Icing detection method, device and system for fan, and storage medium

Abstract

The embodiment of the invention provides an icing detection method and device for a fan, a storage medium and a system. The method comprises the steps that the surface position of any blade of the fan and current image data and current meteorological data of the top of a cabin of the fan are acquired; determining current motion data of the fan; preprocessing the surface position of any blade, the current meteorological data, the current image data and the current motion data; inputting the preprocessed surface position of any blade, the current motion data, the current image data and the current meteorological data into an icing detection model to obtain a current icing correction value at the surface position of any blade; acquiring a current icing static value of the top of a cabin of the fan; and according to the current icing correction value and the current icing static value, the icing monitoring value at the surface position of any blade is determined, and the icing condition of the whole blade of the fan can be comprehensively sensed.

Description

Technical Field

[0001] The present application relates to the technical field of ice coating detection, and in particular to an ice coating detection method, device, storage medium and system for a wind turbine. Background Art

[0002] The blades of wind turbines (hereinafter referred to as wind turbine blades) are the key moving parts of wind turbines. They mainly convert the kinetic energy of wind into mechanical energy, and then generate electricity into electrical energy. During winter cold waves, the ambient temperature is usually below freezing, and there may be supercooled water droplets in the air. When these supercooled water droplets come into contact with the surface of the wind turbine blades, the water droplets will quickly absorb heat and freeze on the surface of the blades because the surface temperature of the blades is lower than the temperature of water. Icing on the wind turbine blades will change the aerodynamic performance of the blades, resulting in power loss, and at the same time change the mass distribution of the blades, causing unstable operation of the wind turbine, and in severe cases even causing blade damage or shutdown. Effective wind turbine blade icing monitoring methods can help analyze the operating status of wind turbines and improve the accuracy of wind power prediction in freezing weather.

[0003] Currently, the existing wind turbine icing monitoring mostly adopts the method of placing sensors on the top of the nacelle. However, when the blades rotate, ice ridges of different shapes will form on the blade tip, leading edge or trailing edge. Single, static sensors cannot reflect the true icing status of the blade as a whole. The local fixed-point icing monitoring method on the surface of the wind turbine blade can only monitor individual locations, which is also not universal. Therefore, the single-point static icing detection in the existing technology has great limitations and cannot fully perceive the icing status of the entire blade. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide an icing detection method, device, storage medium and system for a wind turbine, so as to solve the problem that single-point static icing detection in the prior art has large limitations and cannot fully perceive the icing condition of the entire blade.

[0005] In order to achieve the above-mentioned object, the present application provides, in a first aspect, a method for detecting ice coating on a wind turbine, comprising: Obtaining the surface position of any blade of the wind turbine, the current image data of the top of the nacelle of the wind turbine, and the current meteorological data; Determine current motion data of the wind turbine, the current motion data including the rotation speed of any blade surface position of the wind turbine, the current yaw angle, and the current pitch angle of any blade; Preprocessing any blade surface position, current meteorological data, current image data, and current motion data; Inputting the preprocessed surface position of any blade, current motion data, current image data and current meteorological data into the ice detection model to obtain the current ice correction value at any blade surface position; Get the current static value of ice coverage on the top of the wind turbine nacelle; The ice coverage monitoring value at any blade surface position is determined according to the current ice coverage correction value and the current ice coverage static value.

[0006] In an embodiment of the present application, at least one chip-type capacitive ice sensor is installed on the wind turbine, and an ice detection model is trained through the following steps: determining training data, the training data including the installation position of each chip-type capacitive ice sensor on the wind turbine, historical image data of the top surface of the wind turbine cabin, historical meteorological data of the wind turbine, and historical motion data of the wind turbine; inputting the training data into a preset neural network so that the preset neural network outputs a historical ice correction value; obtaining the historical ice static value of the top of the wind turbine cabin, and the blade surface ice monitoring value collected by each chip-type capacitive ice sensor; determining the loss value of the preset neural network based on the historical ice correction value, the historical ice static value, and all the blade surface ice monitoring values; when the loss value meets the preset conditions, determining that the training of the preset neural network is completed, and obtaining the ice detection model.

[0007] In the embodiment of the present application, the loss value of the preset neural network is determined by the following formula (1): Formula (1) in, refers to the loss value of the preset neural network, Refers to the number of chip capacitive ice sensors. refers to the historical ice cover correction value, Refers to the historical static value of ice cover, It refers to the leaf surface ice monitoring value collected by the i-th patch capacitive ice sensor.

[0008] In an embodiment of the present application, a meteorological sensor and an image acquisition device are installed on the wind turbine, and determining the training data includes: obtaining the installation position of each chip-type capacitive ice sensor on the wind turbine; receiving historical image data of the top surface of the cabin acquired by the image acquisition device; receiving historical meteorological data acquired by the meteorological sensor; obtaining the historical speed, yaw angle and pitch angle of the blade where each chip-type capacitive ice sensor is located; determining the rotation speed of the blade where each chip-type capacitive ice sensor is located according to the historical speed and the installation position of each chip-type capacitive ice sensor; determining the historical motion data of the wind turbine according to the rotation speed, yaw angle and pitch angle; and preprocessing the installation position, historical image data, historical meteorological data and historical motion data to obtain training data.

[0009] In an embodiment of the present application, determining the rotation speed of the blade where each chip-type capacitive ice sensor is located based on the historical rotation speed and the installation position of each chip-type capacitive ice sensor includes: determining the distance between the installation position of each chip-type capacitive ice sensor and the center point of the fan hub; determining the rotation speed of each chip-type capacitive ice sensor based on the historical rotation speed and distance of the fan.

[0010] In the embodiment of the present application, the rotation speed of each patch capacitive ice sensor is determined by the following formula: Formula (2) in, is the rotation speed of the i-th chip capacitive ice sensor, It refers to the distance between the i-th chip capacitive ice sensor and the center point of the fan hub. It refers to the historical speed of the fan where the i-th chip capacitor ice sensor is located.

[0011] In an embodiment of the present application, determining the ice coverage monitoring value at any blade surface position according to the current ice coverage correction value and the current ice coverage static value includes: determining the total value between the current ice coverage correction value and the current ice coverage static value as the ice coverage monitoring value.

[0012] A second aspect of the present application provides an ice detection device for a wind turbine, comprising: a memory configured to store instructions; The processor is configured to call instructions from the memory and implement the above-mentioned ice coating detection method for the wind turbine when executing the instructions.

[0013] A third aspect of the present application provides a machine-readable storage medium having instructions stored thereon, which, when executed by a processor, configure the processor to execute the above-mentioned ice coating detection method for a wind turbine.

[0014] A fourth aspect of the present application provides an ice detection system for a wind turbine, comprising: The microwave ice monitoring sensor is installed on the top of the wind turbine cabin to collect the static value of ice on the top of the wind turbine cabin; A meteorological sensor is installed on the top of the wind turbine cabin and is used to collect current meteorological data on the top surface of the wind turbine cabin; At least one chip capacitive sensor is installed on the outer surface of the blade of the wind turbine to collect the blade surface ice coverage monitoring value of the outer surface of the blade; An image acquisition device, installed on the top of the wind turbine cabin, for acquiring current image data of the top surface of the wind turbine cabin; Collection cabinet, used to receive and forward static ice coverage values, current meteorological data, leaf surface ice coverage monitoring values ​​and current image data; The above-mentioned ice coating detection device for a wind turbine.

[0015] Through the above technical solution, meteorological data, image data and motion data are effectively integrated, and the impact of wind turbine blade position and blade movement on icing monitoring is fully considered. The monitoring data of different blade positions and even different wind turbines are effectively generalized to positions where icing monitoring is not directly performed, avoiding the limitation of using a single ice thickness data to represent the icing condition of the wind turbine. By predicting the icing condition at the blade surface position, the icing condition of the entire wind turbine blade can be fully perceived.

[0016] Other features and advantages of the embodiments of the present application will be described in detail in the subsequent specific implementation section. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present application, but do not constitute a limitation on the embodiments of the present application. In the accompanying drawings: Figure 1 A schematic diagram of a flow chart of an ice coating detection method for a wind turbine according to an embodiment of the present application is schematically shown; Figure 2 A schematic diagram of a flow chart of an ice coating detection method for a wind turbine according to another embodiment of the present application is shown; Figure 3 A schematic diagram of an ice detection system for a wind turbine according to an embodiment of the present application is schematically shown; Figure 4 An internal structural diagram of a computer device according to an embodiment of the present application.

[0018] Description of Reference Numerals DETAILED DESCRIPTION

[0019] In order to make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the specific implementation methods described herein are only used to illustrate and explain the embodiments of the present application, and are not used to limit the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0020] It should be noted that if the embodiments of the present application involve directional indications (such as up, down, left, right, front, back...), such directional indications are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0021] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present application, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or suggesting their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0022] Figure 1 The flowchart of the ice detection method for a wind turbine according to an embodiment of the present application is schematically shown. Figure 1 As shown, in one embodiment of the present application, a method for detecting ice coating on a wind turbine is provided, comprising the following steps: Step 101: Acquire any blade surface position of the wind turbine, current image data of the top of the wind turbine cabin, and current meteorological data.

[0023] When performing ice detection on a wind turbine, the processor may obtain the surface position of any blade of the wind turbine, the current image data of the top of the wind turbine cabin, and the current meteorological data. Specifically, an image acquisition device may be installed on the wind turbine, and the image acquisition device may be installed at a position convenient for photographing the top surface of the wind turbine cabin. A meteorological sensor may be installed on the wind turbine to collect the current meteorological data of the top of the wind turbine cabin, wherein the current meteorological data includes but is not limited to the temperature, atmospheric pressure, relative humidity, wind speed, and wind direction of the top of the wind turbine cabin.

[0024] Step 102: Determine current motion data of the wind turbine, where the current motion data includes the rotation speed of any blade surface position of the wind turbine, the current yaw angle, and the current pitch angle of any blade.

[0025] The processor can determine the current motion data of the wind turbine, wherein the current motion data includes the rotation speed of any blade surface position of the wind turbine, the current yaw angle, and the current pitch angle of any blade. Specifically, the processor can obtain the current rotation speed of the wind turbine, and can determine the distance between any blade surface position and the center point of the hub of the wind turbine, and can determine the rotation speed of any blade surface position based on the current rotation speed and the distance. The current yaw angle and the current pitch angle of any blade can be obtained by, but not limited to, monitoring of sensors.

[0026] Step 103: pre-process any blade surface position, current meteorological data, current image data and current motion data.

[0027] Since the acquired or determined data come from different acquisition devices, the data structures and characteristics are significantly different, so the processor can pre-process any blade surface position, current meteorological data, current image data, and current motion data. The pre-processing method may include repeated expansion and combined processing.

[0028] Step 104: Input the pre-processed position of any blade surface, current motion data, current image data and current meteorological data into an ice detection model to obtain a current ice correction value at any blade surface position.

[0029] The processor can input the preprocessed surface position of any blade, current motion data, current image data and current meteorological data into the ice detection model to obtain the current ice correction value at any blade surface position. The ice detection model is obtained based on a preset neural network training, wherein the preset neural network may include a multi-head attention layer, a forward propagation layer and an output layer neural network.

[0030] In an embodiment of the present application, at least one chip-type capacitive ice sensor is installed on the wind turbine, and an ice detection model is trained through the following steps: determining training data, the training data including the installation position of each chip-type capacitive ice sensor on the wind turbine, historical image data of the top surface of the wind turbine cabin, historical meteorological data of the wind turbine, and historical motion data of the wind turbine; inputting the training data into a preset neural network so that the preset neural network outputs a historical ice correction value; obtaining the historical ice static value of the top of the wind turbine cabin, and the blade surface ice monitoring value collected by each chip-type capacitive ice sensor; determining the loss value of the preset neural network based on the historical ice correction value, the historical ice static value, and all the blade surface ice monitoring values; when the loss value meets the preset conditions, determining that the training of the preset neural network is completed, and obtaining the ice detection model.

[0031] At least one chip capacitive ice sensor is installed on the wind turbine. The chip capacitive sensor is based on the silicon diaphragm capacitive sensor. It measures the ice thickness on the outer surface of the blade according to the change in equivalent capacitance caused by icing. It uses a flexible base plate to firmly and reliably attach to the blade surface without affecting the aerodynamic shape of the blade. It uses solar cell components and power management components to achieve energy acquisition. It uses ZigBee wireless transmission components to transmit data with the E collection cabinet, which has the advantages of low power consumption and low latency at a distance of 100 meters.

[0032] The processor can determine training data, which includes the installation position of each chip capacitive ice sensor on the wind turbine, historical image data of the top surface of the wind turbine cabin, historical meteorological data of the wind turbine, and historical movement data of the wind turbine.

[0033] In an embodiment of the present application, a meteorological sensor and an image acquisition device are installed on the wind turbine, and determining the training data includes: obtaining the installation position of each chip-type capacitive ice sensor on the wind turbine; receiving historical image data of the top surface of the cabin acquired by the image acquisition device; receiving historical meteorological data acquired by the meteorological sensor; obtaining the historical speed, yaw angle and pitch angle of the blade where each chip-type capacitive ice sensor is located; determining the rotation speed of the blade where each chip-type capacitive ice sensor is located according to the historical speed and the installation position of each chip-type capacitive ice sensor; determining the historical motion data of the wind turbine according to the rotation speed, yaw angle and pitch angle; and preprocessing the installation position, historical image data, historical meteorological data and historical motion data to obtain training data.

[0034] The processor can obtain the installation position of each chip-type capacitive ice sensor on the wind turbine. The installation position may be the tip, root, leading edge and trailing edge of the blade. The processor can receive historical image data of the top surface of the cabin collected by the image acquisition device, and can receive historical meteorological data collected by the meteorological sensor. The historical meteorological data may include but is not limited to temperature, atmospheric pressure, relative humidity, wind speed and wind direction. The processor can obtain the historical speed, yaw angle and pitch angle of the blade where each chip-type capacitive ice sensor is located from the wind turbine active system.

[0035] The processor can determine the rotation speed of the blade where each patch capacitive ice sensor is located according to the historical speed and the installation position of each patch capacitive ice sensor. In an embodiment of the present application, determining the rotation speed of the blade where each patch capacitive ice sensor is located according to the historical speed and the installation position of each patch capacitive ice sensor includes: determining the distance between the installation position of each patch capacitive ice sensor and the center point of the fan hub; determining the rotation speed of each patch capacitive ice sensor according to the historical speed and distance of the fan.

[0036] The processor can determine the distance between the installation position of each patch capacitive ice sensor and the center point of the fan hub, and can determine the rotation speed of each patch capacitive ice sensor according to the historical speed and distance of the fan. Specifically, in the embodiment of the present application, the rotation speed of each patch capacitive ice sensor is determined by the following formula: Formula (2) in, is the rotation speed of the i-th chip capacitive ice sensor, It refers to the distance between the i-th chip capacitive ice sensor and the center point of the fan hub. It refers to the historical speed of the fan where the i-th chip capacitor ice sensor is located.

[0037] The processor can determine the historical motion data of the wind turbine based on the rotation speed, yaw angle and pitch angle, and can pre-process the installation location, historical image data, historical meteorological data and historical motion data to obtain training data. Specifically, the location, meteorological and motion data features are basically floating point numbers f, which are repeatedly expanded into n-dimensional vectors Then, the vector addition, Hadamard product and other methods are used to perform preliminary fusion and expansion of each feature representation within the category to obtain a set of . Image data is generally represented as a multi-channel matrix with high dimensionality. An image pre-training model (such as VGG, ResNet) is used for feature extraction to obtain an n-dimensional vector representation Img_ext. After that, the various features can be pre-processed and spliced ​​to obtain k n-dimensional vector representations. The multi-head self-attention mechanism inside the Transformer structure is used to model the interaction and interaction between features of different categories. Under the condition of ensuring the stability of the model, heterogeneous modal features are effectively integrated. After that, a fully connected layer is used as the final output layer to output a floating point number as the ice monitoring correction value. .

[0038] The processor can input the training data into the preset neural network so that the preset neural network outputs the historical icing correction value. The processor can obtain the historical icing static value of the top of the wind turbine cabin and the blade surface icing monitoring value collected by each patch capacitive icing sensor. Among them, the historical icing static value can be collected by the microwave icing monitoring sensor on the wind turbine. The processor can determine the loss value of the preset neural network based on the historical icing correction value, the historical icing static value and all the blade surface icing monitoring values.

[0039] In the embodiment of the present application, the loss value of the preset neural network is determined by the following formula (1): Formula (1) in, refers to the loss value of the preset neural network, Refers to the number of chip capacitive ice sensors. refers to the historical ice cover correction value, Refers to the historical static value of ice cover, It refers to the leaf surface ice monitoring value collected by the i-th patch capacitive ice sensor.

[0040] When the loss value meets the preset conditions, the processor can determine that the preset neural network training is completed and obtain the ice detection model. The preset conditions can be that the loss value reaches a certain range, or that the loss value is less than a preset value, which can be set according to actual needs, so that the model output result is similar to the blade surface monitoring result under the correction of the model.

[0041] The processor may input the pre-processed position of any blade surface, current motion data, current image data and current meteorological data into the ice detection model to obtain the current ice correction value at any blade surface position.

[0042] Step 105: Obtain the current static value of ice coverage on the top of the nacelle of the wind turbine.

[0043] The processor may obtain the current static value of ice coating on the top of the nacelle of the wind turbine. Specifically, a microwave ice coating monitoring sensor may be installed on the wind turbine to collect the current static value of ice coating on the top of the nacelle of the wind turbine.

[0044] Step 106: Determine an ice coverage monitoring value at any blade surface position according to the current ice coverage correction value and the current ice coverage static value.

[0045] The processor may determine an ice coverage monitoring value at any blade surface position according to the current ice coverage correction value and the current ice coverage static value.

[0046] In an embodiment of the present application, determining the ice coverage monitoring value at any blade surface position according to the current ice coverage correction value and the current ice coverage static value includes: determining the total value between the current ice coverage correction value and the current ice coverage static value as the ice coverage monitoring value.

[0047] The processor may determine a total value between the current ice cover correction value and the current ice cover static value as the ice cover monitoring value.

[0048] like Figure 2 As shown, a flow chart of another method for detecting icing of a wind turbine is provided.

[0049] When monitoring ice cover, location data, meteorological data, motion data, and image data can be obtained. Among them, meteorological data may include temperature, relative humidity, atmospheric pressure, wind speed, and wind direction. Motion data may include rotation speed, yaw angle, and pitch angle. Afterwards, feature combination of location data, meteorological data, and motion data can be performed, and pre-training extraction of image data can be performed to obtain complete monitoring data.

[0050] Afterwards, the monitoring data can be sequentially input into the multi-head attention layer, the forward propagation layer, and the output layer to obtain the ice thickness correction value. Static ice data can be obtained, where the static ice data refers to the cabin top ice monitoring value of the microwave ice monitoring sensor. Then, the sum of the static ice data and the ice thickness correction value can be determined as the ice value.

[0051] In one embodiment, a method for detecting ice coating on a wind turbine is provided, comprising the following steps: Step 1: According to the three-dimensional model of the wind turbine blade and the actual monitoring needs, select several monitoring points on the wind turbine blade (such as the tip, root, leading edge, trailing edge, etc. of each blade), and install multiple patch capacitive ice sensors C, which are numbered in sequence. , and record the distance from the blade to the center of the hub (i.e. the distance from the installation location of each patch capacitive sensor to the center point of the wind turbine hub) and the three-dimensional coordinates of the blade surface (i.e. the three-dimensional installation position of each patch capacitive sensor).

[0052] Step 2: Install microwave ice monitoring sensor A, meteorological sensor and image acquisition equipment on the top of the wind turbine nacelle.

[0053] Step 3: The collection cabinet regularly collects the cabin top ice monitoring value of microwave ice monitoring sensor A , leaf surface ice monitoring values ​​of each patch capacitive ice sensor C , various meteorological data of meteorological sensor B (temperature Te, atmospheric pressure Pr, relative humidity Rh, wind speed Ws, wind direction Wd) and the ice coverage condition Img on the top surface of the cabin.

[0054] Step 4: The data acquisition cabinet transmits the collected data back to the host computer, which obtains the wind turbine speed Rs (in revolutions per minute rpm), yaw angle Ay and blade pitch angle Ap from the wind turbine main control system in real time and integrates them into monitoring data. ,in represents the rotation speed of the sensor, Indicates the opening and closing status of the blade where the sensor is located.

[0055]

[0056] Step 5: Construct a multi-sensor collaborative perception model, comprehensively consider sensor location, weather, motion, image and other data to correct the static ice monitoring value on the top of the cabin. It can be used as a data label for the ice thickness at the monitoring point, and the collaborative perception model can be used to fit it with other data and the static ice monitoring value on the top of the cabin. The difference.

[0057] Since the data come from different acquisition devices, there are significant differences in the structure and characteristics of the data. Therefore, preprocessing and internal expansion are performed before fusion.

[0058] The location, weather, and motion data features are basically floating point numbers f, which are expanded into n-dimensional vectors through repetition. Then, the vector addition, Hadamard product and other methods are used to perform preliminary fusion and expansion of each feature representation within the category to obtain a set of .

[0059] Image data is generally represented as a multi-channel matrix with high dimensionality. Image pre-training models (such as VGG, ResNet) are used for feature extraction to obtain an n-dimensional vector representation Img_ext. After preprocessing, various features are concatenated to obtain k n-dimensional vector representations. The multi-head self-attention mechanism inside the Transformer structure is used to model the interaction and interaction between features of different categories. Under the condition of ensuring the stability of the model, heterogeneous modal features are effectively integrated. A fully connected layer is used as the final output layer, and a floating point number is output as the ice monitoring correction value. .

[0060] Step 6: Repeat steps 3-5, and use the data collected from each monitoring point to train the multi-sensor collaborative perception model constructed in step 5. Use mean square error (MSE) as the loss function so that the model output results are similar to the blade surface monitoring results under model correction.

[0061] Step 7: Arbitrary given blade surface 3D coordinates , combined with the current meteorological, motion, image and other data, and input into the model trained in step 6, the ice coverage monitoring results of the corresponding position can be output, so that the monitoring data can be generalized to any position on the blade surface.

[0062] Through the above scheme, meteorological data, image data and motion data are effectively integrated, and the influence of wind turbine blade position and blade movement on icing monitoring is fully considered. The monitoring data of different blade positions and even different wind turbines are effectively generalized to positions where icing monitoring is not directly performed, avoiding the limitation of using single ice thickness data to represent the icing condition of the wind turbine. By predicting the icing condition at the blade surface position, the icing condition of the entire wind turbine blade can be fully perceived.

[0063] Figure 1 and Figure 2 FIG. 1 is a flow chart of a method for detecting ice coating on a wind turbine in one embodiment. It should be understood that although Figure 1 and Figure 2 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 1 and Figure 2 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0064] In one embodiment, an ice detection device for a wind turbine is provided, comprising: a memory configured to store instructions; The processor is configured to call instructions from the memory and implement the above-mentioned ice coating detection method for the wind turbine when executing the instructions.

[0065] In one embodiment, a storage medium is provided, on which a program is stored, and when the program is executed by a processor, the above-mentioned ice coating detection method for a wind turbine is implemented.

[0066] In one embodiment, a processor is provided, and the processor is used to run a program, wherein the program executes the above-mentioned ice coating detection method for a wind turbine when it is run.

[0067] In an embodiment of the present application, an ice detection system for a wind turbine is provided, comprising: The microwave ice monitoring sensor is installed on the top of the wind turbine cabin to collect the static value of ice on the top of the wind turbine cabin; A meteorological sensor is installed on the top of the wind turbine cabin and is used to collect current meteorological data on the top surface of the wind turbine cabin; At least one chip capacitive sensor is installed on the outer surface of the blade of the wind turbine to collect the blade surface ice coverage monitoring value of the outer surface of the blade; An image acquisition device, installed on the top of the wind turbine cabin, for acquiring current image data of the top surface of the wind turbine cabin; Collection cabinet, used to receive and forward static ice coverage values, current meteorological data, leaf surface ice coverage monitoring values ​​and current image data; The above-mentioned ice coating detection device for a wind turbine.

[0068] Among them, the microwave ice monitoring sensor includes a microwave antenna, a microwave transceiver module and a detection circuit. The degree of microwave attenuation during the transmission of a specific medium is used to estimate the dielectric constant of the medium and invert the ice thickness on the microwave antenna. The meteorological sensor is used to collect the current meteorological data on the top surface of the wind turbine cabin. The current meteorological data includes the temperature, atmospheric pressure, relative humidity, wind speed and wind direction data on the top of the cabin. The patch capacitive sensor is based on the silicon diaphragm capacitive sensor. According to the change of equivalent capacitance caused by icing, the ice thickness on the outer surface of the blade is measured; a flexible bottom plate is used to firmly and reliably attach to the blade surface without affecting the aerodynamic shape of the blade; the device is powered by solar cell components and power management components; ZigBee wireless transmission components are used to transmit data with the E collection cabinet, which has the advantages of low power consumption and low latency at a distance of hundreds of meters. The image acquisition device can be a camera, video camera, camera, recorder and other devices with image acquisition functions.

[0069] like Figure 3 As shown, a schematic diagram of an ice detection system for a wind turbine is provided.

[0070] Among them, A is a microwave ice monitoring sensor, B is a meteorological sensor, C is a patch capacitive sensor, D is an image acquisition device, E is a collection cabinet, and F is a host computer. Microwave ice monitoring sensor A, meteorological sensor B, and image acquisition device D are arranged on the flat area on the top of the wind turbine cabin. The patch capacitive sensor C is attached to the outer surface of the blade. The collection cabinet E is installed in the vacant position of the cabin. The host computer F is deployed in the relay protection room of the wind farm booster station.

[0071] Microwave ice monitoring sensor A includes a microwave antenna, a microwave transceiver module and a detection circuit. It uses the degree of attenuation of microwaves during transmission in a specific medium to estimate the dielectric constant of the medium and invert the ice thickness on the microwave antenna.

[0072] Meteorological sensor B is responsible for collecting temperature, atmospheric pressure, relative humidity, wind speed and wind direction data on the top of the cabin. The patch capacitive sensor C is based on a silicon diaphragm capacitive sensor. It measures the ice thickness on the outer surface of the blade based on the change in equivalent capacitance caused by icing. It uses a flexible bottom plate to firmly and reliably attach to the blade surface without affecting the aerodynamic shape of the blade. It uses solar cell components and power management components to achieve energy acquisition for the equipment. It uses ZigBee wireless transmission components to transmit data with the data collection cabinet E, which has the advantages of low power consumption and low latency at a distance of 100 meters.

[0073] Image acquisition device D is used to capture the ice condition on the top surface of the cabin. Collection cabinet E is responsible for receiving data from microwave ice monitoring sensor A, meteorological sensor B, patch capacitive sensor C and image acquisition device D. It is fixed in a vacant position in the cabin with a special bracket, can be powered in the cabin, and connected to the tower-based switch via optical fiber.

[0074] The host computer F is responsible for summarizing the ice-related data collected by each wind turbine in the entire wind farm and building a multi-sensor collaborative perception model. The database is mainly used to store the monitoring data in a structured manner, and a high-performance GPU is used for deep learning model training and inference.

[0075] The data collection cabinet E is responsible for collecting data. The microwave ice monitoring sensor A, meteorological sensor B and image acquisition device D located on the top of the cabin are connected to the collection cabinet E through wired communication; the patch capacitive sensor C sends data to the collection cabinet E by wireless transmission; the collection cabinet E of each wind turbine is connected to the wind turbine tower base switch through the optical fiber laid in the tower, and is transmitted to the upper computer F in the relay protection room of the wind farm substation with the help of the wind farm optical fiber ring network for aggregation; the upper computer F stores various monitoring data, completes the preprocessing and annotation of the data for the regression problem of ice thickness monitoring, uses GPU to complete deep learning heterogeneous modal feature fusion training, and is responsible for the prediction of wind turbine blade ice.

[0076] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 4As shown. The computer device includes a processor A01, a network interface A02, a memory (not shown in the figure) and a database (not shown in the figure) connected through a system bus. Among them, the processor A01 of the computer device is used to provide computing and control capabilities. The memory of the computer device includes an internal memory A03 and a non-volatile storage medium A04. The non-volatile storage medium A04 stores an operating system B01, a computer program B02 and a database (not shown in the figure). The internal memory A03 provides an environment for the operation of the operating system B01 and the computer program B02 in the non-volatile storage medium A04. The database of the computer device is used to store ice detection data. The network interface A02 of the computer device is used to communicate with an external terminal through a network connection. When the computer program B02 is executed by the processor A01, a method for detecting ice for a wind turbine is implemented.

[0077] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0078] An embodiment of the present application provides a device, which includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, the following steps are implemented: obtaining the surface position of any blade of the wind turbine, the current image data of the top of the wind turbine cabin, and the current meteorological data; determining the current motion data of the wind turbine, the current motion data including the rotation speed of the surface position of any blade of the wind turbine, the current yaw angle, and the current pitch angle of any blade; preprocessing the surface position of any blade, the current meteorological data, the current image data, and the current motion data; inputting the preprocessed surface position of any blade, the current motion data, the current image data, and the current meteorological data into an ice detection model to obtain a current ice correction value at any blade surface position; obtaining the current ice static value of the top of the wind turbine cabin; and determining the ice monitoring value at any blade surface position according to the current ice correction value and the current ice static value.

[0079] In one embodiment, at least one chip-type capacitive ice sensor is installed on the wind turbine, and an ice detection model is trained through the following steps: determining training data, the training data including the installation position of each chip-type capacitive ice sensor on the wind turbine, historical image data of the top surface of the wind turbine cabin, historical meteorological data of the wind turbine, and historical motion data of the wind turbine; inputting the training data into a preset neural network so that the preset neural network outputs a historical ice correction value; obtaining the historical ice static value of the top of the wind turbine cabin, and the blade surface ice monitoring value collected by each chip-type capacitive ice sensor; determining the loss value of the preset neural network based on the historical ice correction value, the historical ice static value, and all the blade surface ice monitoring values; when the loss value meets the preset conditions, determining that the training of the preset neural network is completed, and obtaining the ice detection model.

[0080] In one embodiment, the loss value of the preset neural network is determined by the following formula (1): Formula (1) in, refers to the loss value of the preset neural network, Refers to the number of chip capacitive ice sensors. refers to the historical ice cover correction value, Refers to the historical static value of ice cover, It refers to the leaf surface ice monitoring value collected by the i-th patch capacitive ice sensor.

[0081] In one embodiment, a meteorological sensor and an image acquisition device are installed on the wind turbine, and determining the training data includes: obtaining the installation position of each chip-type capacitive ice sensor on the wind turbine; receiving historical image data of the top surface of the cabin acquired by the image acquisition device; receiving historical meteorological data acquired by the meteorological sensor; obtaining the historical rotation speed, yaw angle and pitch angle of the blade where each chip-type capacitive ice sensor is located of the wind turbine; determining the rotation speed of the blade where each chip-type capacitive ice sensor is located according to the historical rotation speed and the installation position of each chip-type capacitive ice sensor; determining the historical motion data of the wind turbine according to the rotation speed, yaw angle and pitch angle; and preprocessing the installation position, historical image data, historical meteorological data and historical motion data to obtain training data.

[0082] In one embodiment, determining the rotation speed of the blade where each chip-type capacitive ice sensor is located based on the historical rotation speed and the installation position of each chip-type capacitive ice sensor includes: determining the distance between the installation position of each chip-type capacitive ice sensor and the center point of the fan hub; determining the rotation speed of each chip-type capacitive ice sensor based on the historical rotation speed and distance of the fan.

[0083] In one embodiment, the rotation speed of each chip capacitive ice sensor is determined by the following formula: Formula (2) in, is the rotation speed of the i-th chip capacitive ice sensor, It refers to the distance between the i-th chip capacitive ice sensor and the center point of the fan hub. It refers to the historical speed of the fan where the i-th chip capacitor ice sensor is located.

[0084] In one embodiment, determining the ice covering monitoring value at any blade surface position according to the current ice covering correction value and the current ice covering static value includes: determining a total value between the current ice covering correction value and the current ice covering static value as the ice covering monitoring value.

[0085] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program for initializing steps of an ice detection method for a wind turbine.

[0086] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0087] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0088] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0089] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0090] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0091] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0092] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0093] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0094] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for detecting ice coating on a fan, characterized in that: The ice coating detection method comprises: Acquire the surface position of any blade of the wind turbine, current image data of the top of the nacelle of the wind turbine, and current meteorological data; Determining current motion data of the wind turbine, the current motion data including a rotation speed of any blade surface position of the wind turbine, a current yaw angle, and a current pitch angle of any blade; Preprocessing any blade surface position, the current meteorological data, the current image data, and the current motion data; Inputting the preprocessed surface position of any blade, current motion data, current image data and current meteorological data into an ice detection model to obtain a current ice correction value at the surface position of any blade; Obtaining a current static value of ice coverage on the top of the nacelle of the wind turbine; An ice coverage monitoring value at any blade surface position is determined according to the current ice coverage correction value and the current ice coverage static value.

2. The method for detecting icing of a wind turbine according to claim 1, characterized in that: At least one chip capacitive ice sensor is installed on the fan, and the ice detection model is trained by the following steps: Determine training data, the training data including the installation position of each chip capacitive ice sensor on the wind turbine, historical image data of the top surface of the nacelle of the wind turbine, historical meteorological data of the wind turbine, and historical motion data of the wind turbine; Inputting the training data into a preset neural network so that the preset neural network outputs a historical ice coverage correction value; Obtaining the historical static value of ice coverage on the top of the nacelle of the wind turbine and the blade surface ice coverage monitoring value collected by each patch-type capacitive ice coverage sensor; Determining the loss value of the preset neural network according to the historical icing correction value, the historical icing static value and all blade surface icing monitoring values; When the loss value satisfies a preset condition, it is determined that the preset neural network training is completed, and the ice detection model is obtained.

3. The method for detecting icing of a wind turbine according to claim 2, characterized in that: The loss value of the preset neural network is determined by the following formula (1): Formula (1) in, refers to the loss value of the preset neural network, Refers to the number of chip capacitive ice sensors. refers to the historical ice cover correction value, Refers to the historical static value of ice cover, It refers to the leaf surface ice monitoring value collected by the i-th patch capacitive ice sensor.

4. The method for detecting icing of a wind turbine according to claim 2, characterized in that: The wind turbine is equipped with a meteorological sensor and an image acquisition device, and the training data determined includes: Get the installation position of each chip capacitor ice sensor on the fan; receiving historical image data of the top surface of the cabin acquired by the image acquisition device; Receiving historical meteorological data collected by the meteorological sensor; Obtaining the historical rotation speed, yaw angle and pitch angle of the blade where each chip-type capacitive ice sensor is located of the wind turbine; Determine the rotation speed of the blade where each patch type capacitive ice coating sensor is located according to the historical rotation speed and the installation position of each patch type capacitive ice coating sensor; Determine historical motion data of the wind turbine according to the rotation speed, the yaw angle, and the pitch angle; The installation location, the historical image data, the historical meteorological data, and the historical motion data are preprocessed to obtain the training data.

5. The method for detecting icing of a wind turbine according to claim 4, characterized in that: The step of determining the rotation speed of the blade where each patch type capacitive ice coating sensor is located according to the historical rotation speed and the installation position of each patch type capacitive ice coating sensor comprises: Determine the distance between the installation position of each patch capacitive ice sensor and the center point of the hub of the wind turbine; The rotation speed of each chip-type capacitive ice sensor is determined according to the historical rotation speed of the fan and the distance.

6. The method for detecting icing of a wind turbine according to claim 5, characterized in that: The rotation speed of each chip capacitive ice sensor is determined by the following formula: Formula (2) in, is the rotation speed of the i-th chip capacitive ice sensor, It refers to the distance between the ith chip capacitive ice sensor and the center point of the hub of the wind turbine. It refers to the historical speed of the fan where the i-th chip capacitor ice sensor is located.

7. The method according to claim 1, characterized in that Determining the ice coverage monitoring value at any blade surface position according to the current ice coverage correction value and the current ice coverage static value comprises: The total value between the current ice covering correction value and the current ice covering static value is determined as the ice covering monitoring value.

8. An ice detection device for a fan, characterized in that: The ice detection device comprises: a memory configured to store instructions; A processor is configured to call the instruction from the memory and implement the ice coating detection method for a wind turbine according to any one of claims 1 to 7 when executing the instruction.

9. An ice detection system for a fan, characterized in that: include: The microwave ice monitoring sensor is installed on the top of the wind turbine cabin to collect the static value of ice on the top of the wind turbine cabin; A meteorological sensor is installed on the top of the wind turbine cabin and is used to collect current meteorological data on the top surface of the wind turbine cabin; At least one chip capacitive sensor is installed on the outer surface of the blade of the wind turbine to collect the blade surface ice coverage monitoring value of the outer surface of the blade; An image acquisition device, installed on the top of the wind turbine cabin, for acquiring current image data of the top surface of the wind turbine cabin; A collection cabinet, used for receiving and forwarding the static value of ice coverage, the current meteorological data, the leaf surface ice coverage monitoring value and the current image data; An ice detection device for a wind turbine according to claim 8.

10. A machine-readable storage medium having instructions stored thereon, characterized in that: When the instruction is executed by a processor, the processor is configured to execute the ice coating detection method for a wind turbine according to any one of claims 1 to 7.

Images