Fan blade clearance monitoring method and system, electronic device and storage medium

Abstract

The application relates to the technical field of wind turbine units, and particularly provides a wind turbine blade clearance monitoring method and system, an electronic device and a storage medium, and aims to solve the problems of low detection accuracy and high false alarm rate of the existing clearance monitoring technology. Therefore, the wind turbine blade clearance monitoring method comprises the following steps: acquiring monitoring data of a wind turbine blade at a current moment, wherein the monitoring data comprises clearance data, pitch angle data and blade rotating speed data; inputting the monitoring data into a pre-constructed clearance prediction model to predict operation data of the wind turbine blade at a next moment, the clearance prediction model being constructed based on actual operation data and simulation operation data; and outputting alarm information based on the operation data of the wind turbine blade at the next moment. The clearance prediction model is constructed by using the actual operation data and the simulation operation data, the accuracy of the judgment of the dangerous tower scanning working condition of the wind turbine blade is improved, and the operation safety of the wind turbine unit is effectively ensured.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of wind power generation, in particular to a wind turbine blade clearance monitoring method and system, an electronic device and a storage medium. BACKGROUND

[0002] In the field of wind power generation, with the large-scale development of wind turbine blades and the rapid development of wind farms, it is particularly important to ensure the safe operation of wind turbines. The clearance distance between the blade and the tower is one of the key factors affecting the safety of wind turbines. The introduction of machine learning and machine vision technology provides a new solution for wind turbine clearance monitoring, making blade clearance monitoring and prediction more intuitive and accurate. There are related video clearance systems to monitor and predict blade clearance to ensure the safety of the unit. However, the current clearance prediction system has the problems of low accuracy and high false alarm rate, which leads to the problem of "early warning but unable to prevent" in the clearance warning and tower sweeping prevention system. In addition, with the development of wind farms in more complex and harsh environments, such as deserts, gobi and desert areas, higher requirements are put forward for the environmental adaptability and accuracy of the clearance prediction technology.

[0003] Correspondingly, there is a need for a new wind turbine blade clearance monitoring scheme to solve the above problems. SUMMARY

[0004] In order to overcome the above defects, the present application is proposed to solve or at least partially solve the technical problems of low accuracy and high false alarm rate of the clearance prediction system.

[0005] In a first aspect, a wind turbine blade clearance monitoring method is provided, the method comprising: obtaining monitoring data of a wind turbine blade at a current time, wherein the monitoring data comprises clearance data, pitch angle data and blade speed data; inputting the monitoring data into a pre-constructed clearance prediction model to predict operation data of the wind turbine blade at a next time, the clearance prediction model being constructed based on actual operation data and simulation operation data; and controlling an alarm information to be output based on the operation data of the wind turbine blade at the next time.

[0006] In one technical solution of the above wind turbine blade clearance monitoring method, the clearance prediction model is constructed by the following steps: obtaining actual operation data; obtaining simulation operation data; determining a training data set based on the actual operation data and the simulation operation data; and constructing a clearance prediction model based on the training data set.

[0007] In one technical solution of the above wind turbine blade clearance monitoring method, the actual operation data is obtained by: obtaining clearance data, corresponding pitch angle data and blade speed data of different types of wind turbines under normal operating conditions as actual operation data.

[0008] In a technical scheme of the fan blade clearance monitoring method, the obtaining of the simulation running data comprises: solving Navier-Stokes equations by using computational fluid dynamics to determine flow field information of the wind turbine generator; performing performance analysis on the wind turbine generator rotor blade based on the flow field information of the wind turbine generator, aerodynamic characteristics of a two-dimensional airfoil, and momentum theory by using a fan actuation line method; determining aerodynamic performance related parameters of the wind wheel by using momentum theory and considering the influence of the wind wheel on the incoming flow; obtaining running data of the wind turbine generator under different loads based on the aerodynamic performance related parameters of the wind wheel; and performing screening on the running data under different loads based on a preset screening condition to obtain simulation clearance data, corresponding simulation pitch angle data, and simulation blade rotating speed data under a dangerous working condition as simulation running data, wherein the dangerous working condition comprises an extreme wind speed working condition, an extreme wind direction change working condition, a fault working condition, a special environment working condition, and an operation working condition.

[0009] In a technical scheme of the fan blade clearance monitoring method, the determining of the training data set based on the actual running data and the simulation running data comprises: performing data preprocessing on the actual running data and the simulation running data respectively to obtain a training data set, wherein the data preprocessing comprises at least one of missing value processing, abnormal value processing, noise reduction processing, and normalization processing.

[0010] In a technical scheme of the fan blade clearance monitoring method, the constructing of the clearance prediction model based on the training data set comprises: constructing a long short-term memory neural network model, training the long short-term memory neural network model by using the training data set, taking clearance data, pitch angle data, and blade rotating speed data at a current time as input, and outputting clearance data, pitch angle data, and blade rotating speed data at a next time by the long short-term memory neural network, taking mean square error as a model loss function, selecting Adam as a model optimizer, evaluating prediction performance of the long short-term memory neural network model by using mean absolute error, and obtaining a trained clearance prediction model in a case where the prediction performance reaches a preset standard.

[0011] In a technical scheme of the fan blade clearance monitoring method, the controlling of the output of the alarm information based on the running data of the fan blade at the next time comprises: judging whether the fan blade has a tower scanning risk based on the running data of the fan blade at the next time, generating alarm information if yes, and judging as a safe state if no.

[0012] In a second aspect, a wind turbine blade clearance monitoring system is provided, the system comprising: an acquisition module configured to acquire monitoring data of a wind turbine blade at a current time; a prediction module configured to predict operation data of the wind turbine blade at a next time using a pre-constructed clearance prediction model, the clearance prediction model being constructed based on actual operation data and simulation operation data; and a control module configured to control output of an alarm information based on the operation data of the wind turbine blade at the next time.

[0013] In a third aspect, an electronic device is provided, the electronic device comprising at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program, and the computer program is executed by the at least one processor to implement the method of any one of the technical solutions of the wind turbine blade clearance monitoring method.

[0014] In a fourth aspect, a computer readable storage medium is provided, the computer readable storage medium storing a plurality of program codes therein, the program codes being adapted to be loaded and executed by a processor to implement the method of any one of the technical solutions of the wind turbine blade clearance monitoring method.

[0015] The one or more technical solutions of the present application have at least one or more of the following beneficial effects:

[0016] The wind turbine blade clearance monitoring method provided by the present application comprises: acquiring monitoring data of a wind turbine blade at a current time, wherein the monitoring data comprises clearance data, pitch angle data and blade rotation speed data; inputting the monitoring data into a pre-constructed clearance prediction model to predict operation data of the wind turbine blade at a next time, the clearance prediction model being constructed based on actual operation data and simulation operation data; and controlling output of an alarm information based on the operation data of the wind turbine blade at the next time. The simulation operation data is obtained by using a numerical simulation method, and can simulate and supplement dangerous working conditions that are difficult to capture in actual operation. By combining the actual operation data and the simulation operation data to construct the clearance prediction model, the prediction ability of the model in dangerous working conditions can be significantly improved, so that the alarm information is issued according to the prediction result, the operation safety of the wind turbine generator is effectively ensured, and the loss caused by accidental shutdown is reduced. BRIEF DESCRIPTION OF DRAWINGS

[0017] The disclosure of the present application will become more apparent with reference to the drawings. It is easily understood by those skilled in the art that the drawings are only for illustrative purposes, and are not intended to limit the scope of protection of the present application. Among them:

[0018] Figure 1 is a main step flow diagram of a wind turbine blade clearance monitoring method according to an embodiment of the present application;

[0019] Figure 2 is a detailed step flow diagram of a fan blade clearance monitoring method according to an embodiment of the present application;

[0020] Figure 3 is a main structure diagram of a fan blade clearance monitoring system according to an embodiment of the present application;

[0021] Figure 4 is a main structure diagram of an electronic device according to an embodiment of the present application.

[0022] Reference signs:

[0023] 11: memory; 12: processor; 31: acquisition module; 32: prediction module; 33: control module. DETAILED DESCRIPTION

[0024] Some embodiments of the present application will be described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present application, and are not intended to limit the protection scope of the present application.

[0025] In the description of the present application, "module" and "processor" can include hardware, software or a combination of both. A module can include hardware circuitry, various suitable sensors, communication ports, memories, and can also include a software part such as program code, and can be a combination of software and hardware. The processor can be a central processor, 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 can be implemented in software, hardware or a combination of both. The computer readable storage medium includes any suitable medium that can store program code, such as a magnetic disk, a hard disk, an optical disk, a flash memory, a read-only memory, a random access memory, etc. The term "A and / or B" means all possible combinations of A and B, such as only A, only B or A and B. The term "at least one of A or B" or "at least one of A and B" has a similar meaning as "A and / or B", and can include only A, only B or A and B. The singular form of the term "one", "this" can also include the plural form.

[0026] The current clearance prediction system has the problems of low accuracy, high false alarm rate, etc., which leads to the problem of "pre-warning but unable to prevent" in the clearance early warning and prevention system. In addition, with the development of wind farms to more complex and harsh environments, such as desert, gobi and desert areas, higher requirements are put forward for the environmental adaptability and accuracy of the clearance prediction technology.

[0027] To this end, the fan blade clearance monitoring method provided by the application comprises: acquiring monitoring data of a fan blade at a current time, wherein the monitoring data comprises clearance data, pitch angle data and blade speed data; inputting the monitoring data into a pre-constructed clearance prediction model to predict operation data of the fan blade at a next time, the clearance prediction model being constructed based on actual operation data and simulation operation data; and outputting alarm information based on the operation data of the fan blade at the next time. The application can accurately predict the operation data at the next time by constructing the clearance prediction model by combining the actual operation data actually collected and the simulation operation data supplemented based on numerical simulation, can provide a buffer time for potential dangerous clearance, and can be widely applied to various types and scales of wind turbines to provide strong support for safe operation of the wind power industry.

[0028] Referring to the drawings Figure 1 , Figure 1 is a main step flow schematic diagram of a fan blade clearance monitoring method according to an embodiment of the application. As Figure 1 indicated, the fan blade clearance monitoring method in the embodiment of the application mainly comprises the following steps S101 to S103.

[0029] Step S101: acquiring monitoring data of a fan blade at a current time, wherein the monitoring data comprises clearance data, pitch angle data and blade speed data;

[0030] In the embodiment, the clearance data of the fan blade refers to the minimum gap between the fan blade and the surrounding environment when the fan rotates. The pitch angle (Pitch Angle) is also called the pitch angle, which refers to the angle between the top wing type chord line of the fan blade and the rotation plane.

[0031] Step S102: inputting the monitoring data into a pre-constructed clearance prediction model to predict operation data of the fan blade at a next time, the clearance prediction model being constructed based on actual operation data and simulation operation data.

[0032] In the embodiment, the monitoring data at the current time is input into the clearance prediction model, and after receiving the input data, the clearance prediction model will perform calculation and analysis to predict the clearance data, the pitch angle data and the blade speed data of the fan blade at the next time.

[0033] Step S103: outputting alarm information based on the operation data of the fan blade at the next time.

[0034] Based on the method described in steps S101 to S103, the present application uses the monitoring data obtained in real time from the fan blade as the input of the clearance prediction model, predicts the operation data of the wind turbine at the next moment, and further analyzes and judges the prediction data, and then outputs the alarm information, provides a buffer time for potential dangerous clearance, and can be widely applied to various types and sizes of wind turbines, and provides strong support for the safe operation of the wind power industry.

[0035] The steps S101 to S103 are further described below.

[0036] Referring to the accompanying Figure 2 , Figure 2 is a detailed step flow diagram of a fan blade clearance monitoring method according to an embodiment of the present application.

[0037] As Figure 2 shown, the fan blade clearance monitoring method of the present embodiment includes the following steps:

[0038] In one embodiment, the clearance prediction model is constructed by the following steps: obtaining actual operation data; obtaining simulation operation data; determining a training data set based on the actual operation data and the simulation operation data; and constructing a clearance prediction model based on the training data set.

[0039] Specifically, the current clearance prediction algorithm based on machine learning is designed based on short-term clearance data and working condition data, the dangerous working condition data accounts for a small proportion in the data set, and cannot cover all dangerous working conditions, so the prediction ability of the model constructed by machine learning is limited. The method of the present application first collects the actual operation data of the wind turbine, and simulates the dangerous working conditions of the wind turbine by a simulation method to obtain simulation operation data. The simulation operation data includes the operation data of the wind turbine in the dangerous working condition obtained by numerical simulation, and the simulation operation data can effectively supplement the actual operation data. Then, the training data set is determined based on the actual operation data and the simulation operation data, and the clearance prediction model is constructed according to the training data set, so that the ability of the clearance prediction model constructed based on the actual operation data and the simulation operation data to judge the dangerous working condition is improved, thereby improving the early warning ability and effectively ensuring the safe operation of the unit.

[0040] In one embodiment, the actual operation data is obtained by: obtaining the clearance data, corresponding pitch angle data and blade speed data of different types of fans under normal working conditions as the actual operation data.

[0041] Specifically, the clearance data of different types of wind turbines under normal working conditions and the corresponding pitch angle data and blade speed data are collected.

[0042] In one embodiment, acquiring simulation operation data includes: using computational fluid dynamics to solve the Navier-Stokes equations to determine the flow field information of the wind turbine; using the wind turbine actuator line method to perform performance analysis on the wind turbine blades based on the flow field information, the aerodynamic characteristics of the two-dimensional airfoil, and momentum theory; using momentum theory to consider the influence of the wind turbine on the incoming flow and determine the aerodynamic performance parameters of the wind turbine; based on the aerodynamic performance parameters of the wind turbine, obtaining the operation data of the wind turbine under different loads; and filtering the operation data under different loads based on preset screening conditions to obtain the simulated clearance data, corresponding simulated pitch angle data, and simulated blade speed data under hazardous conditions, as simulation operation data. The hazardous conditions include extreme wind speed conditions, extreme wind direction change conditions, fault conditions, special environmental conditions, and operating conditions.

[0043] Specifically, firstly, a three-dimensional geometric model of the wind turbine is constructed, including components such as the tower, nacelle, and rotor, ensuring that the model accurately reflects the actual structure and dimensions of the wind turbine. Then, a three-dimensional mesh generation technique is used to divide the computational domain surrounding the wind turbine into discrete mesh cells. For critical areas such as the rotor, mesh refinement is applied to improve computational accuracy. Based on actual atmospheric conditions, parameters such as wind speed, wind direction, and turbulence intensity are set for the inlet boundary; the outlet boundary is set to fully developed conditions; and the wall boundaries are set to no-slip boundary conditions based on the surface characteristics of the wind turbine components. Finally, the simple solver in Fluent is selected to solve the Navier-Stokes equations, and control parameters such as time step and number of iterations are set to obtain the flow field information of the wind turbine.

[0044] Then, the wind turbine blades are divided into multiple micro-elements (blade elements) along the spanwise direction at equal intervals or according to specific rules, each blade element possessing independent aerodynamic characteristics. Through experimental measurements or numerical simulations, aerodynamic characteristic data of the corresponding two-dimensional airfoil at different angles of attack are obtained for each blade element, such as lift coefficient and drag coefficient. Based on momentum theory, considering the momentum exchange of each blade element with the incoming flow, and combining this with the aerodynamic characteristics of the two-dimensional airfoil, the force situation of each blade element is calculated, thereby performing performance analysis on the wind turbine blades.

[0045] Furthermore, considering the disturbance effect of the wind turbine on the incoming flow, momentum conservation equations are established before and after the turbine's operation using momentum theory to analyze changes in parameters such as incoming flow velocity and pressure. Based on the forces acting on the turbine and the changes in incoming flow parameters, aerodynamic performance parameters of the turbine, such as power, axial force, and torque, are calculated. By calculating the aerodynamic performance parameters of the turbine under different operating conditions, operating data of the wind turbine under various loads are obtained.

[0046] Finally, the calculated operating data of the wind turbine under different loads are sorted and stored, and classified according to different working conditions (such as wind speed, wind direction, turbulence intensity, etc.). According to the design standards and actual operation requirements of the wind turbine, the determination criteria of the limit load working condition are determined as the preset screening conditions, and then the operating data under different loads are screened according to the preset screening conditions, and the operating data under the limit load condition are screened out, and the operating data under the limit load condition screened out are taken as the simulation operating data under the dangerous working condition.

[0047] The dangerous working condition specifically includes an extreme wind speed working condition, an extreme wind direction change working condition, a fault working condition, a special environment working condition and an operation working condition. The extreme wind speed working condition refers to an extreme working gust, an extreme wind speed model or an extreme wind speed shear. The extreme working gust, such as an extreme gust, may cause power grid outage at the beginning time, the minimum wind speed time, the maximum wind speed time and the maximum gust acceleration time within the range from the cut-in wind speed to the cut-out wind speed of the wind turbine, generate a huge blade flap moment and tower bottom overturning moment, and cause serious impact on the structure of the wind turbine.

[0048] The extreme wind speed model: the extreme strong wind condition beyond the design wind speed of the wind turbine is considered in the simulation to test the structural strength and stability of the wind turbine under the limit wind speed, such as a short-term extreme wind speed, which may cause the blades, tower and other components to bear loads exceeding the limit, resulting in damage.

[0049] The extreme wind speed shear: the condition of too large wind speed change rate in the vertical direction, which causes uneven force on different parts of the wind wheel, increases the fatigue load of the blades and the transmission system, and even may cause the distortion of the blades and the damage of the transmission components.

[0050] The extreme wind direction change working condition refers to an extreme wind direction change, such as a large change in wind direction in a short time, which may cause the yaw system to fail to respond in time, cause the wind turbine to bear the load in a non-design direction, generate additional torque and moment on the tower, nacelle and blades, and increase the risk of structural damage.

[0051] The fault working condition refers to power grid faults, mechanical faults and control system faults; the power grid faults include power grid voltage drop, frequency anomaly, three-phase imbalance and other faults, which affect the grid-connected operation and power output of the wind turbine, may cause the generator to overload, the frequency converter to be damaged, and even cause the wind turbine to be off the grid, causing harm to the power grid and the wind turbine itself.

[0052] The mechanical fault, such as blade fracture, gearbox fault, bearing damage and other mechanical component faults, analyzes the influence of the fault on the overall performance and structure of the wind turbine, such as blade fracture which may destroy the balance of the wind wheel and cause severe vibration, and generate a huge impact on the tower and foundation.

[0053] Control system failures such as pitch system failures make the blade pitch angle unable to be adjusted normally, resulting in the unit being unable to effectively control the power and load; yaw system failures make the wind turbine unable to timely align with the wind direction, reducing power generation efficiency, and may also cause the unit to bear abnormal load.

[0054] Special environmental conditions refer to special conditions such as icing conditions and earthquake conditions; the icing condition is that in a low-temperature environment, the surfaces of components such as blades and tower drums are iced, increasing the weight and aerodynamic resistance of the components, changing the aerodynamic performance of the blades, resulting in a decrease in the power of the unit, and even possibly causing icing to fall off, causing safety hazards. The earthquake condition is that in an earthquake-prone area, the earthquake action is considered in the simulation, the influence of earthquake acceleration, frequency, etc. on the foundation, tower drum and upper structure of the wind turbine is analyzed, the anti-seismic performance of the unit in the earthquake is evaluated, and the foundation settlement, tower drum tilting or collapse is prevented.

[0055] Operating conditions refer to emergency shutdown conditions or start-up and grid-connection conditions; the emergency shutdown condition: such as suddenly triggering an emergency shutdown instruction during operation, the unit quickly pitches and disconnects the frequency converter, which may cause the blade root and the tower drum bottom to bear a huge load impact, and the load change during shutdown needs to be analyzed through numerical simulation to optimize the shutdown strategy. The start-up and grid-connection condition: during the speed rising process of the wind turbine during start-up and the grid-connection instant, current surges and mechanical stress changes occur, which need to be focused on in numerical simulation to ensure that the electrical and mechanical components of the unit can withstand the corresponding stress.

[0056] In an embodiment, the determining the training data set based on the actual operation data and the simulation operation data comprises: respectively performing data preprocessing on the actual operation data and the simulation operation data to obtain the training data set, the data preprocessing comprising at least one of missing value processing, abnormal value processing, noise reduction processing, and normalization processing.

[0057] Specifically, the collected actual operation data and simulation operation data are preprocessed, such as checking whether there are missing values in the data, for missing values, deleting samples containing missing values or using methods such as mean, median, etc. for processing; checking whether there are abnormal values in the data, if there are abnormal values, deleting or replacing them; noise reduction processing refers to using common noise reduction methods such as smoothing filtering, wavelet transform, Kalman filtering or particle filtering to reduce noise in the data and improve the signal-to-noise ratio of the data, thereby improving the training effect of the model; normalization processing refers to using common normalization methods to scale data of different features to the same scale, thereby eliminating the dimensional difference between the features and improving the training speed and performance of the model. After the above data preprocessing steps are completed, the processed actual operation data and simulation operation data are merged into a training data set.

[0058] In one embodiment, constructing a clearance prediction model based on the training dataset includes: constructing a long short-term memory neural network model; training the long short-term memory neural network model using the training dataset; taking the current clearance data, pitch angle data, and blade speed data as input; the long short-term memory neural network outputting the clearance data, pitch angle data, and blade speed data for the next time step; using the mean squared error as the model loss function; selecting Adam as the model optimizer; using the mean absolute error to evaluate the prediction performance of the long short-term memory neural network model; and obtaining the trained clearance prediction model when the prediction performance reaches a preset standard.

[0059] Specifically, the Long Short-Term Memory (LSTM) neural network model is a special type of recurrent neural network (RNN) that excels at processing time-series data. In this embodiment, a multi-layer LSTM network is constructed as the Long Short-Term Memory neural network model, with the following specific structure:

[0060] Input layer: The input layer receives the training dataset as input, specifically using headroom data, pitch angle data, and blade rotation speed data as input.

[0061] Network Layers: A three-layer LSTM is configured. The first LSTM layer has 128 hidden units and passes the output sequence to the next layer. The second LSTM layer has 84 hidden units, and the number of hidden units in the third LSTM layer can be adjusted according to the actual situation.

[0062] Dropout layer: Add a Dropout layer after each LSTM layer, with a dropout rate of 0.2 to prevent overfitting and randomly drop some neurons.

[0063] The output layer is a fully connected layer (Dense layer) with 3 output dimensions, corresponding to the predicted airspace data, pitch angle data, and blade rotation speed data for the next time step.

[0064] The Long Short-Term Memory (LSTM) neural network model is constructed using Keras' Sequential model as its basic framework. An LSTM layer is added to handle time-series data or data with sequence dependencies. A Dropout layer is added to randomly discard the outputs of some neurons during training, reducing overfitting. An output layer (fully connected layer, Dense layer) is added to output the final prediction result.

[0065] Then, using the preprocessed training dataset, a blade clearance prediction model is trained. This model continuously learns from actual operating data and combines it with simulation data obtained from numerical simulations to continuously optimize the prediction model. The specific training steps for the blade clearance prediction model include:

[0066] The Adam optimizer is selected, and the learning rate is set to 0.001. The Adam optimizer is an adaptive learning rate method based on first and second moment estimates.

[0067] The mean squared error (MSE) is used as the loss function to measure the difference between the predicted values and the actual values of the model. The mean absolute error (MAE) is selected as the evaluation indicator to monitor the performance of the model during training.

[0068] The fit method is used to input the input data X and the target data Y, set the epochs to 100, and the batch_size to 32 for training. Epochs represent the number of rounds of training, and setting epochs to 100 means that the model will traverse the entire training data set 100 times. In each round of training, the model will update its internal weights and parameters to minimize the loss function. Batch_size represents the number of samples used to update the model weights each time, and setting batch_size to 32 means that the model will use 32 samples of data to calculate a gradient update.

[0069] In each epoch, the training data is divided into multiple batches. For batch_size of 32, if the training data has 1000 samples, then each epoch will contain 1000 / 32 = 31.25 batches, usually rounded up to 32 batches. For each batch, the model will predict the output based on the input data and the current weights, and then calculate the difference between the predicted results and the target data Y, which is measured by the loss function (such as MSE).

[0070] Then, the model uses the Adam optimizer to update the weights according to the gradient of the loss function to minimize the loss. The optimizer adjusts the weights according to the gradient so that the model's predictions are closer to the true target data. This process is repeated in each batch until the entire training data set is used once, completing an epoch.

[0071] For step S101, the monitoring data of the current moment of the fan blade is obtained, wherein the monitoring data includes clearance data, pitch angle data and blade speed data;

[0072] Specifically, the distance between the blade and the surrounding environment (such as the tower, other blades or obstacles) can be monitored in real time by installing sensors or laser range finders and the like, and the clearance distance between the blade and the surrounding environment can be calculated by analyzing the video or image captured by the camera using image recognition technology to obtain clearance data. The pitch angle data can be obtained by directly measuring the pitch angle through the angle sensor installed on the blade. The blade speed can be directly measured by the speed sensor installed on the generator shaft or the blade, and in some specific embodiments, the blade speed can also be determined by analyzing the generator output power or current and the like.

[0073] For step S102, in one embodiment, the monitoring data is input into a pre-constructed clearance prediction model to predict the running data of the fan blade at the next moment, and the clearance prediction model is constructed based on actual running data and simulation running data.

[0074] Specifically, the monitoring data of the fan blade is collected. Before the monitoring data is input into the clearance prediction model, the monitoring data can be pre-processed, such as removing noise, outliers, and normalization processing. The pre-processed monitoring data is input into the pre-constructed clearance prediction model, and the model will predict the running data of the fan blade at the next moment based on the learned knowledge and rules.

[0075] For step S103, in one embodiment, the alarm information is controlled based on the running data of the fan blade at the next moment, including: determining whether the fan blade has a tower scanning risk based on the running data of the fan blade at the next moment, and if so, generating an alarm information; if not, determining that the fan blade is in a safe state.

[0076] Specifically, according to the predicted running data at the next moment, it is determined whether the fan blade has a tower scanning risk. The tower scanning risk refers to the risk that the fan blade may collide with the fan tower during rotation. If it is determined that the fan blade has a tower scanning risk, an alarm information is immediately generated. The alarm information can be a display alarm, a speaker alarm, or a indicator light alarm, and can also include information such as the specific type of risk, possible consequences, and suggested countermeasures. In addition, a corresponding control function can be set to automatically take emergency measures such as stopping the fan operation, adjusting the blade angle, etc. when the tower scanning risk is detected, so as to prevent accidents and reduce losses.

[0077] If it is determined that there is no tower scanning risk, it is considered that the fan blade is in a safe state, and the running state of the fan blade can be continuously monitored.

[0078] It should be noted that although the above embodiments describe the steps in a specific order, those skilled in the art can understand that, in order to achieve the effects of the present application, the different steps do not have to be executed in such an order, and they can be executed simultaneously (in parallel) or in other orders. After these adjustments, the schemes after the adjustments belong to equivalent technical schemes and will also fall within the protection scope of the present application.

[0079] Those skilled in the art can understand that all or part of the processes in the method of the above embodiment can also be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer readable storage medium. When the computer program is executed by a processor, the steps of each method embodiment described above can be implemented. The computer program includes computer program code, which can be in the form of source code, object code, executable files or some intermediate forms, etc. The computer readable storage medium can include any entity or device, medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory, random access memory, electrical carrier signal, telecommunication signal and software distribution medium, etc. that can carry the computer program code.

[0080] The present application also provides a fan blade clearance monitoring system.

[0081] Referring to the drawings Figure 3 , Figure 3 is a schematic diagram of the main structure of a fan blade clearance monitoring system according to an embodiment of the present application. As shown in Figure 3 , the fan blade clearance monitoring system of the present application comprises an acquisition module 31, a prediction module 32 and a control module 33. In some embodiments, one or more of the acquisition module 31, the prediction module 32 and the control module 33 can be combined together into one module.

[0082] In some embodiments, the acquisition module 31 can be configured to acquire monitoring data of the fan blade at the current time; the prediction module 32 can be configured to predict running data of the fan blade at the next time by using a pre-constructed clearance prediction model, the clearance prediction model being constructed based on actual running data and simulation running data; and the control module 33 can be configured to control output of alarm information based on the running data of the fan blade at the next time. In one implementation, the description of the specific implementation functions can be referred to steps S101 to S103.

[0083] The above fan blade clearance monitoring system is used to execute Figure 1The technical principles, technical problems solved, and technical effects of the two are similar, and a person skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process and related description of the fan blade clearance monitoring system can refer to the content described in the embodiment of the fan blade clearance monitoring method, which will not be repeated here.

[0084] Another aspect of the present application also provides an electronic device.

[0085] In an embodiment of an electronic device according to the present application, the electronic device can include at least one processor; and a memory connected in communication with the at least one processor; wherein the memory has stored therein a computer program, which, when executed by the at least one processor, implements the method according to any of the above embodiments. The electronic device according to the present application can include a driving device, a smart car, a robot, and the like. For the convenience of description, only the parts related to the embodiments of the present application are shown in the drawings, and the specific technical details not disclosed are described in the method part of the embodiments of the present application. Figure 4 , Figure 4 The memory 11 and the processor 12 are communicatively connected by a bus, as shown in the example.

[0086] In some embodiments of the present application, the electronic device can further include at least one sensor for sensing information. The sensor is communicatively connected to any type of processor mentioned in the present application.

[0087] Another aspect of the present application also provides a computer-readable storage medium.

[0088] In an embodiment of a computer-readable storage medium according to the present application, the computer-readable storage medium can be configured to store a program of a fan blade clearance monitoring method for executing the above-mentioned method embodiments, which can be loaded and run by a processor to implement the above-mentioned fan blade clearance monitoring method. For the convenience of description, only the parts related to the embodiments of the present application are shown, and the specific technical details not disclosed are described in 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, and optionally, the computer-readable storage medium in the embodiments of the present application is a non-transitory computer-readable storage medium.

[0089] So far, the technical solution of the present application has been described in combination with one embodiment shown in the drawings, but a person skilled in the art can easily understand that the protection scope of the present application is obviously not limited to these specific embodiments. A person skilled in the art can make equivalent changes or replacements to the related technical features without departing from the principles of the present application, and the technical solutions after the changes or replacements will fall within the protection scope of the present application.

Claims

1. A method of wind turbine blade clearance monitoring, characterized in that, The method comprises: acquiring monitoring data of the fan blade at the current moment, wherein the monitoring data comprises clearance data, pitch angle data and blade speed data; inputting the monitoring data into a pre-constructed clearance prediction model to predict the operation data of the fan blade at the next moment, wherein the clearance prediction model is constructed based on actual operation data and simulation operation data, wherein the actual operation data comprises clearance data, corresponding pitch angle data and blade speed data of different fan models under normal working conditions, and the simulation operation data comprises simulation clearance data, corresponding simulation pitch angle data and simulation blade speed data under dangerous working conditions; the clearance prediction model is constructed by the following steps: acquiring actual operation data; acquiring simulation operation data; determining a training data set based on the actual operation data and the simulation operation data; constructing a clearance prediction model based on the training data set; wherein the simulation operation data is acquired by the following steps: determining flow field information of a wind turbine by solving Navier-Stokes equations using computational fluid dynamics methods; performing performance analysis on the wind turbine rotor blades based on the flow field information of the wind turbine, aerodynamic characteristics of a two-dimensional airfoil and momentum theory using a fan actuation line method; determining aerodynamic performance related parameters of the wind wheel by considering the influence of the wind wheel on the incoming flow using momentum theory; obtaining operation data of the wind turbine under different loads based on the aerodynamic performance related parameters of the wind wheel; screening the operation data under different loads based on a pre-set screening condition to obtain simulation clearance data, corresponding simulation pitch angle data and simulation blade speed data under dangerous working conditions as simulation operation data, wherein the dangerous working conditions include extreme wind speed conditions, extreme wind direction change conditions, fault conditions, icing conditions, earthquake conditions and operation conditions; controlling to output an alarm information based on the operation data of the fan blade at the next moment.

2. The fan blade clearance monitoring method of claim 1, wherein, The actual operation data is acquired by: acquiring clearance data, corresponding pitch angle data and blade speed data of different fan models under normal working conditions as actual operation data.

3. The fan blade clearance monitoring method of claim 1, wherein, The training data set is determined based on the actual operation data and the simulation operation data by: respectively performing data preprocessing on the actual operation data and the simulation operation data to obtain a training data set, wherein the data preprocessing comprises at least one of missing value processing, abnormal value processing, noise reduction processing and normalization processing.

4. The fan blade clearance monitoring method of claim 1, wherein, The clearance prediction model is constructed based on the training data set by: constructing a long short-term memory neural network model, training the long short-term memory neural network model using the training data set, taking the clearance data, pitch angle data and blade speed data at the current moment as input, and outputting the clearance data, pitch angle data and blade speed data at the next moment from the long short-term memory neural network model, taking mean square error as a model loss function, selecting Adam as a model optimizer, evaluating the prediction performance of the long short-term memory neural network model using mean absolute error, and obtaining a trained clearance prediction model when the prediction performance reaches a pre-set standard.

5. The fan blade clearance monitoring method of claim 1, wherein, The fan blade next time operation data is used to control output alarm information, including: Based on the fan blade next time operation data to determine whether the fan blade exists sweep tower risk, if yes, then generate alarm information; If not, it is determined to be a safe state.

6. A wind turbine blade clearance monitoring system, characterized in that The system is used to execute the fan blade clearance monitoring method in any one of claims 1 to 5, and the system comprises: An acquisition module is configured to acquire monitoring data of a fan blade at a current time; A prediction module is configured to predict operation data of the fan blade at a next time by using a pre-constructed clearance prediction model, wherein the clearance prediction model is constructed based on actual operation data and simulation operation data; A control module is configured to control output of alarm information based on the fan blade next time operation data.

7. An electronic device comprising at least one processor and at least one memory adapted to store a plurality of program codes, characterized in that, The program code is adapted to be loaded and run by the processor to execute the fan blade clearance monitoring method in any one of claims 1 to 5.

8. A computer readable storage medium having stored therein a plurality of program codes, characterized in that, The program code is adapted to be loaded and run by the processor to execute the fan blade clearance monitoring method in any one of claims 1 to 5.

Images