction on the electric field data in an environment where the wind turbine blade is located, the sound wave data in the environment where the wind turbine blade is located, and the vibration data of the wind turbine blade. Associating each blade state data with the lightning strike probability to obtain an association data set. Training a preset machine learning model using the association data set to obtain the blade lightning strike probability identification model.

[0064] Further function descriptions of each of the above modules and units are the same as those of the corresponding embodiments described above, and will not be described here.

[0065] The wind turbine blade lightning strike monitoring apparatus in the present embodiment is presented in the form of functional units. The units herein refer to ASIC (Application Specific Integrated Circuit) circuits, processors and memories executing one or more software or fixed programs, and / or other devices that can provide the above functions.

[0066] The present embodiment also provides a computer device with the wind turbine blade lightning strike monitoring apparatus described above. Figure 4 as shown in the accompanying drawings.

[0067] Please refer to Figure 5 , Figure 5 is a structural schematic diagram of a computer device provided by an optional embodiment of the present application, as shown in the accompanying drawings.Figure 5 As shown, the computer device includes one or more processors 10, memory 20, and interfaces 30 for the various components to communicate with one another. The various components communicate through one or more buses, and can be mounted on a common motherboard or in other manners as appropriate. The processor 10 can execute instructions, for example, stored in the memory 20 or elsewhere to implement processes that the computer device is designed to perform, for example, the processes of the various embodiments described herein. The computer device also includes one or more mass storage devices 40 for storing data files such as an operating system, application programs, and data. The mass storage device 40 can be connected via a mass storage interface 50 or other suitable interface to one or more buses. The computer device also includes one or more input devices 60, for example, a keyboard, mouse, pen, voice input device, etc. The computer device also includes one or more output devices 70, for example, a display screen, speakers, etc. One specific computer device for which the embodiments described herein can be implemented is a server computer device, for example, a server computer device in a server array, a group of blade server computers, or a multi-processor system. Figure 5 The processor 10 is used as an example in the following description.

[0068] The processor 10 can be a central processing unit, a network processing unit, or a combination thereof. The processor 10 can further include a hardware chip. The hardware chip can be an application specific integrated circuit, a programmable logic device, or a combination thereof. The programmable logic device can be a complex programmable logic device, a field programmable logic device, a general array logic, or any combination thereof.

[0069] The memory 20 stores instructions that are executable by the at least one processor 10, so as to enable the at least one processor 10 to perform the method shown in the above embodiments.

[0070] The memory 20 can include a program storage area and a data storage area. The program storage area can store an operating system, application programs required by at least one function, etc. The data storage area can store data created according to the use of the computer device, etc. In addition, the memory 20 can include a high-speed random access memory, and can further include a non-transitory memory, for example, at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state memory device. In some alternative embodiments, the memory 20 can optionally include a memory that is remotely arranged with respect to the processor 10, and these remote memories can be connected to the computer device through a network. Examples of the network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0071] The memory 20 can include a volatile memory, for example, a random access memory; the memory can also include a non-volatile memory, for example, a flash memory, a hard disk, or a solid-state disk; and the memory 20 can further include a combination of the above-mentioned kinds of memories.

[0072] The computer device further includes a communication interface 30 for the computer device to communicate with other devices or communication networks.

[0073] The embodiments of the present application further provide a computer readable storage medium, and the method according to the embodiments of the present application can be implemented in hardware, firmware, or recorded in a storage medium, or stored in a remote storage medium or a non-transitory machine readable storage medium and downloaded to a local storage medium through network, so that the method described herein can be processed by such software on a storage medium using a general purpose computer, a special purpose processor, or programmable or special hardware. The storage medium can be a magnetic disk, an optical disk, a read-only memory, a random access memory, a flash memory, a hard disk, or a solid state disk, etc. Further, the storage medium can also include a combination of the above-mentioned memories. It can be understood that the computer, the processor, the microprocessor controller, or the 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 the computer, the processor, or the hardware, the method shown in the above embodiments is implemented.

[0074] Part of the present application can be applied as a computer program product, for example, computer program instructions, when executed by a computer, through the operation of the computer, the method and / or technical solutions according to the present application can be invoked or provided. Those skilled in the art should understand that the form of computer program instructions in a computer readable medium includes but is not limited to source files, executable files, installation package files, etc. Correspondingly, the way of executing computer program instructions by computer includes but is not limited to: the computer directly executes the instructions, or the computer compiles the instructions and then executes the corresponding compiled program, or the computer reads and executes the instructions, or the computer reads and installs the instructions and then executes the corresponding installed program. Here, the computer readable medium can be any available computer readable storage medium or communication medium accessible to the computer.

[0075] Although the embodiments of the present application are described in conjunction with the accompanying drawings, various modifications and changes can be made by those skilled in the art without departing from the spirit and scope of the present application, and such modifications and changes fall within the scope defined by the appended claims.

Claims

1. A wind turbine blade lightning strike monitoring system, characterized in that, The system includes: an electric field sensor, an acoustic sensor, a vibration sensor, and a lightning strike monitoring module; The electric field sensor is set at a first preset position on the wind turbine blade and is used to collect electric field data in the environment where the wind turbine blade is located. The acoustic sensor is set at the second preset position on the wind turbine blade and is used to collect sound wave data in the environment where the wind turbine blade is located. The vibration sensor is set at the third preset position on the wind turbine blade and is used to collect vibration data of the wind turbine blade. The lightning strike monitoring module is connected to the electric field sensor, the acoustic sensor, and the vibration sensor respectively, and is used to identify the lightning strike situation of the wind turbine blades based on the electric field data, the acoustic wave data, and the vibration data, so as to obtain the lightning strike identification result of the wind turbine blades.

2. The system according to claim 1, characterized in that, The system also includes an early warning module; The early warning module is connected to the lightning strike monitoring module and is used to generate alarm information based on the lightning strike identification result.

3. A method for monitoring lightning strikes on wind turbine blades, characterized in that, The method, applied to the wind turbine blade lightning strike monitoring system as described in claim 1 or 2, comprises: Acquire electric field data, acoustic wave data, and vibration data of the environment in which the wind turbine blades are located. Feature extraction is performed on the electric field data, the sound wave data, and the vibration data respectively to obtain the first feature of the electric field data, the second feature of the sound wave data, and the third feature of the vibration data. The first feature, the second feature, and the third feature are input into a pre-constructed blade lightning strike probability identification model so that the blade lightning strike probability identification model outputs the target probability of the wind turbine blade being struck by lightning. Based on the target probability, it is determined whether the wind turbine blade has been struck by lightning, and the lightning strike identification result of the wind turbine blade is obtained.

4. The method according to claim 3, characterized in that, The step of determining whether the wind turbine blade has been struck by lightning based on the target probability, and obtaining the lightning strike identification result of the wind turbine blade, includes: If the target probability is greater than a preset threshold, it is determined that the wind turbine blade has been struck by lightning; If the target probability is less than or equal to a preset threshold, it is determined that the wind turbine blades have not been struck by lightning.

5. The method according to claim 4, characterized in that, The method further includes: If the wind turbine blades are struck by lightning, the characteristic parameter value of the lightning current is determined based on the electric field data, the sound pressure level is determined based on the sound wave data, and the peak acceleration of vibration is determined based on the vibration data. The severity level of a lightning strike on a wind turbine blade is determined based on the lightning current characteristic parameter value, the sound pressure level, and the peak vibration acceleration.

6. The method according to claim 4, characterized in that, The blade lightning strike probability identification model is constructed through the following steps: The blade state dataset and the lightning strike probability of each blade state data in the blade state dataset are obtained. The blade state data is obtained by feature extraction from the electric field data, acoustic wave data and vibration data of the environment in which the wind turbine blades are located. The state data of each blade is correlated with the probability of lightning strike to obtain a correlated dataset; The preset machine learning model is trained using the associated dataset to obtain the blade lightning strike probability identification model.

7. A wind turbine blade lightning strike monitoring device, characterized in that, The device, applied to the wind turbine blade lightning strike monitoring system as described in claim 1 or 2, comprises: The acquisition module is used to acquire electric field data, acoustic wave data, and vibration data of the environment in which the wind turbine blades are located. The feature extraction module is used to extract features from the electric field data, the sound wave data, and the vibration data respectively, to obtain a first feature of the electric field data, a second feature of the sound wave data, and a third feature of the vibration data. The identification module is used to input the first feature, the second feature and the third feature into a pre-constructed blade lightning strike probability identification model, so that the blade lightning strike probability identification model outputs the target probability of the wind turbine blade being struck by lightning. The first determining module is used to determine whether the wind turbine blade has been struck by lightning based on the target probability, and to obtain the lightning strike identification result of the wind turbine blade.

8. A computer device, characterized in that, include: The system includes a memory and a processor, which are interconnected. The memory stores computer instructions, and the processor executes the computer instructions to perform the wind turbine blade lightning strike monitoring method according to any one of claims 3 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to execute the wind turbine blade lightning strike monitoring method according to any one of claims 3 to 6.

10. A computer program product, characterized in that, Includes computer instructions for causing a computer to execute the wind turbine blade lightning strike monitoring method according to any one of claims 3 to 6.

Images