Fan blade icing state prediction method, device, equipment, medium and product

Abstract

This invention relates to the field of electronic technology and discloses a method, apparatus, equipment, medium, and product for predicting the icing state of wind turbine blades. The method inputs target meteorological data into a pre-constructed wind turbine blade icing state identification model, which then outputs icing state data of the wind turbine blades. The wind turbine blade icing state identification model characterizes the correlation between meteorological data of the wind turbine's environment and the icing state data of the wind turbine blades. The method provided by this invention determines the icing state data of the wind turbine under target meteorological conditions through a pre-constructed wind turbine blade icing state identification model, enabling prediction of the wind turbine's icing state under target meteorological conditions. This facilitates maintenance personnel in taking corresponding measures to address icing problems in advance, solving the problem in related technologies where detection and alarms are only performed after icing occurs, and icing conditions cannot be predicted in advance.

Description

Technical Field

[0001] This invention relates to the field of electronic technology, specifically to methods, devices, equipment, media, and products for predicting the icing status of wind turbine blades. Background Technology

[0002] Wind turbine icing monitoring is a crucial link in the safe production, economic operation, and intelligent upgrading of wind farms. Its core value lies in preventing accidents, reducing losses, and optimizing efficiency. Related technologies generally rely on manual inspections and a small number of fixed-location sensors for wind turbine icing detection. Manual inspections are limited by time and space, making it impossible to grasp the icing situation of the entire wind farm in real time and comprehensively. Furthermore, inspection personnel face personal safety risks when working in inclement weather. The number of fixed sensors is insufficient to cover all critical parts of the wind turbine, leaving blind spots in monitoring icing conditions at special locations such as the edges of the turbine blades and high points of the tower. In addition, both manual inspections and sensor detection can only detect icing problems after they occur. Icing has adverse effects on wind turbine operation, such as power reduction and abnormal vibration. Taking appropriate measures after icing problems occur may lead to economic losses, and the wind turbine equipment also faces a significant risk of damage. Summary of the Invention

[0003] In view of this, the present invention provides a method, device, equipment, medium and product for predicting the icing state of wind turbine blades, in order to solve the problem that in related technologies, whether it is manual inspection or sensor detection, detection and alarm are carried out after the icing problem occurs, and the icing condition cannot be predicted in advance.

[0004] In a first aspect, the present invention provides a method for predicting the icing state of wind turbine blades. The method includes: acquiring target meteorological data of the environment where the wind turbine is located; inputting the target meteorological data into a pre-constructed wind turbine blade icing state identification model, so that the wind turbine blade icing state identification model outputs icing state data of the wind turbine blades, wherein the wind turbine blade icing state identification model is used to characterize the correlation between the meteorological data of the environment where the wind turbine is located and the icing state data of the wind turbine blades.

[0005] The wind turbine blade icing state prediction method provided by this invention inputs target meteorological data into a pre-constructed wind turbine blade icing state identification model, so that the model outputs icing state data of the wind turbine blades. The wind turbine blade icing state identification model is used to characterize the correlation between the meteorological data of the wind turbine's environment and the icing state data of the wind turbine blades. The method provided by this invention determines the icing state data of the wind turbine under target meteorological conditions through a pre-constructed wind turbine blade icing state identification model, realizing the prediction of the wind turbine's icing state under target meteorological conditions. This facilitates maintenance personnel to take corresponding measures in advance to deal with icing problems, solving the problem in related technologies that only detect and alarm after icing problems occur, and cannot predict icing conditions in advance.

[0006] In an optional implementation, the method further includes: acquiring basic data and design parameters of the wind turbine blades; constructing a digital twin model of the wind turbine based on the basic data and design parameters, the digital twin model including a geometric model, a structural dynamics model, an aerodynamic model, a thermodynamic model, and an early warning model, wherein the geometric model is used to characterize the three-dimensional spatial digital mapping of the wind turbine, the structural dynamics model is used to simulate the mechanical response of the wind turbine under load, the aerodynamic model is used to calculate the aerodynamic characteristics of the wind turbine blades in the airflow, the thermodynamic model is used to simulate the internal heat transfer process of the wind turbine, and the early warning model is used to provide early warning based on the output information of the structural dynamics model, the aerodynamic model, the thermodynamic model, and the icing state data; inputting the icing state data into the digital twin model so that the digital twin model can simulate the operating state of the wind turbine based on the icing state data to obtain simulation information; and sending the simulation information to a display terminal for display.

[0007] The method provided in this optional implementation constructs a digital twin model of the wind turbine, enabling comprehensive and real-time status monitoring of every component of the wind turbine unit. Whether it's critical operating parameters or subtle component changes, everything can be accurately represented in the digital twin model, achieving comprehensive real-time control over the icing situation of the wind farm. By simulating the wind turbine's operation under icing conditions using the digital twin model, the impact of icing on turbine operation is fully considered, thus more realistically reflecting the effects of icing on the turbine, allowing maintenance personnel to promptly identify problems.

[0008] In one optional implementation, the early warning model provides early warning through the following steps: acquiring structural feature data output by the structural dynamics model, aerodynamic feature data output by the aerodynamic model, and thermodynamic feature data output by the thermodynamic model; determining a first risk value based on icing status data; determining a second risk value based on the structural feature data; determining a third risk value based on the aerodynamic feature data; determining a fourth risk value based on the thermodynamic feature data; determining a target risk value based on the first, second, third, and fourth risk values; and issuing an early warning for the wind turbine's operating status if the target risk value exceeds a preset threshold.

[0009] The method provided in this optional implementation determines the target risk value of the wind turbine's operating status by using structural feature data output by the structural dynamics model, aerodynamic feature data output by the aerodynamic model, thermodynamic feature data output by the thermodynamic model, and icing state data. Based on the target risk value, the method provides an early warning of the wind turbine's operating status, ensuring the accuracy of the early warning results.

[0010] In one optional implementation, icing state data is input into a digital twin model to simulate the wind turbine's operating state based on the icing state data, thereby obtaining simulation information. This includes: inputting the icing state data into a pre-constructed icing texture feature determination model to obtain icing texture feature data of the wind turbine blades, wherein the icing texture feature determination model is used to characterize the correlation between the icing state data and the icing texture feature data of the wind turbine blades; and inputting the icing state data and the icing texture feature data into the digital twin model to output simulation information.

[0011] The method provided in this optional implementation determines the icing texture feature data of the wind turbine blades and uses a digital twin model to model the operating state of the wind turbine blades, which facilitates the improvement of the realism of subsequent visualization.

[0012] In one optional implementation, the wind turbine blade icing status identification model is constructed through the following steps: acquiring multiple meteorological data of the environment where the wind turbine is located and the corresponding icing status data of each meteorological data; obtaining an associated dataset by associating each meteorological data with the corresponding icing status data; and training a preset model using the associated dataset until the model accuracy meets the preset conditions to obtain the wind turbine blade icing status identification model.

[0013] In one optional implementation, icing status data is obtained through the following steps: acquiring first icing monitoring data and second icing monitoring data collected by a preset monitoring device; inputting the first icing monitoring data into an icing thickness identification model so that the icing thickness identification model outputs icing thickness data; inputting the second icing monitoring data into an icing type identification model so that the icing type identification model outputs icing type data; and determining icing status data based on the icing thickness data and the icing type data.

[0014] Secondly, the present invention provides a wind turbine blade icing state prediction device, the device comprising: a first acquisition module for acquiring target meteorological data of the environment where the wind turbine is located; and a first determination module for inputting the target meteorological data into a pre-constructed wind turbine blade icing state identification model, so that the wind turbine blade icing state identification model outputs icing state data of the wind turbine blade, wherein the wind turbine blade icing state identification model is used to characterize the correlation between the meteorological data of the environment where the wind turbine is located and the icing state data of the wind turbine blade.

[0015] Thirdly, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to perform the wind turbine blade icing state prediction method of the first aspect or any corresponding embodiment described above.

[0016] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to execute the wind turbine blade icing state prediction method of the first aspect or any corresponding embodiment thereof.

[0017] Fifthly, the present invention provides a computer program product, including computer instructions for causing a computer to execute the wind turbine blade icing state prediction method of the first aspect or any corresponding embodiment thereof. Attached Figure Description

[0018] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0019] Figure 1 This is a flowchart illustrating the wind turbine blade icing state prediction method according to an embodiment of the present invention. Figure 2 This is a flowchart illustrating another method for predicting the icing state of wind turbine blades according to an embodiment of the present invention. Figure 3 This is a structural block diagram of a wind turbine blade icing state prediction device according to an embodiment of the present invention; Figure 4 This is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0021] In related technologies, wind turbine icing detection generally relies on manual inspections and a small number of fixed-location sensors. Manual inspections are limited by time and space, making it impossible to grasp the icing situation of the entire wind farm in real time and comprehensively. Furthermore, inspection personnel face safety risks when working in inclement weather. The number of fixed sensors is insufficient to cover all critical parts of the wind turbine, leaving blind spots in monitoring icing conditions at special locations such as blade edges and high points on the tower. In addition, both manual inspections and sensor detection only issue alarms after icing problems occur. Icing has adverse effects on wind turbine operation, such as power reduction and abnormal vibration. Waiting until icing problems occur to issue warnings and take corresponding measures may result in economic losses and expose the wind turbine equipment to a significant risk of damage.

[0022] In view of this, the wind turbine blade icing state prediction method provided in this application embodiment can be applied to a server to predict the icing state of wind turbine blades. The method provided in this application embodiment inputs target meteorological data into a pre-constructed wind turbine blade icing state identification model, so that the wind turbine blade icing state identification model outputs icing state data of the wind turbine blades. The wind turbine blade icing state identification model is used to characterize the correlation between the meteorological data of the wind turbine's environment and the icing state data of the wind turbine blades, realizing the prediction of the wind turbine's icing state under target meteorological conditions. This facilitates maintenance personnel to take corresponding measures in advance to deal with icing problems, solving the problem in related technologies that only detect and alarm after icing problems occur, and cannot predict the icing state in advance.

[0023] According to an embodiment of the present invention, a method for predicting the icing state of wind turbine blades is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0024] This embodiment provides a method for predicting the icing state of wind turbine blades, which can be used in the aforementioned server. Figure 1 This is a flowchart of a wind turbine blade icing state prediction method according to an embodiment of the present invention, as shown below. Figure 1 As shown, the process includes the following steps: Step S101: Obtain target meteorological data of the environment where the wind turbine is located.

[0025] For example, the wind turbine can be a wind turbine unit that requires icing state prediction, and the target meteorological data can include, but is not limited to, meteorological forecast data of the environment where the wind turbine is located for a future target period. The meteorological forecast data can include, but is not limited to, temperature and humidity. The embodiments of this application do not limit the specific content of the target period, which can be determined by those skilled in the art according to their needs.

[0026] Step S102: Input the target meteorological data into the pre-constructed wind turbine blade icing state identification model, so that the wind turbine blade icing state identification model outputs the icing state data of the wind turbine blades. The wind turbine blade icing state identification model is used to characterize the correlation between the meteorological data of the wind turbine's environment and the icing state data of the wind turbine blades. The icing state data may include, but is not limited to, the thickness and type of icing, and the icing type may include, but is not limited to, frost ice, rime ice, mixed ice, and ice-free.

[0027] For example, in this embodiment of the application, a preset model can be trained using a training set, enabling the preset model to learn the correlation between meteorological data and icing state data, thereby obtaining a pre-constructed wind turbine blade icing state recognition model. The preset model may include, but is not limited to, a deep learning model. This embodiment of the application does not limit the specific content of the preset model, and those skilled in the art can determine it according to their needs.

[0028] The wind turbine blade icing state prediction method provided in this embodiment inputs target meteorological data into a pre-constructed wind turbine blade icing state identification model, so that the wind turbine blade icing state identification model outputs icing state data of the wind turbine blades. The wind turbine blade icing state identification model is used to characterize the correlation between the meteorological data of the wind turbine's environment and the icing state data of the wind turbine blades, realizing the prediction of the wind turbine's icing state under the target meteorological conditions. This facilitates maintenance personnel to take corresponding measures in advance to deal with icing problems, and solves the problem in related technologies that only detect and alarm after icing problems occur, but cannot predict the icing state in advance.

[0029] This embodiment provides a method for predicting the icing state of wind turbine blades, which can be used in the aforementioned server. Figure 2 This is a flowchart of a wind turbine blade icing state prediction method according to an embodiment of the present invention, as shown below. Figure 2 As shown, the process includes the following steps: Step S201: Obtain target meteorological data for the environment where the wind turbine is located. For details, please refer to [link to relevant documentation]. Figure 1 Step S101 of the illustrated embodiment will not be described again here.

[0030] Step S202: Input the target meteorological data into the pre-constructed wind turbine blade icing state identification model so that the wind turbine blade icing state identification model outputs the icing state data of the wind turbine blade. The wind turbine blade icing state identification model is used to characterize the correlation between the meteorological data of the wind turbine's environment and the icing state data of the wind turbine blade.

[0031] In some alternative implementations, the wind turbine blade icing status identification model is constructed through the following steps: Step a1: Obtain multiple meteorological data of the environment where the wind turbine is located, as well as the icing status data corresponding to each meteorological data.

[0032] For example, multiple meteorological data can be meteorological data of the environment where the wind turbine is located at different historical periods, and icing status data can be determined based on icing monitoring data. Icing monitoring data can include, but is not limited to, radar inversion water vapor information, micrometeorology, blade icing images, etc.

[0033] Step a2 involves associating each meteorological data with its corresponding icing status data to obtain an associated dataset.

[0034] For example, the embodiments of this application do not limit the way meteorological data and icing status data are associated. Those skilled in the art can determine the method according to their needs, as long as the association can be achieved.

[0035] Step a3: Train the preset model using the associated dataset until the model accuracy meets the preset conditions to obtain the wind turbine blade icing status recognition model.

[0036] For example, the preset model may include, but is not limited to, a deep learning model, and the preset conditions may be determined based on experience.

[0037] In some alternative implementations, icing status data is obtained through the following steps: Step b1: Obtain the first icing monitoring data and the second icing monitoring data collected by the preset monitoring equipment.

[0038] For example, in the embodiments of this application, the first icing monitoring data may include, but is not limited to, radar inversion water vapor information and micro-meteorological information, and the second icing monitoring data may include, but is not limited to, icing image data.

[0039] Step b2: Input the first icing monitoring data into the icing thickness identification model so that the icing thickness identification model outputs icing thickness data.

[0040] For example, in this embodiment of the application, historical lightning-induced water vapor information and micro-meteorological information are used as training samples, and ice thickness is used as the output to train a convolutional neural network enhanced Transformer (CNN++Transformer) model to obtain an ice thickness recognition model.

[0041] Step b3: Input the second icing monitoring data into the icing type identification model so that the icing type identification model outputs icing type data.

[0042] For example, in this embodiment of the application, images of icing on leaves collected by a camera, drone or sensor are used as training data, and the icing type, such as frost, rime, mixed ice or no ice, is used as the output to train the CNN model to obtain an icing type recognition model.

[0043] Step b3: Determine the icing status data based on the icing thickness data and icing type data.

[0044] For example, in this embodiment of the application, ice thickness data and ice type data are used as ice status data.

[0045] Step S203: Obtain the basic data and design parameters of the wind turbine blades.

[0046] For example, in this embodiment of the application, a sensor is set at a preset position on the wind turbine blade, and the basic data of the wind turbine blade and the design parameters of the wind turbine blade are obtained through the sensor.

[0047] The sensor locations and corresponding sensors include: In the blade root region, strain sensors are installed to monitor bending and torsional stresses; a fiber Bragg grating sensor array is used for distributed monitoring of temperature and strain distribution. In the blade tip region, accelerometers are used for high-frequency vibration monitoring; laser displacement sensors are used for non-contact deformation measurement. At the leading and trailing edges, fiber Bragg grating (FBG) strain sensors are installed to monitor aerodynamic load distribution; acoustic emission sensors are used to capture crack propagation signals.

[0048] The design parameters include: blade design parameters (geometric parameters, layup angle, material rigidity matrix) and manufacturing process data.

[0049] Step S204: Construct a digital twin model of the wind turbine based on basic data and design parameters. The digital twin model includes a geometric model, a structural dynamics model, an aerodynamic model, a thermodynamic model, and an early warning model. The geometric model is used to characterize the three-dimensional digital mapping of the wind turbine. The structural dynamics model is used to simulate the mechanical response of the wind turbine under load. The aerodynamic model is used to calculate the aerodynamic characteristics of the wind turbine blades in the airflow. The thermodynamic model is used to simulate the internal heat transfer process of the wind turbine. The early warning model is used to issue early warnings based on the output information of the structural dynamics model, the aerodynamic model, the thermodynamic model, and the icing status data.

[0050] For example, in this embodiment of the application, a geometric model and a functional model of a digital twin of a wind farm are constructed using basic data and the geometric parameters of the wind turbine blades. The functional model includes a structural dynamics model, an aerodynamic model, a thermodynamic model, and an early warning model. Stiffness, mass, and damping matrices are established based on the Finite Element Method (FEA), and assembled into an overall structural dynamics equation. Solving this equation yields the displacement, stress, and strain responses of the wind turbine structure under various loads. The aerodynamic model of the wind turbine blades is a mathematical or physical model used to describe and predict the aerodynamic characteristics exhibited by the wind turbine blades in the airflow. The aerodynamic model of the wind turbine blades is constructed using Computational Fluid Dynamics (CFD). CFD is used to simulate the fluid flow inside and around the wind turbine, including airflow velocity and pressure distribution, while the thermodynamic model is used to describe the heat exchange between the fluid and the solid, as well as the heat conduction process within the solid. By coupling these two models, the effects of fluid flow on heat transfer (such as forced convection heat transfer) and the effects of heat transfer on fluid properties and flow state (such as density changes caused by thermal expansion) are considered, achieving a more accurate simulation. For the solid components of the wind turbine (such as blades and hubs), a thermodynamic model is established based on the thermophysical properties of their materials (such as thermal conductivity, specific heat capacity, and density). At a fixed time step, information such as fluid velocity, temperature, and pressure calculated by the CFD model is transferred to the thermodynamic model, while the temperature distribution information of the solid components calculated by the thermodynamic model is fed back to the CFD model.

[0051] In this embodiment, the geometric model is a three-dimensional geometric representation created based on parameters such as blade length, chord length distribution, and twist angle distribution, and a finite element mesh is generated. The aerodynamic model employs a combination of Blade Element Momentum Theory (BEM) and CFD. First, the basic aerodynamic loads are calculated using BEM, then corrected using CFD, considering the impact of blade deformation on aerodynamic performance. The thermodynamic model, coupled with the CFD model, calculates heat exchange between the fluid and solid, considering convection, conduction, and radiation, and simulates the blade temperature distribution. The structural dynamics model constructs the mass matrix, stiffness matrix, and damping matrix based on the finite element method, solving for the displacement and stress response of the structure under aerodynamic loads, temperature loads, and icing loads. The early warning model monitors parameters such as stress, temperature, icing thickness, and displacement in real time, triggering corresponding levels of warnings when thresholds are exceeded. This implementation adopts a modular design, with data exchange between models via interfaces, supporting multiphysics coupled simulations. You can adapt to different types of wind turbines and simulation requirements by modifying the configuration file.

[0052] Step S205: Input the icing status data into the digital twin model so that the digital twin model can simulate the operating status of the wind turbine based on the icing status data and obtain simulation information.

[0053] Specifically, step S205 above includes: Step c1: Input the icing state data into the pre-built icing texture feature determination model to obtain the icing texture feature data of the wind turbine blade. The icing texture feature determination model is used to characterize the correlation between the icing state data and the icing texture feature data of the wind turbine blade.

[0054] For example, in this embodiment of the application, the ice thickness and ice type are used as inputs to a pre-trained data-driven model, and the output is ice texture feature values. The preset network model is then trained to obtain an ice texture feature determination model.

[0055] Furthermore, in this embodiment of the application, the ice texture feature data can also be determined by a pre-set relationship table between ice thickness, ice type and ice texture features, as shown in Table 1 below.

[0056] Table 1

[0057] Step c2: Input the icing state data and icing texture feature data into the digital twin model so that the digital twin model can output simulation information.

[0058] For example, in this embodiment of the application, the icing state of the wind turbine blades is simulated on a digital twin model of the wind turbine blades based on the icing texture features to obtain simulation information.

[0059] Step S206: Send the simulation information to the display terminal for display.

[0060] For example, the display terminal can be a terminal device with display function. The specific content of the display terminal is not limited in the embodiments of this application, and those skilled in the art can determine it according to their needs.

[0061] In some optional implementations, the early warning model issues an early warning through the following steps: Step d1: Obtain the structural feature data output by the structural dynamics model, the aerodynamic feature data output by the aerodynamic model, and the thermodynamic feature data output by the thermodynamic model.

[0062] For example, structural characteristic data may include, but is not limited to, peak blade stress, tower vibration acceleration, and blade deformation. Aerodynamic characteristic data may include, but is not limited to, power loss values. Thermodynamic characteristic data may include, but is not limited to, bearing temperature and gearbox oil temperature difference.

[0063] In this embodiment, the structural dynamics model receives information on the distribution and thickness of icing. Icing increases the blade's mass and alters its center of gravity, thus affecting the blade's vibration characteristics and structural response. Icing information is integrated into the input parameters of the structural dynamics model via an interface, taking the impact of icing into account when calculating the blade's moment of inertia and mass distribution. An icing state identification model transmits information such as the geometry and surface roughness of the icing to the aerodynamic model. Based on this information, the aerodynamic model adjusts the blade's airfoil parameters and aerodynamic coefficients to more accurately simulate the interaction between the airflow and the blade. The icing process involves heat exchange; the icing state identification model provides information on the thickness and type of icing. The thermodynamic model uses this information to calculate the ice growth and melting rates, as well as the heat transfer process between the blade and the ice.

[0064] Step d2: Determine the first risk value based on the icing status data.

[0065] For example, in this embodiment of the application, a first risk value is determined based on the severity and development trend of icing.

[0066] Step d3: Determine the second risk value based on the structural feature data.

[0067] For example, in this embodiment of the application, a second risk value is determined based on the stress and deformation output by the structural dynamics model.

[0068] Step d4: Determine the third risk value based on aerodynamic characteristic data.

[0069] For example, in this embodiment of the application, a third risk value is determined based on the power loss output by the aerodynamic model.

[0070] Step d5: Determine the fourth risk value based on thermodynamic characteristic data.

[0071] For example, in this embodiment of the application, a fourth risk value is determined based on the bearing temperature and the gearbox oil temperature difference.

[0072] Step d6: Determine the target risk value based on the first risk value, the second risk value, the third risk value, and the fourth risk value.

[0073] For example, in this embodiment of the application, the first risk value, the second risk value, the third risk value and the fourth risk value are weighted and summed to obtain the target risk value.

[0074] Step d7: If the target risk value is greater than the preset threshold, issue an early warning on the operating status of the wind turbine.

[0075] For example, the specific content of the preset threshold is not limited in the embodiments of this application. Those skilled in the art can determine it according to their needs, as long as it is reasonable.

[0076] This embodiment also provides a wind turbine blade icing state prediction device, which is used to implement the above embodiments and preferred embodiments, and will not be repeated as already described. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0077] This embodiment provides a device for predicting the icing status of wind turbine blades, such as... Figure 3 As shown, it includes: The first acquisition module 301 is used to acquire target meteorological data of the environment where the wind turbine is located; The first determining module 302 is used to input the target meteorological data into the pre-constructed wind turbine blade icing state identification model, so that the wind turbine blade icing state identification model outputs the icing state data of the wind turbine blade. The wind turbine blade icing state identification model is used to characterize the correlation between the meteorological data of the environment where the wind turbine is located and the icing state data of the wind turbine blade.

[0078] In some alternative embodiments, the device further includes: The second acquisition module is used to acquire the basic data and design parameters of the wind turbine blades; The building module is used to construct a digital twin model of the wind turbine based on basic data and design parameters. The digital twin model includes a geometric model, a structural dynamics model, an aerodynamic model, a thermodynamic model, and an early warning model. The geometric model is used to characterize the three-dimensional digital mapping of the wind turbine. The structural dynamics model is used to simulate the mechanical response of the wind turbine under load. The aerodynamic model is used to calculate the aerodynamic characteristics of the wind turbine blades in the airflow. The thermodynamic model is used to simulate the internal heat transfer process of the wind turbine. The early warning model is used to provide early warning based on the output information of the structural dynamics model, the aerodynamic model, the thermodynamic model, and the icing status data. The second determining module is used to input the icing status data into the digital twin model so that the digital twin model can simulate the operating status of the wind turbine based on the icing status data and obtain simulation information. The display module is used to send analog information to the display terminal for display.

[0079] In some optional implementations, the early warning model issues an early warning through the following steps: Obtain structural feature data output by the structural dynamics model, aerodynamic feature data output by the aerodynamic model, and thermodynamic feature data output by the thermodynamic model; The first risk value is determined based on the icing status data; The second risk value is determined based on structural feature data; The third risk value is determined based on aerodynamic characteristic data; The fourth risk value is determined based on thermodynamic characteristic data; The target risk value is determined based on the first risk value, the second risk value, the third risk value, and the fourth risk value; If the target risk value exceeds the preset threshold, an early warning will be issued regarding the operating status of the wind turbine.

[0080] In some alternative implementations, the second determining module includes: The first determination submodule is used to input the icing state data into the pre-built icing texture feature determination model to obtain the icing texture feature data of the wind turbine blade. The icing texture feature determination model is used to characterize the correlation between the icing state data and the icing texture feature data of the wind turbine blade. The second determining submodule is used to input icing state data and icing texture feature data into the digital twin model so that the digital twin model outputs simulation information.

[0081] In some alternative implementations, the wind turbine blade icing status identification model is constructed through the following steps: Acquire multiple meteorological data of the environment where the wind turbine is located, as well as the corresponding icing status data for each meteorological data; By associating each meteorological data with the corresponding icing status data, an associated dataset is obtained; The pre-set model is trained using the associated dataset until the model accuracy meets the pre-set conditions, thus obtaining the wind turbine blade icing status recognition model.

[0082] In some alternative implementations, icing status data is obtained through the following steps: Acquire the first and second icing monitoring data collected by the preset monitoring equipment; Input the first icing monitoring data into the icing thickness identification model so that the icing thickness identification model outputs icing thickness data; The second icing monitoring data is input into the icing type identification model so that the icing type identification model outputs icing type data; Icing status data is determined based on icing thickness and icing type data.

[0083] Further functional descriptions of the above modules and units are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0084] In this embodiment, the wind turbine blade icing state prediction device is presented in the form of a functional unit. Here, a unit refers to an ASIC (Application Specific Integrated Circuit), a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0085] This invention also provides a computer device having the above-described features. Figure 3 The device shown is for predicting the icing status of wind turbine blades.

[0086] Please see Figure 4 , Figure 4 This is a schematic diagram of the structure of a computer device provided in an optional embodiment of the present invention, such as... Figure 4 As shown, the computer device includes one or more processors 10, memory 20, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components communicate with each other via different buses and can be mounted on a common motherboard or otherwise installed as needed. The processors can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on external input / output devices (such as display devices coupled to the interfaces). In some alternative implementations, multiple processors and / or multiple buses can be used with multiple memories, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 4 Take a processor 10 as an example.

[0087] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GDA), or any combination thereof.

[0088] The memory 20 stores instructions executable by at least one processor 10 to cause the at least one processor 10 to perform the method shown in the above embodiments.

[0089] The memory 20 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the computer device. Furthermore, the memory 20 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0090] The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0091] The computer device also includes a communication interface 30 for communicating with other devices or communication networks.

[0092] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code, which, when accessed and executed by the computer, processor, or hardware, implements the methods shown in the above embodiments.

[0093] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0094] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for predicting the icing state of wind turbine blades, characterized in that, The method includes: Acquire target meteorological data of the environment where the wind turbine is located; The target meteorological data is input into a pre-constructed wind turbine blade icing state identification model, so that the wind turbine blade icing state identification model outputs the icing state data of the wind turbine blade. The wind turbine blade icing state identification model is used to characterize the correlation between the meteorological data of the wind turbine's environment and the icing state data of the wind turbine blade.

2. The method according to claim 1, characterized in that, The method further includes: Obtain basic data and design parameters for wind turbine blades; A digital twin model of the wind turbine is constructed based on the aforementioned basic data and design parameters. The digital twin model includes a geometric model, a structural dynamics model, an aerodynamic model, a thermodynamic model, and an early warning model. The geometric model is used to characterize the three-dimensional digital mapping of the wind turbine. The structural dynamics model is used to simulate the mechanical response of the wind turbine under load. The aerodynamic model is used to calculate the aerodynamic characteristics of the wind turbine blades in the airflow. The thermodynamic model is used to simulate the internal heat transfer process of the wind turbine. The early warning model is used to issue early warnings based on the output information of the structural dynamics model, the aerodynamic model, the thermodynamic model, and the icing state data. The icing status data is input into the digital twin model so that the digital twin model can simulate the operating status of the wind turbine based on the icing status data and obtain simulation information. The simulated information is sent to the display terminal for display.

3. The method according to claim 2, characterized in that, The early warning model issues warnings through the following steps: Obtain the structural feature data output by the structural dynamics model, the aerodynamic feature data output by the aerodynamic model, and the thermodynamic feature data output by the thermodynamic model; A first risk value is determined based on the icing status data; A second risk value is determined based on the structural feature data; A third risk value is determined based on the aforementioned aerodynamic characteristic data; A fourth risk value is determined based on the aforementioned thermodynamic characteristic data; The target risk value is determined based on the first risk value, the second risk value, the third risk value, and the fourth risk value; If the target risk value is greater than a preset threshold, an early warning will be issued regarding the operating status of the wind turbine.

4. The method according to claim 2, characterized in that, The icing status data is input into the digital twin model, so that the digital twin model can simulate the operating status of the wind turbine based on the icing status data, and obtain simulation information, including: The icing state data is input into a pre-constructed icing texture feature determination model to obtain icing texture feature data of the wind turbine blade. The icing texture feature determination model is used to characterize the correlation between the icing state data and the icing texture feature data of the wind turbine blade. The icing state data and the icing texture feature data are input into the digital twin model so that the digital twin model outputs simulation information.

5. The method according to any one of claims 1 to 4, characterized in that, The wind turbine blade icing status identification model is constructed through the following steps: Acquire multiple meteorological data of the environment where the wind turbine is located, as well as the corresponding icing status data for each meteorological data; By associating each meteorological data with the corresponding icing status data, an associated dataset is obtained; The preset model is trained using the associated dataset until the model accuracy meets the preset conditions, thus obtaining the wind turbine blade icing state recognition model.

6. The method according to claim 5, characterized in that, The icing status data is obtained through the following steps: Acquire the first and second icing monitoring data collected by the preset monitoring equipment; The first icing monitoring data is input into the icing thickness identification model so that the icing thickness identification model outputs icing thickness data; The second icing monitoring data is input into the icing type identification model so that the icing type identification model outputs icing type data; The icing status data is determined based on the icing thickness data and the icing type data.

7. A device for predicting the icing status of wind turbine blades, characterized in that, The device includes: The first acquisition module is used to acquire target meteorological data of the environment where the wind turbine is located; The first determining module is used to input the target meteorological data into a pre-constructed wind turbine blade icing state identification model, so that the wind turbine blade icing state identification model outputs the icing state data of the wind turbine blade. The wind turbine blade icing state identification model is used to characterize the correlation between the meteorological data of the environment where the wind turbine is located and the icing state data of the wind turbine blade.

8. A computer device, characterized in that, include: The system includes a memory and a processor, which are interconnected. The memory stores computer instructions, and the processor executes the computer instructions to perform the wind turbine blade icing state prediction method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to execute the wind turbine blade icing state prediction method according to any one of claims 1 to 6.

10. A computer program product, characterized in that, Includes computer instructions for causing a computer to execute the wind turbine blade icing state prediction method according to any one of claims 1 to 6.

Images