Fault detection method, device and equipment of fan equipment, medium and program product

Abstract

The invention discloses a fault detection method, device and equipment of fan equipment, a medium and a program product, and relates to the technical field of fault detection.The fault detection method comprises the steps that a starting event, a shutdown event or a fault performance event of the fan equipment is monitored, and operation data of the fan equipment is obtained; starting and stopping noise reduction configuration information and operation and maintenance configuration information corresponding to the fan equipment are obtained; according to the start-stop noise reduction configuration information, performing noise reduction processing on the operation data to obtain noise reduction operation data; and performing fault detection on the fan equipment according to the operation and maintenance configuration information and the noise reduction operation data to obtain a fault detection result. According to the embodiment of the invention, the fault detection accuracy of the fan equipment is improved.

Description

Technical Field

[0001] This invention relates to the field of fault detection technology, and in particular to a fault detection method, apparatus, equipment, medium, and program product for wind turbine equipment. Background Technology

[0002] Fans are core equipment in building and industrial ventilation systems. Their core components include the main shaft, impeller, motor, and bearings. Operating long-term in complex environments such as dusty, humid industrial plants or building ventilation ducts with significant temperature fluctuations, they are prone to malfunctions. Fan failures can lead to deterioration of workshop air quality, production interruptions, or poor building ventilation, impacting not only production efficiency and employee health but also incurring high maintenance costs for repairing and replacing core components. Therefore, real-time fault detection is essential for early warning systems.

[0003] Traditional detection technologies identify faults by collecting operating parameters of wind turbine equipment. However, the accuracy of operating parameters collected in complex environments is low, resulting in low fault detection accuracy and high false alarm and false negative rates. Summary of the Invention

[0004] This invention provides a method, apparatus, equipment, medium, and program product for fault detection of wind turbine equipment, so as to improve the accuracy of fault detection of wind turbine equipment.

[0005] In a first aspect, embodiments of the present invention provide a fault detection method for wind turbine equipment, including:

[0006] The system listens for start-up events, shutdown events, or fault events of the wind turbine equipment, obtains the operating data of the wind turbine equipment, and obtains the start-up, shutdown, noise reduction configuration information and operation and maintenance configuration information of the wind turbine equipment.

[0007] Based on the start / stop noise reduction configuration information, the operating data is subjected to noise reduction processing to obtain noise-reduced operating data;

[0008] Based on the operation and maintenance configuration information and the noise reduction operation data, fault detection is performed on the wind turbine equipment to obtain fault detection results.

[0009] Secondly, embodiments of the present invention also provide a fault detection device for wind turbine equipment, comprising:

[0010] The acquisition module is used to listen for start-up events, shutdown events, or fault performance events of the wind turbine equipment, acquire the operating data of the wind turbine equipment, and acquire the start-up, shutdown, noise reduction configuration information and operation and maintenance configuration information of the wind turbine equipment.

[0011] The noise reduction module is used to perform noise reduction processing on the operating data according to the start / stop noise reduction configuration information to obtain noise-reduced operating data;

[0012] The detection module is used to perform fault detection on the wind turbine equipment based on the operation and maintenance configuration information and the noise reduction operation data, and obtain the fault detection results.

[0013] Thirdly, embodiments of the present invention also provide an electronic device, comprising:

[0014] At least one processor; and

[0015] A memory that is communicatively connected to at least one processor; wherein

[0016] The memory stores instructions that can be executed by at least one processor, which enables the at least one processor to perform the fault detection method for wind turbine equipment provided in any embodiment of the present invention.

[0017] Fourthly, embodiments of the present invention also provide a computer-readable storage medium storing computer instructions, which are used to cause a processor to execute the fault detection method for wind turbine equipment according to any embodiment of the present invention.

[0018] Fifthly, embodiments of the present invention also provide a computer program product, characterized in that the computer program product includes a computer program, which, when executed by a processor, implements the fault detection method for wind turbine equipment according to any embodiment of the present invention.

[0019] This invention, through monitoring wind turbine startup events, shutdown events, or fault behavior events, acquires the operating data of the wind turbine, as well as the corresponding start-up / shutdown noise reduction configuration information and maintenance configuration information. Based on the start-up / shutdown noise reduction configuration information, the operating data is processed to reduce noise, resulting in noise-reduced operating data. Based on the maintenance configuration information and the noise-reduced operating data, fault detection is performed on the wind turbine to obtain fault detection results. This allows for automated, targeted noise reduction of operating data during wind turbine startup or shutdown, thereby improving the accuracy of fault detection for wind turbines.

[0020] 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

[0021] 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.

[0022] Figure 1 This is a flowchart of a fault detection method for wind turbine equipment according to Embodiment 1 of the present invention;

[0023] Figure 2 This is a flowchart of a fault detection method for a wind turbine according to Embodiment 2 of the present invention;

[0024] Figure 3 This is a schematic diagram of the structure of a fault detection device for a wind turbine according to Embodiment 3 of the present invention;

[0025] Figure 4 This is a structural diagram of an electronic device that implements a fault detection method for a wind turbine according to an embodiment of the present invention. Detailed Implementation

[0026] 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.

[0027] It should be noted that the terms "first" and "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.

[0028] In the technical solutions of this invention, the acquisition, storage, and application of operating data, start / stop noise reduction configuration information, and maintenance configuration information all comply with relevant laws and regulations and do not violate public order and good morals.

[0029] Example 1

[0030] Figure 1 This is a flowchart of a fault detection method for wind turbine equipment provided in Embodiment 1 of the present invention. This embodiment can be applied to the situation of fault detection of wind turbine equipment. The method can be executed by a fault detection device for wind turbine equipment. The fault detection device for wind turbine equipment can be implemented in hardware and / or software and specifically configured in electronic equipment.

[0031] See Figure 1 The fault detection method for the wind turbine equipment shown includes:

[0032] S101. Listen to the start-up event, shutdown event, or fault performance event of the wind turbine equipment, obtain the operating data of the wind turbine equipment, and obtain the start-up, shutdown, noise reduction configuration information and operation and maintenance configuration information of the wind turbine equipment.

[0033] S102. Based on the start / stop noise reduction configuration information, perform noise reduction processing on the operating data to obtain noise-reduced operating data.

[0034] S103. Based on the operation and maintenance configuration information and the noise reduction operation data, perform fault detection on the wind turbine equipment and obtain the fault detection results.

[0035] In this embodiment, the wind turbine equipment may include, but is not limited to, wind turbines, fans, and blowers. A start-up event can be an event characterizing the start-up behavior of the wind turbine equipment. A shutdown event can be an event characterizing the shutdown of the wind turbine equipment. Operating data may include, but is not limited to, spindle vibration data, gearbox speed, gearbox oil temperature, motor speed, stator three-phase current, and inverter voltage. Start-up and shutdown noise reduction configuration information may be pre-configured, indicating how noise reduction processing is performed when the wind turbine equipment starts up or stops. Maintenance configuration information may be pre-configured; the maintenance information of the wind turbine equipment can be obtained from the wind turbine equipment's maintenance manual, etc. Noise reduction operating data refers to the operating data after noise reduction processing.

[0036] Specifically, a device or apparatus equipped with the fault detection method for wind turbine equipment according to embodiments of the present invention can continuously monitor the wind turbine equipment. If a start-up event, shutdown event, or fault behavior event of the wind turbine equipment is detected, real-time operating data of the wind turbine equipment is acquired, and start / stop noise reduction configuration information matching the wind turbine equipment is searched. Based on the start / stop noise reduction configuration information, the acquired real-time operating data of the wind turbine equipment is noise-reduced, and the noise-reduced operating data is used as noise-reduced operating data. Based on the operation and maintenance configuration information and the noise-reduced operating data, fault detection is performed on the wind turbine equipment to obtain fault detection results.

[0037] In one optional embodiment, the start-stop noise reduction configuration information and operation and maintenance configuration information corresponding to the wind turbine equipment can be automatically obtained through "manual recognition + multi-scenario template library + intelligent matching". The user clicks "Add Equipment" on the front-end page; selects the equipment scenario, such as zero-carbon smart park; selects the equipment type, such as wind turbine equipment and the specific model of the wind turbine equipment; uploads operation and maintenance files, such as operation and maintenance manual images or operation and maintenance manual documents; the equipment receives the operation and maintenance files uploaded by the user and recognizes the information, automatically matching the pre-set multi-scenario equipment feature template library, which includes start-stop noise reduction configuration information, to generate a lightweight front-end model. No professional operation is required throughout the process, realizing zero-configuration access for multiple types of equipment and solving the pain point of users not knowing how to configure.

[0038] Optionally, the operation and maintenance configuration information includes configuration information for at least one wind turbine fault; the configuration information for the wind turbine fault includes a numerical range of at least one operating data point used to characterize when the wind turbine fault occurs; the step of performing fault detection on the wind turbine equipment based on the operation and maintenance configuration information and the noise reduction operation data to obtain a fault detection result includes: generating at least one fault data sample and at least one normal data sample based on the configuration information for each wind turbine fault; generating an initial detection model based on the operation and maintenance configuration information; training the initial detection model based on each fault data sample and each normal data sample to obtain a trained fault detection model; and performing fault detection on the wind turbine equipment based on the noise reduction operation data using the fault detection model to obtain a fault detection result.

[0039] Wind turbine faults can include, for example, gearbox wear, stator inter-turn short circuits, and bearing jamming. Configuration information for wind turbine faults can be used to characterize the numerical range of operating data when a corresponding fault occurs. For example, configuration information for gearbox wear can be the numerical range of various operating data of the wind turbine when gearbox wear occurs. Fault data samples can be samples of operating data from the wind turbine under fault conditions; normal data samples can be samples of operating data from the wind turbine under normal, i.e., fault-free conditions. The initial detection model can be a parameter-initialized, untrained machine learning model. Fault detection results can include abnormal results and normal results; abnormal results specifically refer to the fault type of the wind turbine.

[0040] Specifically, for each wind turbine fault configuration information, a fault data sample for that wind turbine fault is generated; based on the configuration information of each wind turbine fault, at least one normal data sample is generated; labels are generated for each fault data sample and each normal data sample; wherein, the label corresponding to each fault data sample is the wind turbine fault label corresponding to that fault data sample; the label corresponding to each normal data sample is the normal label; the value of each operational data item in the normal data sample is outside the numerical range of the corresponding operational data when each wind turbine fault occurs; based on the operation and maintenance configuration information, an initial detection model is generated; the predicted labels of each fault data sample and normal data sample are determined through the initial detection model; based on the predicted labels and labels, the initial fault model is trained to obtain a trained fault detection model; the fault detection model is used to process the noise reduction operational data to obtain the fault detection result of the wind turbine equipment.

[0041] Understandably, by adopting the above technical solution, using fault data samples and normal data samples generated from operation and maintenance configuration information to train the generated initial detection model, it is possible to avoid spending a lot of time collecting data from the actual operation of wind turbine equipment while ensuring accurate training, thereby improving the training efficiency of the initial detection model; and by using the trained fault detection model to predict wind turbine faults based on the noise-reduced operating data, the accuracy of wind turbine fault detection is improved.

[0042] Optionally, generating an initial detection model based on the operation and maintenance configuration information includes: determining the number of neurons in the input layer of the initial detection model based on the number of data types in the operating data; determining the number of neurons in the hidden layer and the number of neurons in the output layer of the initial detection model based on the number of data types in the operating data and the number of wind turbine faults; and generating an initial detection model based on the number of neurons in the input layer, the number of neurons in the hidden layer, and the number of neurons in the output layer.

[0043] Specifically, the number of data types in the running data is determined as the number of neurons in the input layer of the initial detection model; the sum of the number of data types in the running data and the number of wind turbine faults is determined, and the power of 2 that is greater than the sum of the data types and has the smallest difference from the sum of the data types is determined; the smallest power of 2 is determined as the number of neurons in the first layer of the hidden layer of the initial detection model; the number of neurons in the second layer of the hidden layer is determined as half the number of neurons in the first layer; the number of wind turbine faults is added by one to obtain the number of neurons in the third layer of the hidden layer; the number of wind turbine faults is determined as the number of neurons in the output layer of the initial detection model; based on the number of neurons in the input layer, the number of neurons in the hidden layer, and the number of neurons in the output layer, the neuron parameters are initialized to generate the initial detection model.

[0044] It is understandable that by adopting the above technical solution, determining the number of neurons in the input layer of the initial detection model based on the number of data types in the operational data enables the number of neurons to match the features of the operational data of the input model, thereby avoiding feature redundancy or information loss. Determining the number of neurons in the hidden layer of the initial detection model based on the number of data types and the number of wind turbine faults allows for the initial capture of multi-feature abnormal patterns using a larger number of neurons in the first layer, followed by the compression of redundant information and focus on core features using half the number of neurons in the second layer, further reducing information loss through the neurons in the third layer, and finally matching the number of neurons in the output layer with the number of wind turbine faults to output the probability of each fault, thus improving the interpretability of the fault detection results.

[0045] In one optional embodiment, the fault detection model is a lightweight front-end model, and the data analysis process is migrated to the front end. Based on the lightweight fault detection model, multi-scenario data preprocessing (such as industrial noise filtering), feature extraction and inference are completed on the browser side. Only the analysis results such as fault warnings are uploaded, reducing the amount of data transmission, realizing real-time response on the terminal side, and solving the pain point of "response lag".

[0046] This invention, through monitoring wind turbine startup events, shutdown events, or fault behavior events, acquires the operating data of the wind turbine, as well as the corresponding start-up / shutdown noise reduction configuration information and maintenance configuration information. Based on the start-up / shutdown noise reduction configuration information, the operating data is processed to reduce noise, resulting in noise-reduced operating data. Based on the maintenance configuration information and the noise-reduced operating data, fault detection is performed on the wind turbine to obtain fault detection results. This allows for automated, targeted noise reduction of operating data during wind turbine startup or shutdown, thereby improving the accuracy of fault detection for wind turbines.

[0047] Example 2

[0048] Figure 2 This is a flowchart of a fault detection method for wind turbine equipment provided in Embodiment 2 of the present invention. Based on the technical solution of the above embodiments, the present invention has optimized and improved the operation of determining noise reduction operation data.

[0049] Furthermore, the phrase "according to the start-stop noise reduction configuration information, the operating data is processed to obtain noise-reduced operating data" is refined to "from the operating data, first operating data matching the electromagnetic interference data type is selected; the operating data other than the first operating data is determined as second operating data; according to the start-stop noise reduction configuration information, the first operating data is processed to obtain third operating data; the second operating data and the third operating data are determined as noise-reduced operating data", to improve the operation of determining noise-reduced operating data.

[0050] It should be noted that for any parts not described in detail in the embodiments of the present invention, please refer to the description in the foregoing embodiments.

[0051] See Figure 2 The fault detection method for the wind turbine equipment shown includes:

[0052] S201. Upon detecting a start-up event, shutdown event, or fault event of the wind turbine equipment, obtain the operating data of the wind turbine equipment, as well as the start-up, shutdown, noise reduction configuration information, and operation and maintenance configuration information corresponding to the wind turbine equipment.

[0053] S202. From the operating data, select the first operating data that matches the electromagnetic interference data type.

[0054] S203. The running data other than the first running data is determined as the second running data.

[0055] S204. Based on the start / stop noise reduction configuration information, perform noise reduction processing on the first operating data to obtain the third operating data.

[0056] S205. The second operating data and the third operating data are determined as noise reduction operating data.

[0057] S206. Based on the operation and maintenance configuration information and the noise reduction operation data, perform fault detection on the wind turbine equipment and obtain the fault detection results.

[0058] In this embodiment, the start / stop noise reduction configuration information includes, but is not limited to, at least one type of electromagnetic interference; the electromagnetic interference data type is a data type of operating data associated with electromagnetic interference; the data type may include, but is not limited to, spindle vibration data, gearbox vibration data, and motor three-phase stator current.

[0059] Specifically, the operating data whose data type is electromagnetic interference type in the start-stop noise reduction configuration information is determined as the first operating data; the operating data other than the first operating data, that is, the operating data whose data type is not electromagnetic interference type in the start-stop noise reduction configuration information, is determined as the second operating data; according to the start-stop noise reduction configuration information, the first operating data is subjected to noise reduction processing to obtain the third operating data; the second operating data and the third operating data are determined as the noise-reduced operating data.

[0060] Optionally, the start / stop noise reduction configuration information includes at least one data sample pair; the data sample pair includes electromagnetic interference data samples and non-electromagnetic interference data samples; the step of performing noise reduction processing on the first operating data according to the start / stop noise reduction configuration information to obtain third operating data includes: generating an initial noise reduction model; training the initial noise reduction model according to each of the data sample pairs to obtain a trained noise reduction model; performing quantization and pruning processing on the trained noise reduction model to obtain a target noise reduction model; and performing noise reduction processing on the first operating data using the target noise reduction model to obtain the third operating data.

[0061] Among them, the electromagnetic interference data sample can be the first operating data sample of the wind turbine equipment under the influence of electromagnetic interference; the electromagnetic interference-free data sample can be the first operating data sample of the wind turbine equipment without the influence of electromagnetic interference. For each data sample pair, the electromagnetic interference-free data sample in the data sample pair can be the data sample obtained by manually reducing the noise of the electromagnetic interference data sample in the data sample pair.

[0062] Specifically, the initial denoising model is used to denoise the electromagnetic interference data samples in each data sample pair to obtain the denoising result of the electromagnetic interference data samples; the initial denoising model is trained with the goal of minimizing the difference between the denoising result of the electromagnetic interference data sample and the electromagnetic interference-free data sample in the same data sample pair, to obtain the trained denoising model; the trained model is quantized and pruned to obtain the target denoising model; the first running data is processed using the target denoising model to obtain the third running data.

[0063] Understandably, the above technical solution allows for the training of a target denoising model using start / stop denoising configuration information. This target denoising model is then used to denoise the first running data, improving the efficiency and accuracy of denoising. Furthermore, quantizing and pruning the denoising model reduces its size, removes redundant parameters, accelerates model processing, and meets real-time requirements.

[0064] Optionally, the step of filtering out the first operating data that matches the electromagnetic interference data type from the operating data includes: selecting vibration data of the transmission components of the wind turbine equipment and current data of the motor of the wind turbine equipment from the operating data; filtering out sub-vibration data that matches the electromagnetic interference data type from the vibration data; filtering out sub-current data that matches the electromagnetic interference data type from the current data; and determining the sub-vibration data and the sub-current data as the first operating data.

[0065] The transmission components may include, but are not limited to, at least one of the following: the main shaft, gearbox, and bearings of the fan equipment. Electromagnetic interference data may include, but are not limited to, peak value of main shaft vibration, mean value of main shaft vibration, variance of main shaft vibration, peak value of bearing vibration, variance of bearing vibration, effective value of current, current imbalance, and current fluctuation amplitude.

[0066] Specifically, from the operating data, the main shaft vibration data and bearing vibration data of the wind turbine equipment, as well as the three-phase stator current data of the motor of the wind turbine equipment, are selected; from the vibration data, sub-vibration data that matches the electromagnetic interference data type are filtered out; specifically, the main shaft vibration peak value, main shaft vibration mean value, main shaft vibration variance, bearing vibration peak value and bearing vibration variance are filtered out; and the effective value, unbalance, and fluctuation amplitude of the current are filtered out; the sub-vibration data and the sub-current data are determined as the first operating data.

[0067] It is understandable that by adopting the above technical solution, the electromagnetic interference data type in the noise reduction configuration information can be further activated or deactivated, and the noise reduction data that needs to be processed can be further extracted, thereby reducing the amount of data that needs to be processed. Without affecting fault detection, the noise reduction efficiency can be improved, thereby improving the fault detection efficiency.

[0068] In one specific embodiment, the fault detection method for wind turbine equipment provided by this invention can run on a technician's mobile device. When the mobile device is running, it monitors the start-up or shutdown events of the wind turbine equipment, maintaining low-power operation to save electricity and extend operating time. Upon detecting a start-up event, shutdown event, or fault behavior event of the wind turbine equipment, it acquires the operating data of the wind turbine equipment, as well as the corresponding start-up / shutdown noise reduction configuration information and maintenance configuration information. A cold start approach is then adopted to generate a target noise reduction model and a fault detection model for fault detection. Since the start-up and shutdown frequency of the wind turbine equipment is low, generating a model for fault detection each time a start-up or shutdown event is detected effectively saves resources compared to continuous, uninterrupted fault detection techniques for wind turbine equipment.

[0069] In one specific implementation, fault detection results are categorized by urgency, presenting information across multiple scenarios to reduce user filtering costs. For example, information can be displayed in three different colored areas. In the red action zone, a strong flashing indicator displays wind turbine equipment faults that must be addressed, along with quick access to maintenance plans and linkage commands. In the yellow warning zone, early-stage faults requiring attention, i.e., safety hazards in the wind turbine equipment, are displayed; users can click to view the detection trend, with transparency increasing with the risk value. In the gray noise-reduced data zone, filtered interference signals are displayed to reduce visual interference, with a semi-transparent, faded effect. Monthly fault reports are also pushed out monthly.

[0070] Furthermore, the linkage instructions in the red action area can be used to provide linkage plans and instruction execution (people / things); the maintenance plan can be generated by the system automatically linking multiple scenario knowledge bases and spare parts inventory systems, including the remaining life of the faulty component, spare parts information of the faulty component, and scenario-based operation steps; users can click on "AR (Augmented Reality) guidance" to scan the device to load 3D disassembly / debugging animations, and simultaneously display safety prompts (such as "power off before disassembling the signal module").

[0071] For example, the display interface can show a fault alarm pop-up window "[Bearing Wear], Remaining life: 72h, Recommendation: Replace within 36h, Spare parts: Location A3-221 (3 in stock)"; and display an AR guidance QR code. When technicians scan the equipment QR code, the 3D disassembly and assembly guide and safety operation specifications are automatically loaded to avoid secondary downtime caused by replacing the wrong spare parts or improper operation.

[0072] Furthermore, scanning the device automatically matches the optimal noise reduction solution. Users can select the cause by operating the flag, and the data, after local differential privacy protection, triggers fine-tuning of the fault detection model. Only parameter updates are shared, not the original data, and the filtering process iterates in real time, reducing similar false alarms. For example, technicians can click the "False Alarm" icon in the device interface, select electromagnetic interference as the cause of the false alarm, perform local differential privacy protection, trigger local model fine-tuning, thereby optimizing the noise reduction model and reducing the subsequent false alarm rate.

[0073] This invention, through the following steps, filters out first operating data that matches the electromagnetic interference data type from the operating data; identifies the operating data other than the first operating data as second operating data; performs noise reduction processing on the first operating data according to the start / stop noise reduction configuration information to obtain third operating data; and identifies the second and third operating data as noise-reduced operating data. This avoids noise reduction of the operating data of wind turbine equipment not subject to electromagnetic interference, thereby preventing distortion of the operating data of wind turbine equipment not subject to electromagnetic interference and ensuring the accuracy of fault detection.

[0074] Example 3

[0075] Figure 3 This is a schematic diagram of a fault detection device for wind turbine equipment provided in Embodiment 3 of the present invention. This embodiment of the invention is applicable to situations involving fault detection of wind turbine equipment. The device can execute a fault detection method for wind turbine equipment. The fault detection device can be implemented in hardware and / or software, and can be configured in an electronic device.

[0076] See Figure 3 The fault detection device for the wind turbine equipment shown includes an acquisition module 301, a noise reduction module 302, and a detection module 303, wherein...

[0077] The acquisition module 301 is used to listen to the start-up event, shutdown event or fault performance event of the wind turbine equipment, acquire the operating data of the wind turbine equipment, and acquire the start-up, shutdown and noise reduction configuration information and operation and maintenance configuration information of the wind turbine equipment.

[0078] The noise reduction module 302 is used to perform noise reduction processing on the running data according to the start / stop noise reduction configuration information to obtain noise-reduced running data;

[0079] The detection module 303 is used to perform fault detection on the wind turbine equipment based on the operation and maintenance configuration information and the noise reduction operation data, and obtain the fault detection result.

[0080] This invention, through an acquisition module, monitors start-up events, shutdown events, or fault manifestation events of wind turbine equipment, acquires the operating data of the wind turbine equipment, and acquires the corresponding start-up / shutdown noise reduction configuration information and operation and maintenance configuration information of the wind turbine equipment. A noise reduction module processes the operating data for noise reduction based on the start-up / shutdown noise reduction configuration information to obtain noise-reduced operating data. A detection module performs fault detection on the wind turbine equipment based on the operation and maintenance configuration information and the noise-reduced operating data to obtain fault detection results. This allows for automated, targeted noise reduction of operating data during wind turbine equipment start-up or shutdown, thereby improving the accuracy of fault detection for wind turbine equipment.

[0081] Optionally, the start / stop noise reduction configuration information includes configuration information for at least one electromagnetic interference data type; the electromagnetic interference data type is a data type of operational data associated with electromagnetic interference.

[0082] Noise reduction module 302 includes:

[0083] The first filtering unit is used to filter out first operating data that matches the electromagnetic interference data type from the operating data;

[0084] The first determining unit is used to determine the running data other than the first running data as the second running data.

[0085] The noise reduction unit is used to perform noise reduction processing on the first operating data according to the start / stop noise reduction configuration information to obtain the third operating data;

[0086] The second determining unit is used to determine the second operating data and the third operating data as noise reduction operating data.

[0087] Optionally, the start / stop noise reduction configuration information includes at least one data sample pair; the data sample pair includes electromagnetic interference data samples and non-electromagnetic interference data samples;

[0088] The noise reduction unit is specifically used for:

[0089] Generate an initial noise reduction model;

[0090] Based on each of the data sample pairs, the initial noise reduction model is trained to obtain a trained noise reduction model;

[0091] The trained model is quantized and pruned to obtain the target noise reduction model;

[0092] The first running data is denoised using the target denoising model to obtain the third running data.

[0093] Optionally, the first determining unit includes:

[0094] The selection unit is used to select vibration data of the transmission components of the wind turbine equipment and current data of the motor of the wind turbine equipment from the operating data.

[0095] The second filtering unit is used to filter out sub-vibration data that match the electromagnetic interference data type from the vibration data;

[0096] The third filtering unit is used to filter out sub-current data that matches the electromagnetic interference data type from the current data;

[0097] The sub-vibration data and the sub-current data are determined as the first operating data.

[0098] Optionally, the operation and maintenance configuration information includes configuration information for at least one wind turbine fault; the configuration information for the wind turbine fault includes a numerical range of at least one operating data point used to characterize when the wind turbine fault occurs.

[0099] The detection module 303 includes:

[0100] The sample generation unit is used to generate at least one fault data sample and at least one normal data sample based on the configuration information of each wind turbine fault.

[0101] The model generation unit is used to generate an initial detection model based on the operation and maintenance configuration information;

[0102] The model training unit is used to train the initial detection model based on each of the fault data samples and each of the normal data samples to obtain a trained fault detection model.

[0103] The detection unit is used to perform fault detection on the wind turbine equipment based on the noise reduction operation data using the fault detection model, and obtain the fault detection result.

[0104] Optional, model generation unit, specifically used for:

[0105] The number of neurons in the input layer of the initial detection model is determined based on the number of data types in the running data.

[0106] Based on the number of data types in the operational data and the number of wind turbine faults, determine the number of neurons in the hidden layer of the initial detection model and the number of neurons in the output layer of the initial detection model.

[0107] An initial detection model is generated based on the number of neurons in the input layer, the number of neurons in the hidden layer, and the number of neurons in the output layer.

[0108] The fault detection device for wind turbine equipment provided in this embodiment of the invention can execute the fault detection method for wind turbine equipment provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects for executing the fault detection method for wind turbine equipment.

[0109] Example 4

[0110] Figure 4 A schematic diagram of a fault detection device 410 for wind turbine equipment, which can be used to implement embodiments of the present invention, is shown. The fault detection device for wind turbine equipment is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The fault detection device for wind turbine equipment can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing 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.

[0111] like Figure 4 As shown, the fault detection device 410 for wind turbine equipment includes at least one processor 411 and a memory, such as a read-only memory (ROM) 412 or a random access memory (RAM) 413, communicatively connected to the at least one processor 411. The memory stores computer programs executable by the at least one processor. The processor 411 can perform various appropriate actions and processes based on the computer program stored in the ROM 412 or loaded from storage unit 418 into the RAM 413. The RAM 413 can also store various programs and data required for the operation of the fault detection device 410. The processor 411, ROM 412, and RAM 413 are interconnected via a bus 414. An input / output (I / O) interface 415 is also connected to the bus 414.

[0112] Multiple components in the wind turbine equipment fault detection device 410 are connected to the I / O interface 415, including: an input unit 416, such as a keyboard, mouse, etc.; an output unit 417, such as various types of displays, speakers, etc.; a storage unit 418, such as a disk, optical disk, etc.; and a communication unit 419, such as a network card, modem, wireless transceiver, etc. The communication unit 419 allows the wind turbine equipment fault detection device 410 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0113] Processor 411 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 411 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 411 performs the various methods and processes described above, such as fault detection methods for wind turbine equipment.

[0114] In some embodiments, the wind turbine equipment fault detection method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 418. In some embodiments, part or all of the computer program may be loaded into and / or installed onto the wind turbine equipment fault detection device 410 via ROM 412 and / or communication unit 419. When the computer program is loaded into RAM 413 and executed by processor 411, one or more steps of the wind turbine equipment fault detection method described above may be performed. Alternatively, in other embodiments, processor 411 may be configured to perform the wind turbine equipment fault detection method by any other suitable means (e.g., by means of firmware).

[0115] Various implementations 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), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations 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.

[0116] Computer programs used to implement the methods of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to the processor of a general-purpose computer, a special-purpose computer, or other programmable wind turbine equipment fault detection 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 implemented. The computer programs can be executed entirely on the machine, partially on the machine, as a standalone software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0117] 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.

[0118] To provide user interaction, the systems and techniques described herein can be implemented on a fault detection device for wind turbine equipment, which includes: 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 fault detection device. Other types of devices can also be used to provide user interaction; 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).

[0119] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or 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.

[0120] A computing system can include clients and servers. Clients and servers are generally geographically separated and typically interact via 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. It addresses the shortcomings of traditional physical hosts and VPS (Virtual Private Server) services, such as high management difficulty and weak business scalability.

[0121] 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.

[0122] 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 fault detection method for wind turbine equipment, characterized in that, The method includes: The system listens for start-up events, shutdown events, or fault events of the wind turbine equipment, obtains the operating data of the wind turbine equipment, and obtains the start-up, shutdown, noise reduction configuration information and operation and maintenance configuration information of the wind turbine equipment. Based on the start / stop noise reduction configuration information, the operating data is subjected to noise reduction processing to obtain noise-reduced operating data; Based on the operation and maintenance configuration information and the noise reduction operation data, fault detection is performed on the wind turbine equipment to obtain fault detection results.

2. The method according to claim 1, characterized in that, The start / stop noise reduction configuration information includes configuration information for at least one type of electromagnetic interference data; the electromagnetic interference data type is a data type of operational data that is associated with electromagnetic interference. The step of performing noise reduction processing on the operating data according to the start / stop noise reduction configuration information to obtain noise-reduced operating data includes: From the operational data, select the first operational data that matches the electromagnetic interference data type; The running data other than the first running data is identified as the second running data; Based on the start / stop noise reduction configuration information, the first operating data is subjected to noise reduction processing to obtain the third operating data; The second and third operating data are determined as noise reduction operating data.

3. The method according to claim 2, characterized in that, The start / stop noise reduction configuration information includes at least one data sample pair; the data sample pair includes electromagnetic interference data samples and no electromagnetic interference data samples. The step of performing noise reduction processing on the first operating data according to the start / stop noise reduction configuration information to obtain the third operating data includes: Generate an initial noise reduction model; Based on each of the data sample pairs, the initial noise reduction model is trained to obtain a trained noise reduction model; The trained denoising model is quantized and pruned to obtain the target denoising model. The first running data is denoised using the target denoising model to obtain the third running data.

4. The method according to claim 2, characterized in that, The step of filtering out the first set of operational data that matches the electromagnetic interference data type from the operational data includes: From the aforementioned operating data, vibration data of the transmission components of the wind turbine equipment and current data of the motor of the wind turbine equipment are selected; From the vibration data, sub-vibration data that matches the electromagnetic interference data type are selected; From the current data, sub-current data that matches the electromagnetic interference data type are selected; The sub-vibration data and the sub-current data are determined as the first operating data.

5. The method according to claim 1, characterized in that, The operation and maintenance configuration information includes configuration information for at least one wind turbine fault; the configuration information for the wind turbine fault includes a numerical range of at least one operating data point used to characterize when the wind turbine fault occurs. The step of performing fault detection on the wind turbine equipment based on the operation and maintenance configuration information and the noise reduction operation data, and obtaining fault detection results, includes: Based on the configuration information of each wind turbine fault, generate at least one fault data sample and at least one normal data sample; Based on the aforementioned operation and maintenance configuration information, an initial detection model is generated; The initial detection model is trained based on each of the fault data samples and each of the normal data samples to obtain a trained fault detection model. The fault detection model is used to detect faults in the wind turbine equipment based on the noise reduction operation data, and the fault detection results are obtained.

6. The method according to claim 5, characterized in that, The step of generating an initial detection model based on the operation and maintenance configuration information includes: The number of neurons in the input layer of the initial detection model is determined based on the number of data types in the running data. Based on the number of data types in the operational data and the number of wind turbine faults, determine the number of neurons in the hidden layer of the initial detection model and the number of neurons in the output layer of the initial detection model. An initial detection model is generated based on the number of neurons in the input layer, the number of neurons in the hidden layer, and the number of neurons in the output layer.

7. A fault detection device for wind turbine equipment, characterized in that, The device includes: The acquisition module is used to listen for start-up events, shutdown events, or fault performance events of the wind turbine equipment, acquire the operating data of the wind turbine equipment, and acquire the start-up, shutdown, noise reduction configuration information and operation and maintenance configuration information of the wind turbine equipment. The noise reduction module is used to perform noise reduction processing on the operating data according to the start / stop noise reduction configuration information to obtain noise-reduced operating data; The detection module is used to perform fault detection on the wind turbine equipment based on the operation and maintenance configuration information and the noise reduction operation data, and obtain the fault detection results.

8. 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 a fault detection method for a wind turbine equipment according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the fault detection method for the wind turbine equipment as described in any one of claims 1-6.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the fault detection method for the wind turbine equipment as described in any one of claims 1-6.

Images