Wind turbine blade state monitoring method based on beidou positioning and related equipment

Abstract

The application discloses a wind turbine blade state monitoring method based on Beidou positioning and related equipment, and relates to the technical field of data processing, and comprises the following steps: constructing a high-precision positioning measurement baseline by comparing signal differences, calculating three-dimensional absolute space coordinates and dynamic attitude angles of each monitoring section in real time, fusing the three-dimensional absolute space coordinates and the dynamic attitude angles, removing rigid motion components of blade overall rotation and yaw from the total motion, obtaining elastic deformation displacement time series of each monitoring section, inputting the elastic deformation displacement time series and angular velocity data into a preset blade state monitoring model, and calculating and outputting three-dimensional displacement fields of any positions on the blade surface and inside the blade through forward propagation. The application decouples rigid body motion through Beidou and inertial fusion, and utilizes a model constraint physical law of embedded motion equation unbalance to realize high-precision reconstruction of a three-dimensional deformation field of the blade, so that the blade state can be accurately monitored.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a method and related equipment for monitoring the condition of wind turbine blades based on BeiDou positioning. Background Technology

[0002] In related technologies, large wind turbine blades experience multimodal coupled vibrations under complex loads, leading to accumulated fatigue damage and necessitating real-time deformation monitoring and active vibration suppression. Three major bottlenecks exist in these technologies: First, the lack of an absolute spatial reference means existing sensors can only acquire local relative motion. Rigid body motions such as blade rotation and yaw are coupled with elastic deformation, making accurate decoupling difficult and resulting in systematic errors in deformation measurements. Second, the contradiction between sparse sensing and global reconstruction is significant. Limited internal blade wiring restricts sensor deployment, making it extremely difficult to reconstruct the global dynamic deformation field from discrete points—a typical challenge of sparse observation. Traditional interpolation methods have low accuracy, and pure data-driven networks have poor cross-condition generalization capabilities. These problems have long constrained blade condition monitoring. Summary of the Invention

[0003] The main purpose of this application is to provide a method and related equipment for monitoring the condition of wind turbine blades based on BeiDou positioning, aiming to solve the technical problem of how to accurately monitor the condition of the blades.

[0004] To achieve the above objectives, this application proposes a method for monitoring the condition of wind turbine blades based on BeiDou positioning. Multiple monitoring sections are arranged along the spanwise direction on the wind turbine blades. A BeiDou positioning receiver antenna and an inertial measurement unit are fixedly installed at each monitoring section. A main receiver for the nacelle is installed on the top of the wind turbine nacelle. The method for monitoring the condition of wind turbine blades based on BeiDou positioning includes: Based on the Beidou positioning receiver antenna, the main receiver in the nacelle, and the tower base reference station at the bottom of the wind turbine tower, a high-precision positioning measurement baseline is constructed by comparing signal differences, so as to calculate the three-dimensional absolute spatial coordinates and dynamic attitude angles of each monitoring section in real time. By integrating the three-dimensional absolute spatial coordinates and the dynamic attitude angles, and removing the rigid body motion components of the overall blade rotation and yaw from the total motion, the elastic deformation displacement time series of each monitoring section is obtained. The elastic deformation displacement time series and the angular velocity data obtained based on the inertial measurement unit are input into a preset blade condition monitoring model to calculate and output the three-dimensional displacement field at any position on the blade surface and inside through forward propagation. The loss function of the preset blade condition monitoring model is embedded with the unbalance quantity of the blade motion equation, and the unbalance quantity of the blade motion equation is used to constrain the three-dimensional displacement field to conform to physical laws.

[0005] In one embodiment, the step of fusing the three-dimensional absolute spatial coordinates and the dynamic attitude angles, and removing the rigid body motion components of the overall blade rotation and yaw from the total motion to obtain the elastic deformation displacement time series of each monitoring section further includes: High-frequency acceleration and angular velocity data acquired by the inertial measurement unit are used as state prediction inputs, and low-frequency three-dimensional absolute spatial coordinates and dynamic attitude angles calculated by the Beidou positioning receiver antenna are used as observation update inputs. Through tight coupling fusion using a data fusion algorithm, the precise spatial pose of each monitoring section is obtained. Establish the transformation relationship between the blade rotation coordinate system and the global coordinate system to determine the overall rotational angular displacement and yaw angular displacement of the blade in the precise spatial pose; Subtract the rigid body motion components corresponding to the overall rotational angular displacement and yaw angular displacement of the blade from the precise spatial pose to obtain the displacement time series at each monitoring section caused only by elastic deformation.

[0006] In one embodiment, before the step of inputting the elastic deformation displacement time series and the angular velocity data obtained based on the inertial measurement unit into the preset blade condition monitoring model, the method further includes: A blade motion equation is constructed based on a beam structure with blade shape and material varying along the length direction as a theoretical model. The blade motion equation includes multi-directional vibration coupling terms in the flapping direction, oscillation direction, and torsional direction, as well as nonlinear terms caused by shape changes. Based on the blade motion equation in the form of unbalance quantity, a total loss function is constructed, and based on the total loss function, a blade condition monitoring model is constructed. Simulation data generated by the blade simulation model under multiple typical working conditions is collected and the simulation data is set as sample data. The simulation data includes the three-dimensional displacement, strain and stress of each discrete point of the blade. Based on the sample data, the blade condition monitoring model is iteratively trained to obtain a preset blade condition monitoring model.

[0007] In one embodiment, after the step of calculating and outputting the three-dimensional displacement field at any position on and inside the blade surface through forward propagation, the method further includes: The main vibration mode features of the current blade are extracted from the three-dimensional displacement field. The main vibration mode features include flapping vibration frequency, oscillation vibration frequency, torsional vibration frequency, decay rate, vibration amplitude and bending morphology distribution corresponding to each vibration frequency. The main vibration mode characteristics are compared with preset alarm values. When the amplitude of any vibration mode characteristic exceeds the alarm value, a monitoring and early warning signal is generated.

[0008] In one embodiment, after the step of generating the monitoring and early warning signal, the method further includes: Using the main vibration mode features as search query conditions, information retrieval and generation operations are performed in a pre-constructed operation and maintenance knowledge relationship network to recall historical operation cases that are most similar to the current vibration mode features, and to recall vibration reduction strategies and performance evaluations corresponding to the historical operation cases. Based on the current vibration mode characteristics and the evaluation of the execution effect, the vibration reduction strategy is optimized; Vibration suppression is achieved based on the optimized vibration reduction strategy.

[0009] In one embodiment, the step of vibration suppression based on the optimized vibration reduction strategy further includes: Based on a pre-set set of physical limits for wind turbine units, a feasibility check is performed on the optimized vibration reduction strategy. If the recommended range of control parameters in the optimized vibration reduction strategy falls entirely within the safety boundary defined by the set of physical limits, the check is deemed to have passed, and the optimized vibration reduction strategy is converted into an executable sequence of control instructions. If the recommended range of control parameters in the optimized vibration reduction strategy exceeds the safety boundary, the recommended range of the control parameters is truncated and readjusted until the adjusted vibration reduction strategy fully meets all physical limit requirements. After the inspection is passed, the control command sequence obtained is sent to the corresponding active vibration damping actuator to suppress vibration. The active vibration damping actuator includes an independent pitch controller, a trailing edge flap actuator, and an electromagnetic damping adjuster.

[0010] Furthermore, to achieve the above objectives, this application also proposes a wind turbine blade condition monitoring device based on BeiDou positioning, wherein the wind turbine blade condition monitoring device based on BeiDou positioning includes: The construction module is used to construct a high-precision positioning measurement baseline based on the Beidou positioning receiver antenna, the main receiver in the nacelle, and the tower base reference station at the bottom of the wind turbine tower by comparing signal differences, so as to calculate the three-dimensional absolute spatial coordinates and dynamic attitude angles of each monitoring section in real time. The fusion module is used to fuse the three-dimensional absolute spatial coordinates and the dynamic attitude angle, and remove the rigid body motion components of the overall rotation and yaw of the blade from the total motion to obtain the elastic deformation displacement time series of each monitoring section. The calculation module is used to input the elastic deformation displacement time series and the angular velocity data obtained based on the inertial measurement unit into a preset blade state monitoring model, so as to calculate and output the three-dimensional displacement field at any position on the blade surface and inside through forward propagation. The loss function of the preset blade state monitoring model is embedded with the unbalance quantity of the blade motion equation, and the unbalance quantity of the blade motion equation is used to constrain the three-dimensional displacement field to conform to the physical laws.

[0011] In addition, to achieve the above objectives, this application also proposes a wind turbine blade condition monitoring device based on BeiDou positioning. The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor. The computer program is configured to implement the steps of the wind turbine blade condition monitoring method based on BeiDou positioning as described above.

[0012] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements the steps of the wind turbine blade condition monitoring method based on BeiDou positioning as described above.

[0013] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the wind turbine blade condition monitoring method based on BeiDou positioning as described above.

[0014] One or more technical solutions proposed in this application have at least the following technical effects: This application discloses a method and related equipment for monitoring the condition of wind turbine blades based on BeiDou positioning, relating to the field of data processing technology. Compared with related technologies, which mainly suffer from three bottlenecks: First, the lack of an absolute spatial reference means existing sensors can only acquire local relative motion; rigid body motions such as blade rotation and yaw are coupled with elastic deformation, making precise decoupling difficult and leading to systematic errors in deformation measurement. Second, the contradiction between sparse sensing and global reconstruction; limited internal wiring within the blade restricts the deployment of sensors, making the reconstruction of the global dynamic deformation field from discrete points a typical challenge of sparse observation. Traditional interpolation methods have low accuracy, and pure data-driven networks have poor cross-condition generalization capabilities. In this application, firstly, based on the BeiDou positioning receiver antenna, the nacelle main receiver, and the tower base reference station at the bottom of the wind turbine tower, through... By comparing signal differences, a high-precision positioning measurement baseline is constructed to calculate the three-dimensional absolute spatial coordinates and dynamic attitude angles of each monitoring section in real time. Then, the three-dimensional absolute spatial coordinates and the dynamic attitude angles are fused, and the rigid body motion components of the overall blade rotation and yaw are removed from the total motion to obtain the elastic deformation displacement time series of each monitoring section. Finally, the elastic deformation displacement time series and the angular velocity data obtained based on the inertial measurement unit are input into a preset blade state monitoring model to calculate and output the three-dimensional displacement field at any position on and inside the blade surface through forward propagation. The loss function of the preset blade state monitoring model is embedded with the unbalance quantity of the blade motion equation, and the unbalance quantity of the blade motion equation is used to constrain the three-dimensional displacement field to conform to physical laws.

[0015] Understandably, this application decouples rigid body motion by integrating BeiDou and inertial navigation, and uses a model that embeds the unbalance quantity of the motion equation to constrain physical laws, thereby achieving high-precision reconstruction of the three-dimensional deformation field of the blade and accurately monitoring the blade's condition. Attached Figure Description

[0016] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0017] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a flowchart illustrating an embodiment of the wind turbine blade condition monitoring method based on BeiDou positioning provided in this application. Figure 2 This is a flowchart illustrating Embodiment 2 of the wind turbine blade condition monitoring method based on BeiDou positioning provided in this application; Figure 3 This is a schematic diagram of the module structure of the wind turbine blade condition monitoring device based on Beidou positioning in an embodiment of this application; Figure 4 This is a schematic diagram of the equipment structure of the hardware operating environment involved in the wind turbine blade condition monitoring method based on Beidou positioning in the embodiments of this application.

[0019] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0020] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0021] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0022] The main solution in this application embodiment is: In this embodiment, for ease of description, the following description will focus on a wind turbine blade condition monitoring device based on BeiDou positioning.

[0023] Due to the lack of an absolute spatial reference, existing sensors can only acquire local relative motion. Rigid body motions such as blade rotation and yaw are coupled with elastic deformation, making it difficult to decouple them accurately, resulting in systematic errors in deformation measurement. The contradiction between sparse sensing and global reconstruction is also a problem. The internal wiring of the blade is limited, and very few sensors can be deployed. Reconstructing the global dynamic deformation field from discrete points is a typical sparse observation problem. Traditional interpolation has low accuracy, and pure data-driven networks have poor generalization ability across operating conditions.

[0024] This application provides a solution comprising: First, based on the BeiDou positioning receiver antenna, the nacelle main receiver, and the tower base reference station at the bottom of the wind turbine tower, a high-precision positioning measurement baseline is constructed by comparing signal differences to calculate the three-dimensional absolute spatial coordinates and dynamic attitude angles of each monitoring section in real time. Then, the three-dimensional absolute spatial coordinates and the dynamic attitude angles are fused, and the rigid body motion components of the overall blade rotation and yaw are removed from the total motion to obtain the elastic deformation displacement time series of each monitoring section. Finally, the elastic deformation displacement time series and the angular velocity data obtained based on the inertial measurement unit are input into a preset blade state monitoring model to calculate and output the three-dimensional displacement field at any position on and inside the blade surface through forward propagation. The loss function of the preset blade state monitoring model contains an unbalance quantity of the blade motion equation, which is used to constrain the three-dimensional displacement field to conform to physical laws.

[0025] Understandably, this application decouples rigid body motion by integrating BeiDou and inertial navigation, and uses a model that embeds the unbalance quantity of the motion equation to constrain physical laws, thereby achieving high-precision reconstruction of the three-dimensional deformation field of the blade and accurately monitoring the blade's condition.

[0026] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or an electronic device capable of performing the above functions, such as a wind turbine blade condition monitoring device based on BeiDou positioning. The following description uses a wind turbine blade condition monitoring device based on BeiDou positioning as an example to illustrate this embodiment and the subsequent embodiments.

[0027] Based on this, this application provides a method for monitoring the condition of wind turbine blades based on BeiDou positioning. Multiple monitoring sections are arranged along the spanwise direction on the wind turbine blades. A BeiDou positioning receiver antenna and an inertial measurement unit are fixedly installed at each monitoring section. A main receiver for the nacelle is installed on the top of the wind turbine nacelle. (Refer to...) Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the wind turbine blade condition monitoring method based on BeiDou positioning in this application.

[0028] In this embodiment, the wind turbine blade condition monitoring method based on BeiDou positioning includes steps S10~S30: Step S10: Based on the Beidou positioning receiver antenna, the main receiver in the nacelle, and the tower base reference station at the bottom of the wind turbine tower, a high-precision positioning measurement baseline is constructed by comparing signal differences, so as to calculate the three-dimensional absolute spatial coordinates and dynamic attitude angles of each monitoring section in real time. It should be noted that the Beidou positioning receiver antenna refers to the satellite signal receiving equipment installed on the monitoring section of the blade, which is used to receive Beidou satellite signals to determine its own spatial position.

[0029] The nacelle main receiver refers to the satellite signal receiving equipment that is fixedly installed on the top of the wind turbine nacelle, serving as one of the references for dynamic differential positioning.

[0030] A tower base reference station refers to a satellite signal receiving device that is fixedly installed at the bottom of the wind turbine tower. Its position coordinates are precisely known, providing a fixed reference for differential positioning.

[0031] The measurement baseline is formed by the spatial connection between each pair of Beidou positioning receiver antennas, main receivers in the cabin, and tower-based reference stations. By comparing the differences in the signals received by each receiver, common errors such as satellite clock errors and atmospheric delays are eliminated, achieving centimeter-level high-precision positioning.

[0032] Three-dimensional absolute spatial coordinates refer to the positional values ​​in the longitude, latitude, and altitude directions under the geodetic coordinate system or global coordinate system.

[0033] Dynamic attitude angles refer to the pitch, roll, and yaw angles of the blade monitoring section in space, describing its spatial orientation.

[0034] In this embodiment, BeiDou positioning receiver antennas, the main receiver in the cabin, and the tower-based reference station simultaneously receive BeiDou satellite signals. By comparing the phase difference and time difference of the signals between the three receivers, a measurement baseline is constructed, and real-time dynamic differential technology is used to calculate the spatial vector of each antenna relative to the reference station. Since antennas are installed on each monitoring section, the three-dimensional absolute spatial coordinates of that section can be calculated in real time; simultaneously, the dynamic attitude angle of that section can be calculated through the relative positional relationship of multiple antennas.

[0035] Understandably, this step establishes an absolute spatial reference on the blade body, obtains the precise position and orientation of each monitoring section, and provides basic input for subsequent differentiation between rigid body motion and elastic deformation.

[0036] Step S20: The three-dimensional absolute spatial coordinates and the dynamic attitude angles are fused together, and the rigid body motion components of the overall rotation and yaw of the blade are removed from the total motion to obtain the elastic deformation displacement time series of each monitoring section. It should be noted that fusion refers to the comprehensive processing of BeiDou positioning data and inertial measurement unit data, utilizing their respective advantages (BeiDou positioning has high accuracy but low frequency, while inertial data has high frequency but is subject to drift) to obtain a better pose estimate.

[0037] Total motion refers to the sum of all spatial motions that actually occur at the blade monitoring section, including the overall rotation of the blade with the hub, the motion caused by the nacelle yaw, and the motion generated by the elastic deformation of the blade itself.

[0038] Rigid body motion components refer to the components of the blade's overall rotation and yaw motion. These components do not cause internal stress in the blade and belong to rigid body displacement.

[0039] Elastic deformation displacement time series refers to the data sequence of displacement changes over time caused only by the deformation of the blade under force after removing the rigid body motion component from the total motion.

[0040] In this embodiment, the three-dimensional absolute spatial coordinates and dynamic attitude angles obtained in step S10 are fused with the high-frequency acceleration and angular velocity data output by the inertial measurement unit. First, the rigid body motion components corresponding to the overall blade rotation and nacelle yaw are separated, and then this part is subtracted from the total motion signal. The remaining signal is the displacement generated by pure elastic deformation. This displacement is arranged in chronological order to form a time series.

[0041] Understandably, this step eliminates the coupling interference of rigid body motion on deformation measurement, obtains a pure elastic deformation signal, and enables the subsequent reconstructed deformation field to truly reflect the structural deformation of the blade rather than rigid body displacement.

[0042] Specifically, the step of fusing the three-dimensional absolute spatial coordinates and the dynamic attitude angles, and removing the rigid body motion components of the overall blade rotation and yaw from the total motion to obtain the elastic deformation displacement time series of each monitoring section, further includes steps S21~S23: Step S21: Using high-frequency acceleration data and angular velocity data obtained based on the inertial measurement unit as state prediction input, and low-frequency three-dimensional absolute spatial coordinates and dynamic attitude angles calculated based on the Beidou positioning receiver antenna as observation update input, the data fusion algorithm is used to perform tight coupling fusion to obtain the precise spatial pose of each monitoring section. It should be noted that high-frequency acceleration data refers to the acceleration values ​​of the three axes output by the inertial measurement unit at a high sampling frequency (such as 200 times per second), which is used to capture rapidly changing motion.

[0043] State prediction input refers to the input data used in data fusion algorithms to predict the system state at the next moment. The estimated value at the current moment is obtained by recursively based on the state and motion model at the previous moment.

[0044] Low-frequency three-dimensional absolute spatial coordinates and dynamic attitude angles refer to the spatial position and attitude data output by the BeiDou positioning receiver antenna at a lower sampling frequency (such as 10 times per second). They are highly accurate but update slowly.

[0045] Observation update input refers to the measured data used in data fusion algorithms to correct the state prediction results, combining the predicted values ​​with the observed values ​​to obtain a more accurate estimate.

[0046] Data fusion algorithms refer to algorithms that integrate data from different sensors (such as inertial measurement units and BeiDou positioning) to improve estimation accuracy by leveraging their respective advantages. In this step, it specifically refers to extended Kalman filtering.

[0047] Tightly coupled fusion refers to the joint processing of the raw data from the inertial measurement unit and the raw observation data from BeiDou positioning in the same filter, rather than solving them independently and then fusing them.

[0048] Precise spatial pose refers to the precise position (three-dimensional coordinates) and attitude (angular displacement in three directions) of each monitoring section in space obtained after fusion.

[0049] In this embodiment, the high-frequency acceleration and angular velocity data output in real time by the inertial measurement unit (IMU) are used as the basis for state prediction. The predicted pose at the current moment is recursively derived from the state at the previous moment through kinematic equations. Simultaneously, the low-frequency three-dimensional absolute spatial coordinates and dynamic attitude angles calculated by the BeiDou positioning receiver antenna are used as observation values. The residual between the predicted and observed values ​​is calculated in the filtering algorithm, and weights are assigned according to their respective noise covariance matrices. The two are then tightly coupled and fused to obtain the corrected precise spatial pose of each monitoring section. Due to the tight coupling method, the drift of the IMU is periodically calibrated by BeiDou data, while the low sampling rate of BeiDou is filled by high-frequency interpolation of the IMU.

[0050] Understandably, this step achieves the complementary advantages of BeiDou positioning and inertial measurement, ensuring centimeter-level positioning accuracy while raising the pose output frequency to the high-frequency level of the inertial measurement unit, providing a continuous and accurate pose sequence for subsequent rigid-flexible decoupling.

[0051] Step S22: Establish the transformation relationship between the blade rotation coordinate system and the global coordinate system to determine the overall rotational angular displacement and yaw angular displacement of the blade in the precise spatial pose; It should be noted that the blade rotating coordinate system refers to a moving coordinate system fixed on the blade. Usually, the blade span is taken as a certain axis, and this coordinate system rotates and deforms together with the blade.

[0052] The global coordinate system refers to an inertial coordinate system fixed on the ground, which does not change with the movement of the wind turbine and is used to describe the absolute motion of the blades.

[0053] The transformation relationship refers to the mathematical transformation matrix between the blade rotating coordinate system and the global coordinate system. It is usually determined by three Euler angles (such as azimuth, cone angle, and twist angle) and is used to transform a vector from one coordinate system to another.

[0054] The overall rotational angular displacement of the blade refers to the change in angle of the blade as the hub rotates around the wind turbine axis, which is a part of rigid body motion.

[0055] Yaw angle displacement refers to the change in horizontal angle caused by the nacelle rotating the blades around the tower axis, and is a part of rigid body motion.

[0056] In this embodiment, a mathematical transformation relationship is established between the blade rotation coordinate system and the global coordinate system. This relationship is based on the blade's current azimuth angle (derived from the hub rotary encoder or the fused pose) and yaw angle (given by the nacelle yaw encoder). Using this transformation relationship, the precise spatial pose obtained in step S21 (expressed in the global coordinate system) is decomposed into two parts: one part is the rigid body motion component caused by the overall blade rotation and yaw, and the other part is the position change caused by elastic deformation. Specifically, the rigid body spatial position and attitude that the cross-section should have without elastic deformation are calculated through coordinate transformation, and then compared with the actual pose to determine the specific values ​​of the overall blade rotational angular displacement and yaw angular displacement.

[0057] Understandably, this step separates the pure rigid body rotation and yaw contributions from the composite motion of the blade, providing a quantitative basis for accurately subtracting the rigid body components and extracting the pure elastic deformation in the subsequent process.

[0058] Step S23: Subtract the rigid body motion components corresponding to the overall rotational angular displacement and yaw angular displacement of the blade from the precise spatial pose to obtain the displacement time series at each monitoring section caused only by elastic deformation.

[0059] It should be noted that the rigid body motion component refers to the spatial position and attitude changes caused by the overall rotation and yaw angle displacement of the blade, which does not cause internal stress in the blade.

[0060] The displacement time series generated by elastic deformation refers to the data sequence arranged in chronological order, which consists only of the changes in spatial position and attitude caused by the deformation of the blade under stress after deducting the rigid body motion component.

[0061] In this embodiment, the overall rotational angular displacement and yaw angular displacement of the blade determined in step S22 are converted into their corresponding spatial position changes and attitude changes (i.e., rigid body motion components) through a kinematic model. Then, the rigid body motion components are subtracted from the precise spatial pose obtained in step S21 at each time step, and the remaining parts are the displacements and attitude changes of the monitoring section caused by the elastic deformation of the blade. These remaining quantities are arranged in chronological order to form a displacement time series caused by elastic deformation.

[0062] Understandably, this step completely eliminates the coupling interference of rigid body motion on deformation measurement, outputs a pure elastic deformation signal, and enables subsequent deformation field reconstruction and control decisions to be based on real structural deformation rather than rigid body displacement.

[0063] Step S30: Input the elastic deformation displacement time series and the angular velocity data obtained based on the inertial measurement unit into the preset blade state monitoring model, so as to calculate and output the three-dimensional displacement field at any position on the blade surface and inside through forward propagation. The loss function of the preset blade state monitoring model is embedded with the unbalance quantity of the blade motion equation. The unbalance quantity of the blade motion equation is used to constrain the three-dimensional displacement field to conform to the physical laws.

[0064] It should be noted that the inertial measurement unit refers to the sensor installed on the monitoring section of the blade, which can measure triaxial acceleration and triaxial angular velocity.

[0065] Angular velocity data refers to the rate at which the blade cross section rotates around the three coordinate axes, as output by the inertial measurement unit.

[0066] The preset blade condition monitoring model refers to a pre-trained neural network model, which takes elastic deformation displacement and angular velocity data as input and outputs a three-dimensional displacement field over the entire blade.

[0067] Forward propagation refers to the basic method of neural network computation, in which input data is processed layer by layer from the input layer through the hidden layers and finally reaches the output layer, without involving backpropagation or parameter updates.

[0068] The three-dimensional displacement field refers to the displacement distribution of any point on and inside the blade surface in three-dimensional space, including the displacement in the flapping direction, oscillation direction, and torsional direction.

[0069] The loss function is a function used to measure the difference between predicted and true values ​​when training a neural network. During training, the network parameters are optimized by minimizing the loss function.

[0070] The imbalance in the blade motion equation refers to the difference between the left and right sides of the equation after substituting the actual observed or predicted motion state into the theoretical blade motion equation. The closer this difference is to zero, the more the motion state conforms to the laws of physics.

[0071] In this embodiment, the elastic deformation displacement time series obtained in step S20 and the angular velocity data output in real time by the inertial measurement unit are directly input into the already trained blade condition monitoring model. The model performs one forward propagation calculation and outputs the three-dimensional displacement field at any position on and inside the blade surface in a very short time. During training, the model's loss function specifically includes the unbalance quantity of the blade motion equation as a penalty term, so the model's output naturally tends to satisfy the physical laws of blade motion.

[0072] Understandably, this step relies on sparse data from only a few monitoring sections to reconstruct the three-dimensional deformation field of the entire blade with high precision and physical consistency, thus resolving the contradiction between sparse observation and global reconstruction in traditional methods.

[0073] Specifically, before the step of inputting the elastic deformation displacement time series and the angular velocity data obtained based on the inertial measurement unit into the preset blade condition monitoring model, steps S31 to S34 are further included: Step S31: Construct the blade motion equations based on a beam structure with blade shape and material varying along the length direction as the theoretical model. The blade motion equations include multi-directional vibration coupling terms in the flapping direction, oscillation direction, and torsional direction, as well as nonlinear terms caused by shape changes. It should be noted that the change in blade shape along the length direction means that the geometric parameters of the blade, such as its cross-sectional airfoil, chord length, and thickness, gradually change from the blade root to the blade tip.

[0074] The variation of material along the length direction refers to the use of different composite material layup designs at different spanwise positions of the blade, with material properties and laminated structure changing with position.

[0075] In structural mechanics, a beam structure refers to a component whose length is much greater than its transverse dimension, which bears bending and torsional loads. Blades can be simplified as variable cross-section cantilever beams.

[0076] The theoretical model refers to the mathematical equations established to describe the mechanical behavior of the blades; in this step, it refers to the blade motion equations.

[0077] The blade motion equation is a partial differential equation that describes the relationship between the displacement, velocity, and acceleration of a blade under the action of force, and includes time and space terms.

[0078] The flapping direction refers to the direction of blade vibration perpendicular to the plane of rotation (i.e., the direction of wind thrust).

[0079] The oscillation direction refers to the direction of vibration of the blade within the plane of rotation (i.e., tangential to the direction of blade motion).

[0080] The direction of torsion refers to the direction of rotational vibration of the blade around its spanwise axis.

[0081] Multidirectional vibration coupling terms refer to mathematical terms that describe the mutual influence between vibrations in different directions. For example, swinging deformation can cause additional torsional torque.

[0082] Nonlinear terms caused by shape changes refer to nonlinear spatial derivative terms in the equations of motion caused by changes in blade cross-section and stiffness along the length, such as stiffness nonlinearity caused by variable cross-section.

[0083] In this embodiment, the blade is taken as the research object and abstracted as a beam structure whose shape and material vary along its length. Based on the theories of elasticity and structural dynamics, the equations of motion that include vibrations in three directions—flapping, oscillation, and torsion—are derived. These equations not only include independent inertial, stiffness, and damping terms for each direction, but also incorporate coupling terms between different directions (such as bending-torsional coupling) caused by the blade's geometric asymmetry and the anisotropy of the composite material. Furthermore, nonlinear spatial terms resulting from the variation of cross-section and stiffness along the length are considered. Ultimately, one or a set of partial differential equations describing the dynamic behavior of the blade are obtained.

[0084] Understandably, this step establishes a mathematical model that characterizes the true dynamic behavior of the blade, providing a theoretical basis for the subsequent construction of physical constraints in the loss function.

[0085] Step S32: Based on the blade motion equation in the form of the unbalance quantity, construct the total loss function, and based on the total loss function, construct the blade condition monitoring model; It should be noted that the unbalance form refers to the residual form where the right side of the equation is not zero after rearranging the blade motion equation, that is, the difference between the left and right sides of the equation. The closer the difference is to zero, the more the prediction conforms to the physical laws.

[0086] The total loss function is a comprehensive metric used to measure the difference between the predicted output and the target when training a neural network. It is composed of a weighted sum of multiple sub-loss terms.

[0087] The blade condition monitoring model refers to a neural network model used to reconstruct the global deformation field of a blade from sparse sensor data. This step refers to the initial model that has not undergone iterative training.

[0088] In this embodiment, the blade motion equation obtained in step S31 is rewritten in the form of an imbalance quantity. Then, this imbalance quantity is used as a physical constraint and written into the total loss function of the neural network. Specifically, a large number of collocation points are selected inside and on the surface of the blade, and the displacement field predicted by the neural network is substituted into the imbalance quantity expression to calculate its value as the physical loss. Simultaneously, the total loss function also includes data fitting loss (to ensure that the prediction at the sensor location matches the actual measurement) and other constraint terms. Based on this total loss function, the network structure of the blade condition monitoring model to be trained is constructed.

[0089] Understandably, this step incorporates physical laws into the model in the form of a loss function, forcing the network output to satisfy the blade motion equation during training, thereby ensuring that the reconstructed deformation field conforms to physical laws.

[0090] Step S33: Collect simulation data generated by the blade simulation model under multiple typical working conditions, and set the simulation data as sample data. The simulation data includes the three-dimensional displacement, strain and stress of each discrete point of the blade. It should be noted that the blade simulation model refers to the finite element model of the blade built in a computer, which can simulate the mechanical response of the blade under a given load.

[0091] Typical operating conditions refer to common load scenarios in wind turbine operation, such as rated power generation conditions, cut-out wind speed conditions, extreme turbulence conditions, and start-up and shutdown conditions.

[0092] Simulation data refers to the numerical results calculated using a blade simulation model.

[0093] Sample data refers to known input-output pairs used to train the neural network model, which serve as a ground truth reference during training in this step.

[0094] Discrete points refer to the fact that the blade simulation model divides the blade into a finite number of units and nodes, with each node being a discrete point.

[0095] Three-dimensional displacement refers to the linear displacement of a discrete point in the three directions of waving, swinging, and torsion.

[0096] Strain refers to the relative deformation of blade material after it is subjected to force, and it is dimensionless.

[0097] Stress refers to the force per unit area inside a blade, and its unit is Pascal.

[0098] In this embodiment, a high-precision finite element simulation model of the blade is established, with material parameters and geometry calibrated. Multiple typical operating conditions are set (such as various wind conditions from cut-in to cut-out, different turbulence intensities, and different yaw errors), and corresponding aerodynamic loads, gravity, and centrifugal force are applied respectively. Simulation calculations are run, and the three-dimensional displacement, strain, and stress results for each discrete point are extracted. These simulation data are then formatted for neural network training and used as sample data.

[0099] Understandably, this step generates high-quality training data covering multiple operating states, providing a sample basis for supervised learning of the model and making up for the shortcomings of sparse actual sensor data that is difficult to cover all operating conditions.

[0100] Step S34: Based on the sample data, iteratively train the blade condition monitoring model to obtain a preset blade condition monitoring model.

[0101] It should be noted that iterative training refers to the process by which a neural network performs multiple forward propagations, calculates the loss, performs backpropagation, and updates the parameters, repeating this process until the loss converges.

[0102] The pre-set blade condition monitoring model refers to a blade condition monitoring model whose parameters are fixed after training and can be directly used for online inference.

[0103] In this embodiment, the sample data obtained in step S33 is used to train the blade condition monitoring model constructed in step S32. In each iteration, the inputs from the sample data (such as displacement and angular velocity at each cross section) are fed into the network, and forward propagation is used to obtain the predicted three-dimensional displacement field; the total loss function (including data fitting loss, unbalance loss of blade motion equation, etc.) is calculated; the gradient is calculated through backpropagation; and the network parameters are updated. This process is repeated until the total loss value stabilizes within an acceptable range and no longer decreases significantly. At this point, the model parameters are fixed, and the preset blade condition monitoring model is obtained.

[0104] Understandably, this step enables the model to learn the mapping relationship from sparse sensor data to the global deformation field and internalize the physical constraints of the blade motion equations, resulting in a mature model that can be deployed online.

[0105] This application discloses a method and related equipment for monitoring the condition of wind turbine blades based on BeiDou positioning, relating to the field of data processing technology. Compared with related technologies, which mainly suffer from three bottlenecks: First, the lack of an absolute spatial reference means existing sensors can only acquire local relative motion; rigid body motions such as blade rotation and yaw are coupled with elastic deformation, making precise decoupling difficult and leading to systematic errors in deformation measurement. Second, the contradiction between sparse sensing and global reconstruction; limited internal wiring within the blade restricts the deployment of sensors, making the reconstruction of the global dynamic deformation field from discrete points a typical challenge of sparse observation. Traditional interpolation methods have low accuracy, and pure data-driven networks have poor cross-condition generalization capabilities. In this application, firstly, based on the BeiDou positioning receiver antenna, the nacelle main receiver, and the tower base reference station at the bottom of the wind turbine tower, through... By comparing signal differences, a high-precision positioning measurement baseline is constructed to calculate the three-dimensional absolute spatial coordinates and dynamic attitude angles of each monitoring section in real time. Then, the three-dimensional absolute spatial coordinates and the dynamic attitude angles are fused, and the rigid body motion components of the overall blade rotation and yaw are removed from the total motion to obtain the elastic deformation displacement time series of each monitoring section. Finally, the elastic deformation displacement time series and the angular velocity data obtained based on the inertial measurement unit are input into a preset blade state monitoring model to calculate and output the three-dimensional displacement field at any position on and inside the blade surface through forward propagation. The loss function of the preset blade state monitoring model is embedded with the unbalance quantity of the blade motion equation, and the unbalance quantity of the blade motion equation is used to constrain the three-dimensional displacement field to conform to physical laws.

[0106] Understandably, this application decouples rigid body motion by integrating BeiDou and inertial navigation, and uses a model that embeds the unbalance quantity of the motion equation to constrain physical laws, thereby achieving high-precision reconstruction of the three-dimensional deformation field of the blade and accurately monitoring the blade's condition.

[0107] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in Embodiment 1 above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 2 After the step of calculating and outputting the three-dimensional displacement field at any position on and inside the blade surface through forward propagation, the method further includes steps A10 to A20: Step A10: Extract the main vibration mode features of the current blade from the three-dimensional displacement field. The main vibration mode features include flapping vibration frequency, oscillation vibration frequency, torsional vibration frequency, decay rate, vibration amplitude and bending morphology distribution corresponding to each vibration frequency. It should be noted that the main vibration mode characteristics refer to the set of key parameters that describe the current vibration behavior of the blade, including frequency, decay rate, amplitude, and morphological distribution.

[0108] The flapping vibration frequency refers to the number of times per second that the blade makes periodic vibrations in the flapping direction (perpendicular to the plane of rotation), and the unit is Hertz.

[0109] The oscillation frequency refers to the number of times per second that the blade makes periodic oscillations in the oscillation direction (within the plane of rotation), and the unit is Hertz.

[0110] Torsional vibration frequency refers to the number of times per second that a blade undergoes torsional periodic vibration around its spanwise axis, measured in Hertz.

[0111] The decay rate refers to how quickly the vibration amplitude decreases over time. It is usually expressed by the damping ratio or logarithmic decay rate and reflects the blade's ability to dissipate vibration energy.

[0112] Vibration amplitude refers to the distance a blade travels from its equilibrium position to its maximum deviation position, and is used to measure the intensity of vibration.

[0113] The bending morphology distribution refers to the spatial shape formed by the relative magnitudes of vibration displacements at various positions along the span of the blade. For example, the first-order bending morphology is a single arc without nodes, while the second-order bending morphology contains one node.

[0114] In this embodiment, data sequences of displacement over time at various monitoring locations on the blade surface (especially near the blade tip, middle, and root) are extracted from the three-dimensional displacement field output in step S30. Spectral analysis (such as Fast Fourier Transform) is performed on these time sequences to identify the frequency peaks where displacement energy is concentrated, corresponding to the dominant vibration frequencies in the flapping, oscillating, and torsional directions, respectively. Simultaneously, the vibration amplitude (peak displacement) and decay rate corresponding to each frequency are calculated from the time-domain curves (damping ratio obtained by fitting the envelope). Then, based on the displacement amplitude ratio at each point along the spanwise direction, the bending morphology distribution is depicted. The above extraction results are summarized as the main vibration mode characteristics.

[0115] Understandably, this step transforms the complex three-dimensional displacement field into easily understandable and comparable quantitative characteristic parameters, providing structured input for subsequent alarm judgment and vibration reduction strategy generation.

[0116] Step A20: Compare the main vibration mode characteristics with the preset alarm values. When the amplitude of any vibration mode characteristic exceeds the alarm value, generate a monitoring and early warning signal.

[0117] It should be noted that the preset alarm values ​​refer to the safety thresholds determined by the blade design or operation and maintenance specifications, such as the maximum allowable vibration amplitude and the minimum allowable damping ratio. Exceeding these values ​​means that the blade is at risk of damage or is malfunctioning.

[0118] Monitoring and early warning signals are prompts generated when the vibration amplitude exceeds the alarm value, used to notify maintenance personnel or trigger subsequent vibration reduction procedures.

[0119] In this embodiment, the main vibration mode features extracted in step A10 (especially the vibration amplitude corresponding to the vibration frequency in each direction) are compared one by one with the alarm values ​​preset in the system. The alarm values ​​are typically set based on the blade's design limit load, fatigue life requirements, or industry standards. If the amplitude of any vibration mode feature exceeds the corresponding alarm value, the blade is determined to be in an abnormal vibration state, and a monitoring and early warning signal is immediately generated. This signal may include the specific vibration mode exceeding the limit, the exceeding amplitude value, and a timestamp. If all vibration amplitudes are within the alarm values, no early warning signal is generated, and the system continues monitoring.

[0120] Understandably, this step enables automatic detection and alarm of abnormal blade vibration, ensuring that subsequent vibration reduction strategy generation steps are triggered in a timely manner when vibration exceeds the standard, preventing fatigue damage accumulation or sudden damage.

[0121] Specifically, after the step of generating the monitoring and early warning signal, steps A30 to A50 are also included: Step A30: Using the main vibration mode features as search query conditions, perform an operation combining information retrieval and generation in the pre-constructed operation and maintenance knowledge relationship network to recall historical operation cases most similar to the current vibration mode features, and recall vibration reduction strategies and execution effect evaluations corresponding to the historical operation cases. It should be noted that the search query conditions refer to the input parameters used to retrieve information in the knowledge network, which in this step are the main vibration mode characteristics.

[0122] Operation and maintenance knowledge relationship network refers to a pre-built structured knowledge base that stores historical operating data of wind turbine units, fault cases, vibration reduction strategies and their implementation effects, and the entities are connected through relationships.

[0123] Information retrieval and generation combined refers to a technical approach that combines retrieval and generation. First, relevant content is retrieved from the knowledge base based on the query conditions, and then this content is used as context to generate more accurate results.

[0124] Recall refers to identifying a number of records from a knowledge network that best match the query criteria.

[0125] Historical operation case studies refer to a complete record of wind turbines under specific vibration conditions in the past, including vibration characteristics, operating conditions, strategies adopted, and their effects.

[0126] Vibration reduction strategies refer to control measures taken to address specific vibration problems, such as adjusting the pitch angle and driving the trailing edge flaps.

[0127] Implementation effect evaluation refers to the quantitative assessment of the vibration improvement after the implementation of vibration reduction strategies in historical cases, such as the increase in damping ratio and the reduction in amplitude.

[0128] In this embodiment, the main vibration mode features (such as frequency, amplitude, and decay rate) extracted in step A10 are used as search query conditions and input into a pre-constructed operation and maintenance knowledge relationship network. Information retrieval and generation are combined within this network: First, the query conditions are matched with historical operation cases stored in the network to determine similarity, recalling several historical cases most similar to the current vibration characteristics; simultaneously, the vibration reduction strategies used at that time and their effectiveness evaluations are also retrieved from these historical cases. The search results are output in order of similarity.

[0129] Understandably, this step involves quickly identifying past cases and effective control measures that most closely resemble the current vibration state from historical operation and maintenance experience, providing a reference for the generation and optimization of subsequent vibration reduction strategies.

[0130] Step A40: Optimize the vibration reduction strategy based on the current vibration mode characteristics and the performance evaluation. It should be noted that optimization refers to adjusting and improving the control parameters (such as amplitude, frequency, phase, etc.) in the historical strategy based on the current actual working conditions and historical effect evaluation, so as to make them more suitable for the current vibration state.

[0131] In this implementation, the historical vibration reduction strategy recalled in step A30 is used as the initial scheme. It is then optimized and adjusted by combining the current vibration mode characteristics extracted in step A10 and the performance evaluation of the strategy recalled in step A30. Specifically, if the historical strategy's performance evaluation is good and the current vibration mode characteristics are highly similar to historical cases, the strategy is directly adopted or fine-tuned. If the similarity is moderate, the control parameters in the strategy (such as pitch amplitude and action frequency) are scaled proportionally or phase-corrected based on the current vibration frequency and amplitude. If the performance evaluation is poor, other similar case strategy combinations are selected or the strategy type is changed. Finally, one or more optimized vibration reduction strategy schemes more suitable for the current working conditions are output.

[0132] Understandably, this step utilizes historical experience to make targeted adjustments to the strategy, avoiding the need to design control schemes from scratch and improving the effectiveness and adaptation speed of vibration reduction strategies.

[0133] Step A50: Vibration suppression is performed based on the optimized vibration reduction strategy.

[0134] It should be noted that the optimized vibration reduction strategy refers to the adjusted and optimized control scheme output in step A40.

[0135] Vibration suppression refers to the process of reducing blade vibration amplitude, increasing damping ratio, and reducing fatigue load by executing control commands.

[0136] In this embodiment, the vibration reduction strategy optimized in step A40 is converted into specific control commands and issued to the actuators of the wind turbine (such as independent pitch controllers, trailing edge flap actuators, electromagnetic damping adjusters, etc.). The actuators act according to the commands, applying reverse damping forces to the blades or adjusting local aerodynamic loads to suppress the current dominant vibration. During execution, the vibration response is continuously monitored; if the vibration is not effectively reduced, a new round of strategy optimization and adjustment can be triggered. After execution, the vibration reduction strategy and its effect are recorded and stored as a new case in the operation and maintenance knowledge network for enriching subsequent retrieval.

[0137] Understandably, this step implements active vibration control at the physical level to reduce blade vibration levels, minimize fatigue damage, and ensure safe blade operation.

[0138] Specifically, the step of vibration suppression based on the optimized vibration reduction strategy further includes steps A51 to A54: Step A51: Based on the pre-set set of physical limits for wind turbine units, conduct a feasibility check on the optimized vibration reduction strategy; It should be noted that the set of physical limits for wind turbine units refers to the pre-set boundary values ​​for safe operation of the equipment, including insurmountable physical constraints such as the maximum angular velocity and maximum angular acceleration of the pitch actuator, the ultimate load of the blade structure, and the maximum allowable power fluctuation.

[0139] Feasibility checks refer to verifying whether all control parameters in the vibration reduction strategy fall within the safety boundaries defined by the set of physical limits.

[0140] In this embodiment, a pre-set set of physical limits for the wind turbine is obtained, which includes the upper and lower limits of the physical constraints for each actuator. The recommended range of control parameters in the optimized vibration reduction strategy is compared one by one with the corresponding physical limits. For example, if the strategy includes an independent pitch command, it checks whether the recommended pitch angular velocity exceeds the maximum allowable angular velocity of the pitch actuator; if it includes trailing edge flap action, it checks whether the flap deflection angle exceeds the structural limit. Each control parameter is compared to determine whether its recommended range is completely covered by the set of physical limits.

[0141] Understandably, this step is a safety pre-assessment before the actual implementation of the vibration reduction strategy to prevent secondary accidents or equipment damage caused by the strategy parameters exceeding the physical capacity of the equipment.

[0142] Step A52: If the recommended range of control parameters in the optimized vibration reduction strategy falls entirely within the safety boundary defined by the set of physical limits, the check is deemed to have passed, and the optimized vibration reduction strategy is converted into an executable control instruction sequence. It should be noted that the recommended range of control parameters refers to the range of control parameter values ​​given in the optimized vibration reduction strategy.

[0143] The safety boundary defined by the set of physical limits refers to the interval formed by the various physical limits.

[0144] A control instruction sequence refers to the process of converting a strategy into a sequence of action instructions that the actuator can recognize and execute.

[0145] In this embodiment, if the feasibility check result of step A51 shows that all recommended ranges of control parameters in the optimized vibration reduction strategy fall completely within the corresponding physical limit safety boundaries (i.e., the minimum value is not lower than the lower limit and the maximum value is not higher than the upper limit), then the check is deemed successful. Subsequently, the strategy is converted into a sequence of control instructions executable by the actuator according to the time sequence and control logic. The instruction sequence includes specific parameters such as instruction type, target value, execution time, and execution speed, and the format conforms to the communication protocol of each execution component.

[0146] Understandably, this step involves encoding the security-verified policy into instructions, transforming it into a format that can be directly issued and executed, thus preparing it for the final execution step.

[0147] Step A53: If the recommended range of control parameters in the optimized vibration reduction strategy exceeds the safety boundary, the recommended range of the control parameters is truncated and readjusted until the adjusted vibration reduction strategy fully meets all physical limit requirements. It should be noted that truncation refers to forcibly limiting the value of control parameters that exceed the safety boundary to the boundary value. For example, if the recommended maximum value is 6 degrees per second and the limit is 5 degrees, then the truncation is 5 degrees.

[0148] Readjustment refers to the need to simultaneously adjust related parameters on the basis of truncation to ensure the physical rationality of the strategy (e.g., adjusting the pitch phase accordingly after reducing the pitch amplitude).

[0149] In this embodiment, if the feasibility check in step A51 finds that some of the recommended ranges of control parameters in the optimized vibration reduction strategy exceed the safety boundaries defined by the physical limit set, then the correction process begins. For parameters exceeding the upper limit, the upper limit is truncated to the upper limit value; for parameters below the lower limit, the lower limit is truncated to the lower limit value. After truncation, it is checked whether the truncated parameter range causes the strategy to lose its expected vibration suppression effect. If the effect decreases significantly, other related parameters are further adjusted (such as extending the action time or changing the strategy combination method) to restore the vibration suppression performance. The check and adjustment are repeated until all control parameters in the adjusted vibration reduction strategy fall completely within the physical limit safety boundaries, and the overall strategy still has an acceptable vibration suppression effect.

[0150] Understandably, this step aims to preserve the effectiveness of the vibration reduction strategy as much as possible without exceeding the physical limits of the equipment, thus achieving a balance between safety and efficiency.

[0151] Step A54: The control command sequence obtained after the inspection is passed is sent to the corresponding active vibration damping actuator to suppress vibration. The active vibration damping actuator includes an independent pitch controller, a trailing edge flap actuator, and an electromagnetic damping adjuster.

[0152] It should be noted that active vibration damping actuators refer to hardware devices that can actively generate control forces to suppress blade vibration.

[0153] An independent pitch controller is an actuator that controls the independent adjustment of the pitch angle of each blade, and can generate a reverse damping torque to suppress low-frequency flapping vibration.

[0154] Trailing edge flap actuators are actuators that drive the movable trailing edge flaps of blades to make fine adjustments, used to change local aerodynamic loads to suppress mid-to-high frequency vibrations.

[0155] An electromagnetic damping regulator is an actuator that adjusts the stiffness and damping parameters of the built-in electromagnetic damper on the blade, used to absorb broadband vibration energy.

[0156] In this embodiment, the control command sequence obtained after passing the check in step A52 or A53 is sent to the independent pitch controller, trailing edge flap actuator, or electromagnetic damping regulator, respectively, according to the command type and the communication interface of the corresponding execution unit. Upon receiving the command, each execution unit performs actions according to the timing and parameters in the command sequence. During vibration suppression, the system continues to collect blade vibration response data for effect evaluation and subsequent knowledge network updates. If the vibration suppression effect is unsatisfactory, a new round of strategy optimization can be triggered.

[0157] Understandably, this step puts the control commands, after safety verification, into physical execution to achieve active vibration reduction and reduce blade vibration amplitude and fatigue load.

[0158] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the wind turbine blade condition monitoring method based on Beidou positioning in this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0159] This application also provides a wind turbine blade condition monitoring device based on BeiDou positioning; please refer to [reference needed]. Figure 3 The wind turbine blade condition monitoring device based on BeiDou positioning includes: Construction module 10 is used to construct a high-precision positioning measurement baseline based on the Beidou positioning receiver antenna, the main receiver in the nacelle and the tower base reference station at the bottom of the wind turbine tower by comparing signal differences, so as to calculate the three-dimensional absolute spatial coordinates and dynamic attitude angles of each monitoring section in real time. Fusion module 20, the fusion module is used to fuse the three-dimensional absolute spatial coordinates and the dynamic attitude angle, and remove the rigid body motion components of the overall rotation and yaw of the blade from the total motion to obtain the elastic deformation displacement time series of each monitoring section; The calculation module 30 is used to input the elastic deformation displacement time series and the angular velocity data obtained based on the inertial measurement unit into a preset blade state monitoring model, so as to calculate and output the three-dimensional displacement field at any position on the blade surface and inside through forward propagation. The loss function of the preset blade state monitoring model is embedded with the unbalance quantity of the blade motion equation, and the unbalance quantity of the blade motion equation is used to constrain the three-dimensional displacement field to conform to physical laws.

[0160] The wind turbine blade condition monitoring device based on BeiDou positioning provided in this application adopts the wind turbine blade condition monitoring method based on BeiDou positioning in the above embodiments, and can solve the technical problem of wind turbine blade condition monitoring based on BeiDou positioning. Compared with related technologies, the beneficial effects of the wind turbine blade condition monitoring device based on BeiDou positioning provided in this application are the same as the beneficial effects of the wind turbine blade condition monitoring method based on BeiDou positioning provided in the above embodiments, and other technical features in the wind turbine blade condition monitoring device based on BeiDou positioning are the same as the features disclosed in the methods of the above embodiments, and will not be repeated here.

[0161] This application provides a wind turbine blade condition monitoring device based on BeiDou positioning. The wind turbine blade condition monitoring device based on BeiDou positioning includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the wind turbine blade condition monitoring method based on BeiDou positioning in the above embodiment 1.

[0162] The following is for reference. Figure 4 The diagram illustrates a structural schematic of a wind turbine blade condition monitoring device based on BeiDou positioning, suitable for implementing embodiments of this application. The wind turbine blade condition monitoring device based on BeiDou positioning in these embodiments may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), and vehicle terminals (e.g., vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 4 The wind turbine blade condition monitoring device based on BeiDou positioning shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments in this application.

[0163] like Figure 4As shown, the wind turbine blade condition monitoring device based on BeiDou positioning may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 1002 or the program loaded from the storage device 1003 into the random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the wind turbine blade condition monitoring device based on BeiDou positioning. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. Communication device 1009 allows the BeiDou-based wind turbine blade condition monitoring equipment to exchange data wirelessly or via wired communication with other devices. Although the figure shows a BeiDou-based wind turbine blade condition monitoring equipment with various systems, it should be understood that it is not required to implement or possess all the systems shown. More or fewer systems can be implemented alternatively.

[0164] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0165] The wind turbine blade condition monitoring device based on BeiDou positioning provided in this application adopts the wind turbine blade condition monitoring method based on BeiDou positioning in the above embodiments, which can solve the technical problem of wind turbine blade condition monitoring based on BeiDou positioning. Compared with related technologies, the beneficial effects of the wind turbine blade condition monitoring device based on BeiDou positioning provided in this application are the same as the beneficial effects of the wind turbine blade condition monitoring method based on BeiDou positioning provided in the above embodiments, and other technical features in the wind turbine blade condition monitoring device based on BeiDou positioning are the same as the features disclosed in the method of the previous embodiment, and will not be repeated here.

[0166] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0167] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0168] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, which are used to execute the wind turbine blade status monitoring method based on BeiDou positioning in the above embodiments.

[0169] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0170] The aforementioned computer-readable storage medium may be included in a wind turbine blade condition monitoring device based on BeiDou positioning; or it may exist independently and not be assembled into a wind turbine blade condition monitoring device based on BeiDou positioning.

[0171] The aforementioned computer-readable storage medium carries one or more programs that, when executed by the BeiDou-based wind turbine blade condition monitoring device, cause the BeiDou-based wind turbine blade condition monitoring device to: Based on the Beidou positioning receiver antenna, the main receiver in the nacelle, and the tower base reference station at the bottom of the wind turbine tower, a high-precision positioning measurement baseline is constructed by comparing signal differences, so as to calculate the three-dimensional absolute spatial coordinates and dynamic attitude angles of each monitoring section in real time. By integrating the three-dimensional absolute spatial coordinates and the dynamic attitude angles, and removing the rigid body motion components of the overall blade rotation and yaw from the total motion, the elastic deformation displacement time series of each monitoring section is obtained. The elastic deformation displacement time series and the angular velocity data obtained based on the inertial measurement unit are input into a preset blade condition monitoring model to calculate and output the three-dimensional displacement field at any position on the blade surface and inside through forward propagation. The loss function of the preset blade condition monitoring model is embedded with the unbalance quantity of the blade motion equation, and the unbalance quantity of the blade motion equation is used to constrain the three-dimensional displacement field to conform to physical laws.

[0172] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0173] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0174] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0175] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described method for monitoring the condition of wind turbine blades based on BeiDou positioning. This method can solve the technical problem of monitoring the condition of wind turbine blades based on BeiDou positioning. Compared with related technologies, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the wind turbine blade condition monitoring method based on BeiDou positioning provided in the above embodiments, and will not be elaborated upon here.

[0176] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the above-described method for monitoring the condition of wind turbine blades based on BeiDou positioning.

[0177] The computer program product provided in this application can solve the technical problem of wind turbine blade condition monitoring based on BeiDou positioning. Compared with related technologies, the beneficial effects of the computer program product provided in this application are the same as those of the wind turbine blade condition monitoring method based on BeiDou positioning provided in the above embodiments, and will not be repeated here.

[0178] The above description is only a part of the embodiments of this application and does not limit the scope of protection of this application. All equivalent structural transformations made under the technical concept of this application and using the content of this application specification and drawings, or direct / indirect applications in other related technical fields, are included in the scope of protection of this application.

Claims

1. A method for monitoring the condition of wind turbine blades based on BeiDou positioning, characterized in that, Multiple monitoring sections are arranged along the spanwise direction on the wind turbine blades. A Beidou positioning receiver antenna and an inertial measurement unit are fixedly installed at each monitoring section. A main receiver for the nacelle is installed on the top of the wind turbine nacelle. The wind turbine blade condition monitoring method based on Beidou positioning includes: Based on the Beidou positioning receiver antenna, the main receiver in the nacelle, and the tower base reference station at the bottom of the wind turbine tower, a high-precision positioning measurement baseline is constructed by comparing signal differences, so as to calculate the three-dimensional absolute spatial coordinates and dynamic attitude angles of each monitoring section in real time. By integrating the three-dimensional absolute spatial coordinates and the dynamic attitude angles, and removing the rigid body motion components of the overall blade rotation and yaw from the total motion, the elastic deformation displacement time series of each monitoring section is obtained. The elastic deformation displacement time series and the angular velocity data obtained based on the inertial measurement unit are input into a preset blade condition monitoring model to calculate and output the three-dimensional displacement field at any position on the blade surface and inside through forward propagation. The loss function of the preset blade condition monitoring model is embedded with the unbalance quantity of the blade motion equation, and the unbalance quantity of the blade motion equation is used to constrain the three-dimensional displacement field to conform to physical laws.

2. The method for monitoring the condition of wind turbine blades based on BeiDou positioning as described in claim 1, characterized in that, The step of fusing the three-dimensional absolute spatial coordinates and the dynamic attitude angles, and removing the rigid body motion components of the overall blade rotation and yaw from the total motion to obtain the elastic deformation displacement time series of each monitoring section, further includes: High-frequency acceleration and angular velocity data acquired by the inertial measurement unit are used as state prediction inputs, and low-frequency three-dimensional absolute spatial coordinates and dynamic attitude angles calculated by the Beidou positioning receiver antenna are used as observation update inputs. Through tight coupling fusion using a data fusion algorithm, the precise spatial pose of each monitoring section is obtained. Establish the transformation relationship between the blade rotation coordinate system and the global coordinate system to determine the overall rotational angular displacement and yaw angular displacement of the blade in the precise spatial pose; Subtract the rigid body motion components corresponding to the overall rotational angular displacement and yaw angular displacement of the blade from the precise spatial pose to obtain the displacement time series at each monitoring section caused only by elastic deformation.

3. The method for monitoring the condition of wind turbine blades based on BeiDou positioning as described in claim 1, characterized in that, Before the step of inputting the elastic deformation displacement time series and the angular velocity data obtained based on the inertial measurement unit into the preset blade condition monitoring model, the method further includes: A blade motion equation is constructed based on a beam structure with blade shape and material varying along the length direction as a theoretical model. The blade motion equation includes multi-directional vibration coupling terms in the flapping direction, oscillation direction, and torsional direction, as well as nonlinear terms caused by shape changes. Based on the blade motion equation in the form of unbalance quantity, a total loss function is constructed, and based on the total loss function, a blade condition monitoring model is constructed. Simulation data generated by the blade simulation model under multiple typical working conditions is collected and the simulation data is set as sample data. The simulation data includes the three-dimensional displacement, strain and stress of each discrete point of the blade. Based on the sample data, the blade condition monitoring model is iteratively trained to obtain a preset blade condition monitoring model.

4. The method for monitoring the condition of wind turbine blades based on BeiDou positioning as described in claim 1, characterized in that, After the step of calculating and outputting the three-dimensional displacement field at any position on and inside the blade surface through forward propagation, the method further includes: The main vibration mode features of the current blade are extracted from the three-dimensional displacement field. The main vibration mode features include flapping vibration frequency, oscillation vibration frequency, torsional vibration frequency, decay rate, vibration amplitude and bending morphology distribution corresponding to each vibration frequency. The main vibration mode characteristics are compared with preset alarm values. When the amplitude of any vibration mode characteristic exceeds the alarm value, a monitoring and early warning signal is generated.

5. The wind turbine blade condition monitoring method based on BeiDou positioning as described in claim 4, characterized in that, Following the step of generating the monitoring and early warning signal, the method further includes: Using the main vibration mode features as search query conditions, information retrieval and generation operations are performed in a pre-constructed operation and maintenance knowledge relationship network to recall historical operation cases that are most similar to the current vibration mode features, and to recall vibration reduction strategies and performance evaluations corresponding to the historical operation cases. Based on the current vibration mode characteristics and the evaluation of the execution effect, the vibration reduction strategy is optimized; Vibration suppression is achieved based on the optimized vibration reduction strategy.

6. The method for monitoring the condition of wind turbine blades based on BeiDou positioning as described in claim 5, characterized in that, The step of vibration suppression based on the optimized vibration reduction strategy further includes: Based on a pre-set set of physical limits for wind turbine units, a feasibility check is performed on the optimized vibration reduction strategy. If the recommended range of control parameters in the optimized vibration reduction strategy falls entirely within the safety boundary defined by the set of physical limits, the check is deemed to have passed, and the optimized vibration reduction strategy is converted into an executable sequence of control instructions. If the recommended range of control parameters in the optimized vibration reduction strategy exceeds the safety boundary, the recommended range of the control parameters is truncated and readjusted until the adjusted vibration reduction strategy fully meets all physical limit requirements. After the inspection is passed, the control command sequence obtained is sent to the corresponding active vibration damping actuator to suppress vibration. The active vibration damping actuator includes an independent pitch controller, a trailing edge flap actuator, and an electromagnetic damping adjuster.

7. A wind turbine blade condition monitoring device based on BeiDou positioning, characterized in that, The wind turbine blade condition monitoring device based on BeiDou positioning includes: The construction module is used to construct a high-precision positioning measurement baseline based on the Beidou positioning receiver antenna, the main receiver in the nacelle, and the tower base reference station at the bottom of the wind turbine tower by comparing signal differences, so as to calculate the three-dimensional absolute spatial coordinates and dynamic attitude angles of each monitoring section in real time. The fusion module is used to fuse the three-dimensional absolute spatial coordinates and the dynamic attitude angle, and remove the rigid body motion components of the overall rotation and yaw of the blade from the total motion to obtain the elastic deformation displacement time series of each monitoring section. The calculation module is used to input the elastic deformation displacement time series and the angular velocity data obtained based on the inertial measurement unit into a preset blade state monitoring model, so as to calculate and output the three-dimensional displacement field at any position on the blade surface and inside through forward propagation. The loss function of the preset blade state monitoring model is embedded with the unbalance quantity of the blade motion equation, and the unbalance quantity of the blade motion equation is used to constrain the three-dimensional displacement field to conform to the physical laws.

8. A wind turbine blade condition monitoring device based on BeiDou positioning, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the wind turbine blade condition monitoring method based on BeiDou positioning as described in any one of claims 1 to 6.

9. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the wind turbine blade condition monitoring method based on Beidou positioning as described in any one of claims 1 to 6.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the steps of the wind turbine blade condition monitoring method based on BeiDou positioning as described in any one of claims 1 to 6.

Images