Fan blade clearance prediction method and system, control device and storage medium

Abstract

The invention relates to the technical field of wind power, particularly provides a fan blade clearance prediction method and system, a control device and a storage medium, and aims to solve the technical problem that blade clearance cannot be accurately monitored under complex extreme wind conditions in the prior art. In order to achieve the purpose, the fan blade clearance prediction method comprises the steps that simulation extreme data, real-time data and historical data are obtained, and each kind of data at least comprises wind condition information, a clearance value and a control parameter; training to obtain a prediction model based on the simulation extreme data and historical data; and obtaining a predicted clearance value at the next moment based on the real-time data and the prediction model. According to the method, the model is trained by utilizing the obtained simulation data under the extremely complex wind condition, the trained prediction model can adapt to the complex and changeable wind condition, and the prediction model can be utilized to timely and accurately output the prediction clearance value at the next moment under the extremely complex wind condition, so that accurate data is provided for safe operation of the fan in advance.

Description

Technical Field

[0001] The present application relates to the technical field of wind power, and specifically provides a method, a system, a control device and a storage medium for predicting the clearance of a wind turbine blade. Background Art

[0002] With the continuous expansion of the scale of wind turbines and the rapid layout on a global scale, ensuring the safe and stable operation of wind turbines has become particularly important. With the enlargement and flexibility of the blades, the clearance control between the blades and the tower has become a key technology.

[0003] In the prior art, under complex, extreme and non-linear wind conditions, the accuracy and response ability of predicting the clearance value of a wind turbine are poor. As a result, in extreme environments such as high altitude, severe cold, and frequent sandstorms, the adaptability and robustness of the prior art face greater challenges. Therefore, there is an urgent need to develop a more accurate and robust method for predicting the clearance of blades, so as to accurately identify potential risks and quickly respond when the wind conditions change suddenly, ensuring the safe operation of wind turbines.

[0004] Correspondingly, there is a need in the art for a new solution of a method, a system, a control device and a storage medium for predicting the clearance of a wind turbine blade to solve the above problems. Summary of the Invention

[0005] In order to overcome the above defects, the present application is proposed to provide a method, a system, a control device and a storage medium for predicting the clearance of a wind turbine blade, which can solve or at least partially solve the technical problem that the clearance of the blade cannot be accurately monitored under complex and extreme wind conditions in the prior art.

[0006] In a first aspect, the present application provides a method for predicting the clearance of a wind turbine blade, the method comprising:

[0007] Obtaining simulation extreme data, real-time data and historical data, wherein each type of the data at least includes wind condition information, clearance value and control parameters;

[0008] Training a prediction model based on the simulation extreme data and the historical data;

[0009] Obtaining a predicted clearance value for the next moment based on the real-time data and the prediction model.

[0010] In a technical solution of the above method for predicting the clearance of a wind turbine blade, the method further comprises:

[0011] Obtaining target control parameters based on a preset first rule, the predicted clearance value and the wind condition information in the real-time data;

[0012] Controlling the operation of the wind turbine based on the target control parameters.

[0013] In one technical solution of the above-mentioned wind turbine blade clearance prediction method, the wind condition information in the real-time data includes at least the wind speed value, the target control parameters include at least the rotation speed of the wind turbine and the pitch angle of the wind turbine, and obtaining the target control parameters based on the preset first rule, the predicted clearance value, and the wind condition information in the real-time data includes:

[0014] Comparing the wind speed value with a preset first threshold, comparing the predicted clearance value with a preset second threshold, and comparing the predicted clearance value with a preset third threshold, wherein the preset second threshold is greater than the preset third threshold;

[0015] Based on the results of the three comparisons, adjusting the rotation speed of the wind turbine and / or the pitch angle of the wind turbine to obtain the target control parameters.

[0016] In one technical solution of the above-mentioned wind turbine blade clearance prediction method, adjusting the rotation speed of the wind turbine and / or the pitch angle of the wind turbine based on the results of the three comparisons includes:

[0017] If the predicted clearance value is less than the preset third threshold, adjusting the rotation speed of the wind turbine and the pitch angle of the wind turbine to corresponding preset values to control the wind turbine to execute an over-limit exit command;

[0018] If the predicted clearance value is less than the preset second threshold but not less than the preset third threshold, when the wind speed value is less than the preset first threshold, reducing the rotation speed value of the wind turbine to obtain the target control parameter, or when the wind speed value is not less than the preset first threshold, increasing the pitch angle of the wind turbine to obtain the target control parameter.

[0019] In one technical solution of the above-mentioned wind turbine blade clearance prediction method, the step of obtaining the clearance value in the real-time data includes:

[0020] Obtaining a real-time image of the target area, where the target area includes at least the wind turbine tower, the wind turbine blade, and the area between the wind turbine tower and the wind turbine blade;

[0021] Performing a preset processing operation on the real-time image to obtain the distance between the wind turbine tower and the wind turbine blade, which is recorded as the clearance value in the real-time data.

[0022] In one technical solution of the above-mentioned wind turbine blade clearance prediction method, performing a preset processing operation on the real-time image to obtain the distance between the wind turbine tower and the wind turbine blade includes:

[0023] Converting the real-time image into a grayscale image;

[0024] Perform edge detection on the grayscale image to obtain the edge contours of the wind turbine tower and the edge contours of the wind turbine blades;

[0025] Based on the edge contours of the wind turbine tower and the edge contours of the wind turbine blades, obtain the distance between the wind turbine tower and the wind turbine blades.

[0026] In a technical solution of the above wind turbine blade clearance prediction method, the obtaining the distance between the wind turbine tower and the wind turbine blades based on the edge contours of the wind turbine tower and the edge contours of the wind turbine blades includes:

[0027] Based on the edge contours of the wind turbine tower and the edge contours of the wind turbine blades, segment the grayscale image to obtain the positional relationship between the wind turbine tower and the wind turbine blades;

[0028] Based on the positional relationship, convert the pixel coordinates of the edge contour of the wind turbine tower into actual physical coordinates, and convert the pixel coordinates of the edge contour of the wind turbine blade into actual physical coordinates;

[0029] Based on the actual physical coordinates of the edge contour of the wind turbine tower and the actual physical coordinates of the edge contour of the wind turbine blade, obtain the distance between the wind turbine tower and the wind turbine blades.

[0030] In a second aspect, the present application provides a wind turbine blade clearance prediction system, and the system includes:

[0031] An acquisition module configured to acquire simulation extreme data, real-time data, and historical data, wherein each type of the data at least includes wind condition information, clearance value, and control parameters;

[0032] A processing module configured to train a prediction model based on the simulation extreme data and the historical data;

[0033] An analysis module configured to obtain a predicted clearance value at the next moment based on the real-time data and the prediction model.

[0034] In a third aspect, a control device is provided, and the control device includes a processor and a storage device. The storage device is adapted to store multiple program codes, and the program codes are adapted to be loaded and run by the processor to execute the wind turbine blade clearance prediction method according to any one of the technical solutions in the technical solution of the above wind turbine blade clearance prediction method.

[0035] In a fourth aspect, a computer-readable storage medium is provided, which stores multiple pieces of program codes. The program codes are adapted to be loaded and run by a processor to execute the wind turbine blade clearance prediction method described in any one of the technical solutions of the above technical solution of the wind turbine blade clearance prediction method.

[0036] One or more of the above technical solutions of the present application have at least one or more of the following beneficial effects:

[0037] In implementing the technical solution of the present application, a prediction model is obtained by training based on simulation extreme data and historical data; based on real-time data including clearance values and the prediction model, a predicted clearance value for the next moment is obtained. The present application uses the obtained simulation data under extremely complex wind conditions to train the model, enabling the model to have stronger adaptability and robustness in extreme environments (such as high altitude, severe cold, sandstorms, etc.), and reducing the prediction deviation caused by environmental factors. Through the present application, the trained prediction model can adapt to complex and variable wind conditions, such as scenarios of wind speed fluctuations and sudden changes in wind direction. Using the prediction model, the predicted clearance value for the next moment can be output in a timely and accurate manner under extreme wind conditions, thereby providing accurate data in advance for the safe operation of the wind turbine.

[0038] Furthermore, in implementing the technical solution of the present application, a target control parameter is obtained based on a preset first rule, the predicted clearance value, and the wind condition information in the real-time data. The present application dynamically adjusts the control parameters of the wind turbine based on the predicted clearance value, forming a closed-loop control mechanism and improving the intelligent level of the wind turbine operation. Through the present application, an optimal control strategy can be quickly generated according to different wind conditions and clearance prediction results, ensuring that the wind turbine can operate safely and efficiently under various working conditions.

[0039] Furthermore, in implementing the technical solution of the present application, the wind speed value is compared with a preset first threshold, the predicted clearance value is compared with a preset second threshold, and the predicted clearance value is compared with a preset third threshold. Thus, based on the results of the three comparisons, the rotation speed and / or the pitch angle of the wind turbine are adjusted. By setting the preset first threshold, the preset second threshold, and the preset third threshold, the present application monitors and compares the wind conditions and clearance states in multiple dimensions, improving the refinement degree of the control strategy. Through the present application, the rotation speed and pitch angle of the wind turbine can be adjusted respectively according to the comparison results of different thresholds, thereby realizing the differential control of the operation state of the wind turbine.

[0040] Furthermore, in implementing the technical solution of this application, when the predicted clearance value is less than a preset third threshold, the rotational speed and pitch angle can be quickly adjusted to preset values, and an overlimit exit instruction is executed to ensure that the wind turbine can stop in time in extreme dangerous situations and avoid major accidents. When the predicted clearance value is within the dangerous range but has not reached the overlimit state, the rotational speed value or pitch angle is selectively adjusted preferentially according to the wind speed, and the optimal adjustment strategy is selected on the premise of minimizing the impact on the power generation efficiency of the wind turbine, realizing the refined control of the clearance distance.

[0041] Furthermore, in implementing the technical solution of this application, by acquiring the real-time image of the target area, the clearance situation between the wind turbine tower and the blade can be visually monitored. Combining with image processing technology, the distance between the wind turbine tower and the blade can be accurately calculated, so as to obtain the accurate clearance value in real time.

[0042] Furthermore, in implementing the technical solution of this application, by converting the real-time image into a grayscale image and performing edge detection, redundant color information and environmental noise can be effectively removed, the contour features of the wind turbine tower and the blade are highlighted, and the efficiency and accuracy of image processing are improved.

[0043] Furthermore, in implementing the technical solution of this application, the positional relationship between the wind turbine tower and the blade can be accurately calculated through image segmentation. Based on the positional relationship, the pixel coordinates can be accurately converted into actual physical coordinates, realizing the mapping from the image space to the physical space, so as to accurately calculate the distance between the wind turbine tower and the blade. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Referring to the accompanying drawings, the disclosure of this application will become easier to understand. It is easy for those skilled in the art to understand that these drawings are only for illustrative purposes and are not intended to limit the protection scope of this application. In addition, similar numbers in the drawings are used to represent similar components, where:

[0045] Figure 1 is a schematic flowchart of the main steps of a method for predicting the clearance of a wind turbine blade according to an embodiment of this application;

[0046] Figure 2 is a schematic flowchart of the main steps of a method for predicting the clearance of a wind turbine blade according to an embodiment of this application;

[0047] Figure 3 is a schematic flowchart of the main steps of obtaining the real-time clearance value according to an embodiment of this application;

[0048] Figure 4 is a schematic program flowchart of the main steps of a method for predicting the clearance of a wind turbine blade according to an embodiment of this application;

[0049] Figure 5 It is a schematic diagram of the main structure block diagram of the fan blade clearance prediction system according to an embodiment of the present application.

[0050] List of reference numerals:

[0051] 11: Acquisition module; 12: Processing module; 13: Analysis module. Detailed implementation manners

[0052] The following describes some implementation manners of the present application with reference to the accompanying drawings. Those skilled in the art should understand that these implementation manners are only used to explain the technical principle of the present application and are not intended to limit the protection scope of the present application.

[0053] In the description of the present application, "module" and "processor" may include hardware, software, or a combination of both. A module may include a hardware circuit, various suitable sensors, communication ports, memories, and may also include a software part, such as program code, or a combination of software and hardware. The processor may be a central processing unit, a microprocessor, an image processor, a digital signal processor, or any other suitable processor. The processor has data and / or signal processing functions. The processor may be implemented in software, in hardware, or in a combination of both. The non-transitory computer-readable storage medium includes any suitable medium for storing program code, such as magnetic disks, hard disks, optical disks, flash memories, read-only memories, random access memories, and so on. The term "A and / or B" represents all possible combinations of A and B, such as only A, only B, or A and B. The term "at least one A or B" or "at least one of A and B" has a meaning similar to "A and / or B" and may include only A, only B, or A and B. The singular terms "a" and "this" may also include the plural form.

[0054] Please refer to the attached Figure 1 , Figure 1 is a schematic diagram of the main step flow of the fan blade clearance prediction method according to an embodiment of the present application. As Figure 1 shown, the fan blade clearance prediction method of the present application mainly includes steps S1 - step S3:

[0055] Step S1, acquire simulation extreme data, real-time data, and historical data;

[0056] Step S2, train a prediction model based on the simulation extreme data and historical data;

[0057] Step S3, obtain the predicted clearance value at the next moment based on the real-time data and the prediction model.

[0058] In this embodiment: The simulated extreme data is the operating data of the wind turbine under extreme working conditions generated by numerical simulation or experiment, such as the operating data of the wind turbine in environments with extremely high wind speed values or drastic wind condition changes like typhoons and snowstorms; the real-time data is the operating data of the wind turbine at the current moment, such as the mechanical state parameters, electrical parameters, and environmental wind condition parameters of the wind turbine; the historical data is the historical operating data of the wind turbine, such as the mechanical state parameters, electrical parameters, and environmental wind condition parameters of the wind turbine. The above three types of data all include at least wind condition information, clearance value, and control parameters. Among them, the wind condition information can include wind-related parameters, such as wind speed, wind direction, turbulence intensity, wind shear, etc. The clearance value is the minimum distance between the blade tip and the tower barrel, and the control parameters can include blade pitch angle, yaw angle, generator torque, etc.

[0059] In this embodiment: Since the historical data mainly records the operating state of the wind turbine under normal working conditions, but extreme events such as typhoons occur with a low frequency, resulting in the lack of extreme working condition samples in the historical data, it is necessary to additionally introduce simulated extreme data to make up for the deficiency of extreme events in the historical data, so that the finally obtained prediction model can accurately output prediction data under different working conditions. During the training process, if the data formats or structures of the historical data and the simulation data are different, data preprocessing is required, which can include but is not limited to data cleaning and data fusion, etc. In terms of model architecture selection, considering that time series data needs to be processed, LSTM, Transformer, CNN, etc. can be selected. During the training process, the historical data can be used for pre-training first, and then the extreme data can be used for fine-tuning to avoid the model from failing in extreme situations.

[0060] In this embodiment: The predicted clearance value is the prediction result output by the prediction model obtained from the previous steps based on one or more of the relevant data at the current moment, such as wind condition information, clearance value, and control parameters. Among them, the time interval duration between the current moment and the next moment is not specifically limited.

[0061] Please refer to the attached Figure 1 and the attached Figure 2 , Figure 2 which is a schematic diagram of the main step flow of the wind turbine blade clearance prediction method according to an embodiment of the present application. As Figure 2 shown, the wind turbine blade clearance prediction method of the present application may further include steps S4 - S5:

[0062] Step S4: Based on a preset first rule, the predicted clearance value, and the wind condition information in the real-time data, obtain the target control parameter;

[0063] Step S5: Control the operation of the wind turbine based on the target control parameter.

[0064] In this embodiment, the preset first rule may be to respectively determine the magnitudes of the predicted clearance value and the corresponding safety threshold, the wind speed value in the wind condition information and the corresponding safety threshold, and the wind speed change rate value in the wind condition information and the corresponding safety threshold, and then confirm whether it is necessary to adjust the control parameter and the specific value of the adjusted control parameter according to their respective weights. Or, determine the safety level of each value based on the magnitudes of the values, and determine the target control parameter based on each safety level. Or, input the comparison results of each value and the corresponding safety threshold into a pre-trained model, and the model outputs the target control parameter.

[0065] In this embodiment, the target control parameter is the control parameter at the next moment after adjustment (or without adjustment). This embodiment does not limit the specific numerical calculation method of the target control parameter. Parse the target control parameter into the corresponding control instruction, and send the control instruction to the control center of the corresponding execution unit, and each control center drives the execution unit to execute the control instruction.

[0066] In an implementation manner of this embodiment, the wind condition information in the real-time data includes at least the wind speed value, and the target control parameter includes at least the rotational speed of the wind turbine and the pitch angle of the wind turbine. In this implementation manner, the above step S4 may further include steps S41 - S42:

[0067] Step S41: Compare the wind speed value with a preset first threshold, compare the predicted clearance value with a preset second threshold, and compare the predicted clearance value with a preset third threshold, where the preset second threshold is greater than the preset third threshold;

[0068] Step S42: Based on the results of the three comparisons, adjust the rotational speed of the wind turbine and / or the pitch angle of the wind turbine to obtain the target control parameter.

[0069] In this embodiment: A first preset threshold is used to determine whether the current wind condition is a high wind speed. If the wind speed value is less than the first preset threshold, it is a low wind speed; if the wind speed value is not less than the first preset threshold, it is a high wind speed. A second preset threshold is used to determine whether the predicted clearance value at the next moment meets the safety distance, and a third preset threshold is used to determine whether the predicted clearance value at the next moment meets the limit distance. If the predicted clearance value is greater than the second preset threshold, it means that the predicted clearance value at the next moment is within the safety distance. If the predicted clearance value is less than the second preset threshold but not less than the third preset threshold, it means that the predicted clearance value at the next moment is within the non-safe distance with potential hazards. If the predicted clearance value is less than the third preset threshold, it means that the predicted clearance value at the next moment is within the dangerous distance where emergency measures must be taken. According to the results of the above comparisons, the optimal adjustment control parameters can be considered in multiple dimensions by, for example, weighted summation, or through a pre-trained model. The comparison results of the three values are input into the model, and the model outputs the optimal target control parameters.

[0070] In one embodiment, step S42 specifically includes: If the predicted clearance value is less than the third preset threshold, adjust the rotation speed of the wind turbine and the pitch angle of the wind turbine to the corresponding preset values to control the wind turbine to execute the overlimit exit instruction; if the predicted clearance value is less than the second preset threshold but not less than the third preset threshold, when the wind speed value is less than the first preset threshold, reduce the rotation speed value of the wind turbine to obtain the target control parameter, or when the wind speed value is not less than the first preset threshold, increase the pitch angle of the wind turbine to obtain the target control parameter. In this embodiment: If the predicted clearance value is less than the third preset threshold, it means that the predicted clearance value at the next moment is within the dangerous distance where emergency measures must be taken. Therefore, it is necessary to increase the pitch angle and reduce the rotation speed value at the same time to prevent the wind turbine blades from colliding with the tower barrel; if the predicted clearance value is less than the second preset threshold but not less than the third preset threshold, and when the wind speed value is less than the first preset threshold, that is, low wind speed, the rotation speed value is adjusted first. The reason is that the wind turbine will pursue maximum power tracking at low wind speeds, that is, capture as much wind energy as possible. The pitch angle generally remains at the optimal angle to maximize lift. If the pitch angle is increased at this time, it will instead reduce the wind energy captured by the blades, resulting in reduced efficiency. Therefore, it is more reasonable to adjust the rotation speed at low wind speeds, which can not only maintain efficiency but also not lose too much energy; if the predicted clearance value is less than the second preset threshold but not less than the third preset threshold, and when the wind speed value is greater than the first preset threshold, that is, high wind speed, the pitch angle is adjusted first. The reason is that when the wind speed exceeds the rated wind speed, the wind turbine needs to limit the power output to prevent overload. At this time, increasing the pitch angle can change the angle of the blades, reduce lift, thereby reducing torque and power. If only the rotation speed is reduced, although the power can also be limited, it may affect the synchronous operation of the generator or cause the rotation speed to be too low to maintain the grid frequency. In addition, the structural load is greater at high wind speeds, and increasing the pitch angle can quickly unload the load and protect the mechanical structure from excessive stress.

[0071] Please refer to the attached Figure 1 and the attached Figure 3 , Figure 3 is a schematic diagram of the main steps for obtaining the real-time clearance value according to an embodiment of the present application. As Figure 3 shown, in step S1 of the method for predicting the clearance of the fan blade of the present application, the process of obtaining the real-time clearance value mainly includes steps S01 - S02:

[0072] Step S01, obtain a real-time image of the target area;

[0073] Step S02, perform a preset processing operation on the real-time image to obtain the distance between the fan tower and the fan blade, denoted as the clearance value in the real-time data.

[0074] In this embodiment: The target area refers to the area between the fan tower and the fan blade, and this target area should at least include the outer contour of the fan tower on the side close to the fan blade and the outer contour of the fan blade on the side close to the fan tower.

[0075] In this embodiment: The preset processing operation includes but is not limited to denoising and enhancement, distortion correction, and feature extraction, and finally obtaining the shortest distance between the fan blade and the fan tower in the actual physical space through camera calibration. Or, a large number of data sets containing the target area are used in advance to train a model, and the shortest distance between the fan blade and the fan tower in the real-time image is determined through the trained model.

[0076] In an implementation manner of this embodiment, step S02 may further include steps S021 - S023:

[0077] Step S021, convert the real-time image into a grayscale image;

[0078] Step S022, perform edge detection on the grayscale image to obtain the edge contour of the fan tower and the edge contour of the fan blade;

[0079] Step S023, based on the edge contour of the fan tower and the edge contour of the fan blade, obtain the distance between the fan tower and the fan blade.

[0080] In this embodiment: The conversion of a real-time image into a grayscale image can be achieved by using a Python-based color space conversion method, or the average value method, the maximum value method, etc. The Canny edge detection method can be used, or an edge detection method based on deep learning can be used, or the edge contour of the wind turbine tower and the edge contour of the wind turbine blade can be obtained by calculating the image gradient. After obtaining the edge contours of the two, the key points can be located first, and then the pixel coordinates of the key points can be converted into actual physical coordinates through spatial mapping, so as to obtain the distance between the two. Or, a trajectory model of the wind turbine blade can be established in advance, the current movement position of the wind turbine blade can be determined through the contour of the wind turbine blade, and finally, based on the trajectory model and the current movement position, the distance between the two can be obtained.

[0081] In one embodiment, the above step S03 may specifically include: based on the edge contour of the wind turbine tower and the edge contour of the wind turbine blade, segmenting the grayscale image to obtain the positional relationship between the wind turbine tower and the wind turbine blade; based on the positional relationship, converting the pixel coordinates of the edge contour of the wind turbine tower into actual physical coordinates, and converting the pixel coordinates of the edge contour of the wind turbine blade into actual physical coordinates; based on the actual physical coordinates of the edge contour of the wind turbine tower and the actual physical coordinates of the edge contour of the wind turbine blade, obtaining the distance between the wind turbine tower and the wind turbine blade.

[0082] Please refer to the appendix Figure 4 , Figure 4 which is a schematic flowchart of the main steps of a method for predicting the clearance of a wind turbine blade according to an embodiment of the present application. As Figure 4 shown, in a specific implementation example, the method for predicting the clearance of a wind turbine blade of the present application can be described as follows:

[0083] Install a high-resolution camera on the wind turbine nacelle or tower to capture the moving image between the blade and the tower in real time. Ensure complete coverage of the rotation trajectory of the blade through the image acquisition means of multiple frames per second, and quickly transmit the data to the central processing unit; then perform grayscale processing on the image data to remove redundant color information, and use a Gaussian filter to eliminate the influence of environmental noise, such as interference from dust and light changes. To ensure the clarity of the image, use the Canny edge detection algorithm to extract the contours of the blade and the tower, and correct the edge features through morphological operations to eliminate isolated noise points and ensure the integrity and continuity of the boundary. After completing the edge detection, accurately identify the positional relationship between the blade and the tower through the method of image segmentation, and finally, through camera calibration and coordinate conversion, convert the pixel coordinates into actual physical coordinates, so as to obtain high-precision clearance distance data.

[0084] By extracting historical clearance data under different wind conditions and incorporating simulation data of extreme working conditions such as sudden change in wind speed and drastic change in wind direction into the training set for training, the coverage range of the data is extended to ensure that the model can adapt to the prediction requirements under various working conditions. After all the input data is standardized, it is input into the LSTM model, enabling it to effectively learn the relationship between the clearance of the wind turbine under different wind conditions and the incoming flow wind speed, pitch angle β, and blade rotation speed ω. The LSTM model dynamically manages the information flow through the structure of the input gate, forget gate, and output gate, capturing the long-term dependencies in the time-series data, thereby achieving accurate prediction of the clearance change.

[0085] Through the LSTM prediction model, the relationship between the clearance change and control parameters under different wind speed segments and different wind speed change rates can be obtained through simulation. By comparing the predicted clearance value with the control threshold and the danger threshold, the corresponding control strategy can be obtained. If the predicted clearance value is less than the danger threshold, the overrun exit strategy is activated to prevent blade damage or collision with the tower barrel. If the predicted clearance value is less than the control threshold but not less than the danger threshold, the optimal adjustment strategy is determined according to the wind speed conditions. Specifically, under low wind speed conditions, the clearance distance is effectively increased by reducing the wind turbine rotor speed, thereby reducing the tip speed ratio and increasing the pitch angle. Under high wind speed conditions, the control of the pitch angle is prioritized, and the real-time pitch control system will perform fine pitch angle adjustment to ensure that the increase in the pitch angle can keep the unit at a safe clearance distance.

[0086] So far, the method for predicting the clearance of the fan blade of the present application has been fully described. It should be noted that although the above steps are described in a specific order in the above embodiments, those skilled in the art can understand that in order to achieve the effects of the present application, different steps do not necessarily have to be executed in such an order. They can be executed simultaneously (in parallel) or in other orders, and these changes are all within the protection scope of the present application.

[0087] Furthermore, the present application also provides a system for predicting the clearance of a fan blade.

[0088] Refer to the attached Figure 5 , Figure 5 which is the main structural block diagram of the system for predicting the clearance of a fan blade according to an embodiment of the present application. As Figure 5As shown in the figure, the fan blade clearance prediction system in the embodiments of the present application mainly includes an acquisition module 11, a processing module 12, and an analysis module 13. In some embodiments, one or more of the acquisition module 11, the processing module 12, and the analysis module 13 may be combined into one module. In some embodiments, the acquisition module 11 may be configured to acquire simulation extreme data, real-time data, and historical data, wherein each type of the data at least includes wind condition information, clearance value, and control parameters. The processing module 12 may be configured to train a prediction model based on the simulation extreme data and the historical data. The analysis module 13 may be configured to obtain a predicted clearance value at the next moment based on the real-time data and the prediction model. In one implementation manner, the description of the specific functions implemented by the acquisition module 11 may be referred to step S1. In one implementation manner, the description of the specific functions implemented by the processing module 12 may be referred to step S2. In one implementation manner, the description of the specific functions implemented by the analysis module 13 may be referred to step S3. In one implementation manner, the processing module 12 may further be configured to obtain a target control parameter based on a preset first rule, the predicted clearance value, and the wind condition information in the real-time data, and control the operation of the fan based on the target control parameter.

[0089] The above fan blade clearance prediction system is used to execute Figure 1 the method embodiments of the fan blade clearance prediction shown in the figure. The technical principles, the technical problems solved, and the technical effects produced by the two are similar. Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working process and related descriptions of the fan blade clearance prediction system can refer to the content described in the embodiments of the fan blade clearance prediction method, which will not be elaborated here.

[0090] Those skilled in the art can understand that all or part of the processes of the methods in the above embodiments of the present application can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form. The computer-readable storage medium may include: any entity or device, medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory, random access memory, electrical carrier signal, telecommunication signal, and software distribution medium that can carry the computer program code.

[0091] Furthermore, the present application also provides a control device. In an embodiment of the control device according to the present application, the control device includes a processor and a storage device. The storage device can be configured to store a program for executing the method for predicting the clearance of the wind turbine blade in the above method embodiment. The processor can be configured to execute the program in the storage device, and the program includes, but is not limited to, the program for executing the method for predicting the clearance of the wind turbine blade in the above method embodiment. For the sake of convenience of description, only the parts related to the embodiments of the present application are shown. For the specific technical details not disclosed, please refer to the method part of the embodiments of the present application. The control device can be a control device formed by various electronic devices.

[0092] Furthermore, the present application also provides a computer-readable storage medium. In an embodiment of the computer-readable storage medium according to the present application, the computer-readable storage medium can be configured to store a program for executing the method for predicting the clearance of the wind turbine blade in the above method embodiment. The program can be loaded and run by a processor to implement the above method for predicting the clearance of the wind turbine blade. For the sake of convenience of description, only the parts related to the embodiments of the present application are shown. For the specific technical details not disclosed, please refer to the method part of the embodiments of the present application. The computer-readable storage medium can be a storage device formed by various electronic devices. Optionally, the computer-readable storage medium in the embodiments of the present application is a non-transitory computer-readable storage medium.

[0093] Furthermore, it should be understood that since the setting of each module is only to illustrate the functional units of the device of the present application, the corresponding physical devices of these modules can be the processor itself, or a part of the software in the processor, a part of the hardware, or a part of the combination of software and hardware. Therefore, the number of each module in the figure is only illustrative.

[0094] Those skilled in the art can understand that the various modules in the device can be adaptively split or combined. Such splitting or combination of the specific modules will not cause the technical solution to deviate from the principle of the present application. Therefore, the technical solutions after splitting or combination will all fall within the protection scope of the present application.

[0095] So far, the technical solutions of the present application have been described in conjunction with the preferred embodiments shown in the drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present application is obviously not limited to these specific embodiments. Without departing from the principle of the present application, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the protection scope of the present application.

Claims

1. A method for predicting the clearance of fan blades, characterized in that: The method comprises: Acquire simulated extreme data, real-time data and historical data, wherein each of the data includes at least wind condition information, clearance value and control parameters; Based on the simulated extreme data and the historical data, a prediction model is obtained by training; Based on the real-time data and the prediction model, a predicted headroom value at the next moment is obtained.

2. The wind turbine blade clearance prediction method according to claim 1, characterized in that: The method further comprises: Obtaining a target control parameter based on a preset first rule, the predicted clearance value, and wind condition information in the real-time data; The operation of the fan is controlled based on the target control parameter.

3. The wind turbine blade clearance prediction method according to claim 2, characterized in that: The wind condition information in the real-time data includes at least a wind speed value, the target control parameter includes at least a rotation speed of the wind turbine and a pitch angle of the wind turbine, and the target control parameter is obtained based on the preset first rule, the predicted clearance value and the wind condition information in the real-time data, including: Comparing the wind speed value with a preset first threshold, comparing the predicted clearance value with a preset second threshold, and comparing the predicted clearance value with a preset third threshold, wherein the preset second threshold is greater than the preset third threshold; Based on the results of the three comparisons, the rotation speed of the wind turbine and / or the pitch angle of the wind turbine are adjusted to obtain the target control parameter.

4. The wind turbine blade clearance prediction method according to claim 3, characterized in that: The adjusting the rotation speed of the wind turbine and / or the pitch angle of the wind turbine based on the three comparison results comprises: If the predicted clearance value is less than the preset third threshold, adjusting the rotation speed of the wind turbine and the pitch angle of the wind turbine to corresponding preset values, so as to control the wind turbine to execute an over-limit exit instruction; If the predicted clearance value is less than the preset second threshold but not less than the preset third threshold, then when the wind speed value is less than the preset first threshold, the speed value of the wind turbine is reduced to obtain the target control parameter, or, when the wind speed value is not less than the preset first threshold, the pitch angle of the wind turbine is increased to obtain the target control parameter.

5. The wind turbine blade clearance prediction method according to claim 1, characterized in that: The step of obtaining the headroom value in the real-time data comprises: Acquire a real-time image of a target area, wherein the target area includes at least a wind turbine tower, wind turbine blades, and an area between the wind turbine tower and the wind turbine blades; A preset processing operation is performed on the real-time image to obtain the distance between the wind turbine tower and the wind turbine blades, which is recorded as the clearance value in the real-time data.

6. The wind turbine blade clearance prediction method according to claim 5, characterized in that: The performing a preset processing operation on the real-time image to obtain the distance between the wind turbine tower and the wind turbine blades includes: Converting the real-time image into a grayscale image; Performing edge detection on the grayscale image to obtain the edge contour of the wind turbine tower and the edge contour of the wind turbine blade; Based on the edge profile of the wind turbine tower and the edge profile of the wind turbine blade, a distance between the wind turbine tower and the wind turbine blade is obtained.

7. The wind turbine blade clearance prediction method according to claim 6, characterized in that: The obtaining the distance between the wind turbine tower and the wind turbine blade based on the edge profile of the wind turbine tower and the edge profile of the wind turbine blade comprises: Based on the edge contour of the wind turbine tower and the edge contour of the wind turbine blade, the grayscale image is segmented to obtain the positional relationship between the wind turbine tower and the wind turbine blade; Based on the positional relationship, the pixel coordinates of the edge contour of the wind turbine tower are converted into actual physical coordinates, and the pixel coordinates of the edge contour of the wind turbine blade are converted into actual physical coordinates; Based on the actual physical coordinates of the edge contour of the wind turbine tower and the actual physical coordinates of the edge contour of the wind turbine blade, the distance between the wind turbine tower and the wind turbine blade is obtained.

8. A fan blade clearance prediction system, characterized in that: The system comprises: An acquisition module, the acquisition module is configured to acquire simulated extreme data, real-time data and historical data, wherein each of the data includes at least wind condition information, clearance value and control parameters; A processing module, wherein the processing module is configured to train a prediction model based on the simulated extreme data and the historical data; An analysis module is configured to obtain a predicted headroom value at a next moment based on the real-time data and the prediction model.

9. A control device, comprising a processor and a storage device, wherein the storage device is suitable for storing a plurality of program codes, characterized in that: The program code is suitable for being loaded and run by the processor to execute the wind turbine blade clearance prediction method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a plurality of program codes, characterized in that: The program code is suitable for being loaded and run by a processor to execute the wind turbine blade clearance prediction method according to any one of claims 1 to 7.

Images