Structural load prediction method, device and equipment and computer readable storage medium

Abstract

The invention discloses a structural load prediction method, device and equipment and a computer readable storage medium, and relates to the technical field of wind power, and the method comprises the steps: obtaining geometric parameters and material attribute parameters of a to-be-predicted fan structure, and an environment parameter feature range of an environment where the to-be-predicted fan structure is located; constructing a multi-physics field coupling model according to the geometric parameters, the material attribute parameters and the environmental parameter characteristic range; the multi-physics field coupling model comprises a temperature field module, a structural mechanical field module, an airflow field module and a particle impact field module, and the physics field modules perform bidirectional data exchange through coupling interfaces to simulate interaction among the physics fields; acquiring an environmental parameter value of the to-be-predicted fan structure under the target working condition; inputting the environmental parameter values into a multi-physics field coupling model to obtain mechanical response data of the to-be-predicted fan structure under the target working condition; and determining predicted load data of the to-be-predicted fan structure according to the mechanical response data.

Description

Technical Field

[0001] This application relates to the field of wind power technology, and in particular to a structural load prediction method, apparatus, equipment, and computer-readable storage medium. Background Technology

[0002] Against the backdrop of the rapid development of the wind power industry, wind turbine structures operate for extended periods in complex natural environments (such as extreme temperature differences, strong wind turbulence, and sandstorm impacts). Their load data directly determines their structural design strength, service life, and operation and maintenance strategies. Therefore, accurate load forecasting is crucial for avoiding resource waste caused by over-design and preventing safety hazards caused by structural fatigue damage, directly impacting the economic efficiency and reliability of wind farm operation.

[0003] Currently, simplified methods such as physical mechanism analysis, basic historical data statistics, or empirical assumptions are commonly used to predict the load data of wind turbine structures in complex environments. However, these methods are difficult to adapt to the dynamic interaction characteristics of multiple factors in complex environments, resulting in low prediction accuracy. Summary of the Invention

[0004] The main objective of this application is to provide a structural load prediction method, apparatus, device, and computer-readable storage medium, which aims to improve the accuracy of load data prediction for wind turbine structures.

[0005] This application provides a structural load prediction method, the method comprising: Obtain the geometric parameters, material property parameters, and environmental parameter characteristic ranges of the environment in which the wind turbine structure is located; the environmental parameter characteristic ranges include temperature variation range, wind speed range, particulate matter concentration range, and / or particle size distribution range. Based on the geometric parameters, material property parameters, and environmental parameter characteristic ranges, a multiphysics coupling model is constructed. The multiphysics coupling model includes a temperature field module, a structural mechanics field module, an airflow field module, and a particle impact field module. The physical field modules exchange data bidirectionally through a coupling interface to simulate the interaction between the physical fields. Obtain the environmental parameter values ​​of the wind turbine structure to be predicted under the target operating conditions; The environmental parameter values ​​are input into the multiphysics coupling model to obtain the mechanical response data of the wind turbine structure to be predicted under the target operating condition. Based on the mechanical response data, the predicted load data of the wind turbine structure to be predicted is determined.

[0006] In one embodiment, the step of constructing a multiphysics coupling model based on the geometric parameters, the material property parameters, and the characteristic range of the environmental parameters includes: Based on the geometric parameters, the material property parameters, and the characteristic range of the environmental parameters, the basic control functions of the temperature field module, the structural mechanics field module, the airflow field module, and the particle impact field module are constructed respectively. A first bidirectional coupling interface, a second bidirectional coupling interface, a third bidirectional coupling interface, a fourth bidirectional coupling interface, and a fifth bidirectional coupling interface are respectively established between the temperature field module and the structural mechanics field module, between the temperature field module and the airflow field module, between the airflow field module and the structural mechanics field module, between the airflow field module and the particle impact field module, and between the particle impact field module and the structural mechanics field module. Based on the basic control functions of the temperature field module, the structural mechanics field module, the airflow field module, and the particle impact field module, as well as the first bidirectional coupling interface, the second bidirectional coupling interface, the third bidirectional coupling interface, the fourth bidirectional coupling interface, and the fifth bidirectional coupling interface, the multiphysics coupling model is integrated to form the multiphysics coupling model.

[0007] In one embodiment, the step of constructing the basic control functions for the temperature field module, the structural mechanics field module, the airflow field module, and the particle impact field module based on the geometric parameters, the material property parameters, and the environmental parameter characteristic ranges, respectively, includes: Based on the geometric parameters, material property parameters, and environmental parameter characteristic ranges, the geometric boundary coefficients, material property coefficients, and environmental load coefficients of the basic control functions of each physical field module are determined respectively. Substitute the geometric boundary coefficients, material property coefficients, and environmental load coefficients of each physical field module into the general expression of the control function corresponding to each physical field module to obtain the basic control functions of the temperature field module, structural mechanics field module, airflow field module, and particle impact field module, respectively.

[0008] In one embodiment, the mechanical response data includes stress distribution data, strain distribution data, displacement distribution data, vibration frequency, and vibration acceleration of the wind turbine structure; The step of determining the predicted load data of the wind turbine structure to be predicted based on the mechanical response data includes: Extract the extreme value data from the mechanical response data, which includes the maximum stress, maximum strain, maximum displacement, maximum vibration frequency, and maximum vibration acceleration; Based on the preset mapping relationship between the extreme values ​​of mechanical response and the load data of the wind turbine structure, the extreme value data is subjected to load equivalent transformation to obtain the predicted load data of the wind turbine structure to be predicted.

[0009] In one embodiment, the step of obtaining material property parameters of the wind turbine structure to be predicted includes: Obtain material property test data of the material used in the wind turbine structure to be predicted at multiple temperature gradient points, where each temperature gradient point covers the temperature change range in the environmental parameter characteristic range. Based on the material property test data, a continuous function of material property change with temperature is obtained through nonlinear fitting; The parameterized data of the material properties characterized by the continuous function as a function of temperature are used as the material property parameters.

[0010] In one embodiment, after the step of determining the predicted load data of the wind turbine structure to be predicted based on the mechanical response data, the method further includes: Obtain the actual load monitoring data of the wind turbine structure to be predicted; The prediction error value of the load data is determined by comparing the actual load monitoring data with the predicted load data. If the prediction error value is greater than the preset error threshold, the coupling parameters and / or coefficients of the basic control function associated with the bidirectional coupling interface in the multiphysics coupling model are adjusted to iteratively optimize the multiphysics coupling model until the determined prediction error value is less than or equal to the prediction error value.

[0011] In one embodiment, the step of adjusting the coupling parameters and / or coefficients of the fundamental control function associated with the bidirectional coupling interface in the multiphysics coupling model includes: Based on the deviation between the predicted load data and the actual load monitoring data, error distribution data is generated; The first contribution weight of each physical field module in the multiphysics coupling model to the error distribution data is determined by the error source tracing algorithm. Adjust the coefficients of the basic control function of the first physics module with the largest contribution weight in the multiphysics coupling model; And / or, through an error tracing algorithm, determine the second contribution weight of each bidirectional coupling interface in the multiphysics coupling model to the error distribution data; Adjust the coupling parameters associated with the bidirectional coupling interface that has the largest second contribution weight in the multiphysics coupling model.

[0012] Furthermore, to achieve the above objectives, this application also provides a structural load prediction device, the device comprising: The data acquisition module is used to acquire the geometric parameters, material property parameters, and environmental parameter characteristic ranges of the environment in which the wind turbine structure to be predicted is located; the environmental parameter characteristic ranges include temperature variation range, wind speed range, particulate matter concentration range, and / or particle size distribution range. The model building module is used to construct a multiphysics coupling model based on the geometric parameters, the material property parameters, and the characteristic range of the environmental parameters. The multiphysics coupling model includes a temperature field module, a structural mechanics field module, an airflow field module, and a particle impact field module. The physical field modules exchange data bidirectionally through a coupling interface to simulate the interaction between the physical fields. The data acquisition module is also used to acquire the environmental parameter values ​​of the wind turbine structure to be predicted under the target operating conditions; The load prediction module is used to input the environmental parameter values ​​into the multiphysics coupling model to obtain the mechanical response data of the wind turbine structure to be predicted under the target operating condition; and to determine the predicted load data of the wind turbine structure to be predicted based on the mechanical response data.

[0013] In addition, to achieve the above objectives, this application also provides an electronic device, which 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 structural load prediction method as described above.

[0014] In addition, to achieve the above objectives, this application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the structural load prediction method described above.

[0015] 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 structural load prediction method described above.

[0016] This application provides a structural load prediction method. First, the geometric parameters, material property parameters, and environmental parameter characteristic ranges of the wind turbine structure to be predicted are obtained. Then, a multi-physics coupling model including a temperature field module, a structural mechanical field module, an airflow field module, and a particle impact field module is constructed based on the above parameters. The physical field modules exchange data bidirectionally through a coupling interface. Then, the environmental parameter values ​​under the target working condition are input into the multi-physics coupling model to obtain mechanical response data, and finally the predicted load data is determined. Compared to conventional methods, the multi-physics coupling model constructed in this application, through bidirectional data exchange between various physics modules, can accurately reproduce the real dynamic interaction process between temperature, airflow, particle impact, and structural mechanics of the wind turbine structure in complex natural environments. For example, changes in temperature distribution in the temperature field can be transmitted to the structural mechanics field through the coupling interface to correct the relevant parameters of the structural mechanics field; changes in wind speed in the airflow field can be transmitted to the particle impact field to adjust the impact velocity and trajectory of particles, and then fed back to the structural mechanics field to update the stress state of the structure. This solves the problem that existing technologies cannot accurately depict the interaction of multiple fields, thereby improving the accuracy of load data prediction for wind turbine structures. It can provide a reliable basis for the design strength verification, service life assessment, and operation and maintenance strategy formulation of wind turbine structures, effectively avoiding the risk of over-design cost waste or structural fatigue damage caused by under-design due to prediction deviations, and ensuring the safe and efficient operation of wind turbine structures in wind farms. Attached Figure Description

[0017] 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.

[0018] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 A schematic flowchart illustrating the structural load prediction method provided in the first embodiment of this application; Figure 2 A schematic flowchart illustrating the structural load prediction method provided in the second embodiment of this application; Figure 3 This is a schematic diagram of the module structure of the structural load prediction device provided in the embodiments of this application; Figure 4 This is a schematic diagram of the hardware operating environment involved in the embodiments of this application.

[0020] 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

[0021] 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.

[0022] 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.

[0023] Against the backdrop of the rapid development of the wind power industry, wind turbine structures operate for extended periods in complex natural environments (such as extreme temperature differences, strong wind turbulence, and sandstorm impacts). Their load data directly determines their structural design strength, service life, and operation and maintenance strategies. Therefore, accurate load forecasting is crucial for avoiding resource waste caused by over-design and preventing safety hazards caused by structural fatigue damage, directly impacting the economic efficiency and reliability of wind farm operation.

[0024] Currently, simplified methods such as physical mechanism analysis, basic historical data statistics, or empirical assumptions are commonly used to predict the load data of wind turbine structures in complex environments. However, these methods are difficult to adapt to the dynamic interaction characteristics of multiple factors in complex environments, resulting in low prediction accuracy.

[0025] For example, in the operation of wind farms in the arid Northwest region, wind turbine structures are exposed to extreme temperature differences, strong wind turbulence, and high concentrations of dust for extended periods. Existing prediction methods only process temperature variation ranges or wind speed ranges independently, neglecting the coupling effect between particulate matter concentration ranges and temperature field modules. Consequently, under dust impact conditions, the relationship between the environmental parameter characteristic ranges and the response of the structural mechanical field modules is incorrectly represented, leading to a systematic deviation between the mechanical response data and actual measured values. This results in the predicted load data failing to accurately reflect the structural state under the target operating conditions.

[0026] If the above problems are not resolved, the systematic deviation in wind turbine structural load prediction will persist, insufficient structural design strength will be induced, the material fatigue process will be accelerated, the probability of structural failure will be increased, and a potential threat will be posed to the safe and stable operation of wind farms.

[0027] Based on this, this application provides a structural load prediction method. First, the geometric parameters, material property parameters, and environmental parameter characteristic ranges of the wind turbine structure to be predicted are obtained. Then, a multi-physics coupling model including a temperature field module, a structural mechanical field module, an airflow field module, and a particle impact field module is constructed based on the above parameters. The physical field modules exchange data bidirectionally through a coupling interface. Then, the environmental parameter values ​​under the target working condition are input into the multi-physics coupling model to obtain mechanical response data, and finally, the predicted load data is determined. Compared to conventional methods, the multi-physics coupling model constructed in this application, through bidirectional data exchange between various physics modules, can accurately reproduce the real dynamic interaction process between temperature, airflow, particle impact, and structural mechanics of the wind turbine structure in complex natural environments. For example, changes in temperature distribution in the temperature field can be transmitted to the structural mechanics field through the coupling interface to correct the relevant parameters of the structural mechanics field; changes in wind speed in the airflow field can be transmitted to the particle impact field to adjust the impact velocity and trajectory of particles, and then fed back to the structural mechanics field to update the stress state of the structure. This solves the problem that existing technologies cannot accurately depict the interaction of multiple fields, thereby improving the accuracy of load data prediction for wind turbine structures. It can provide a reliable basis for the design strength verification, service life assessment, and operation and maintenance strategy formulation of wind turbine structures, effectively avoiding the risk of over-design cost waste or structural fatigue damage caused by under-design due to prediction deviations, and ensuring the safe and efficient operation of wind turbine structures in wind farms.

[0028] The subject executing the structural load prediction method of this application can be an electronic device with data processing, network communication and program execution functions, or a control system, control circuit, etc. that can realize the above functions. This embodiment does not specifically limit it.

[0029] The following description uses an electronic device as the execution subject to illustrate the various embodiments.

[0030] This application proposes a structural load prediction method according to a first embodiment. Please refer to [link / reference]. Figure 1 The structural load prediction method may include steps S10 to S50: Step S10: Obtain the geometric parameters, material property parameters, and environmental parameter characteristic range of the environment in which the wind turbine structure to be predicted is located; the environmental parameter characteristic range includes the temperature change range, wind speed range, particulate matter concentration range, and / or particle size distribution range. Predicting the load data of a wind turbine structure is the technical process of predicting the forces, stresses, and other related mechanical effects acting on the wind turbine structure. The wind turbine structure to be predicted refers to the structural part of a specific wind turbine generator set that requires load prediction, such as the turbine blades, tower, or hub; this embodiment does not specifically limit this. Geometric parameters refer to the dimensions, shape, cross-sectional characteristics, and other spatial configuration information of the wind turbine structure to be predicted. Material property parameters refer to the inherent physical and mechanical properties of the materials constituting the wind turbine structure to be predicted, such as elastic modulus, Poisson's ratio, density, thermal conductivity, specific heat capacity, and coefficient of thermal expansion. These parameters reflect the material's response behavior under different conditions. The environmental parameter characteristic range refers to the expected range of changes in external environmental conditions that the wind turbine structure to be predicted may experience during its service life; this range is used to define the boundary conditions for model simulation.

[0031] Geometric parameters can be obtained by consulting wind turbine design drawings or conducting on-site measurements. For example, data such as the length of the wind turbine blades, chord length distribution, and airfoil cross-sectional shape can be manually entered. Material property parameters can be obtained based on datasheets provided by material suppliers or actual measurement data, such as elastic modulus and yield strength measured at room temperature. The characteristic range of environmental parameters can be determined based on historical meteorological data statistics of the wind turbine installation site. For example, by reviewing meteorological records from the past ten years, the highest and lowest temperatures, maximum wind speeds, and frequency of sandstorms in the area can be determined.

[0032] In other feasible implementations, the step of obtaining the material property parameters of the wind turbine structure to be predicted may also include steps S11-S12: Step S11: Obtain material property test data of the material used in the wind turbine structure to be predicted at multiple temperature gradient points, where each temperature gradient point covers the temperature change range in the characteristic range of environmental parameters. The material property test data may include, but is not limited to, elastic modulus, Poisson's ratio, yield strength, tensile strength, coefficient of thermal expansion, and thermal conductivity. When obtaining material property test data of the material used in the wind turbine structure to be predicted at multiple temperature gradient points, the mechanical, thermal, and other performance parameters of the material at different temperatures can be obtained through experimental measurement or by consulting a reliable material database. This embodiment does not impose specific limitations on this.

[0033] When selecting multiple temperature gradient points, one can choose discrete temperature points that are uniformly distributed within the temperature variation range of the environmental parameter characteristic range, or one can choose temperature points that are densely sampled based on the actual environmental temperature distribution characteristics. This ensures that the acquired data can comprehensively reflect the material's performance changes at different temperatures. This embodiment does not impose specific limitations on this approach. Each temperature gradient point covers the temperature variation range within the environmental parameter characteristic range, aiming to ensure that the collected material property data can cover all temperature conditions that the wind turbine structure may encounter during actual operation, thereby providing accurate input for subsequent predictions.

[0034] Step S12: Based on the material property test data, obtain a continuous function of material property change with temperature through nonlinear fitting; Nonlinear fitting can be achieved using various algorithms, such as least squares, Levenberg-Marquardt, and Gauss-Newton methods, or machine learning methods like neural networks. This embodiment does not impose any specific limitations on these methods. Nonlinear fitting can more accurately capture the complex nonlinear relationships between material properties and temperature.

[0035] Step S13: The parameterized data of the material properties represented by the continuous function as a function of temperature are used as material property parameters.

[0036] In this approach, parameterized data representing the material properties as a function of a continuous function as a function of temperature are used as material property parameters. Essentially, this involves providing a series of discrete values ​​(forming a lookup table) calculated from the continuous function at a specific temperature point to the multiphysics coupling model as input. This parameterized data format allows the multiphysics coupling model to dynamically obtain accurate material properties based on real-time temperature values ​​during calculations, thereby achieving precise simulation of material properties changing with temperature.

[0037] In this embodiment, material property test data of the materials used in the wind turbine structure to be predicted are obtained at multiple temperature gradient points. Based on these data, a continuous function of material properties changing with temperature is obtained through nonlinear fitting. Finally, the parameterized data represented by this continuous function is used as the material property parameters. This series of steps allows the dynamic nonlinear characteristics of material properties changing with temperature to be fully considered when constructing a multiphysics coupling model. In traditional methods, material property parameters are often based on fixed temperature points or simplified models, which ignore the actual impact of temperature changes on material properties, leading to deviations between model predictions and actual conditions. Therefore, this embodiment, by introducing test data at temperature gradient points and nonlinear fitting, can more accurately characterize the true performance of materials at different temperatures, thus providing a more accurate input for the multiphysics coupling model. This enables the multiphysics coupling model to more realistically reflect the mechanical response of the wind turbine structure in complex environments when simulating the interaction between temperature fields, structural mechanical fields, airflow fields, and particle impact fields, thereby improving the accuracy of predicted load data.

[0038] Step S20: Based on the geometric parameters, material property parameters, and environmental parameter characteristic ranges, a multiphysics coupling model is constructed. The multiphysics coupling model includes a temperature field module, a structural mechanics field module, an airflow field module, and a particle impact field module. The physical field modules exchange data bidirectionally through a coupling interface to simulate the interaction between the physical fields. The temperature field module simulates the temperature distribution and heat transfer processes inside and outside the structure. The structural mechanics field module analyzes the mechanical responses of the structure under various loads, including stress, strain, displacement, and deformation. The airflow field module simulates the airflow characteristics around the wind turbine structure, including wind speed, wind pressure distribution, and turbulence effects. The particle impact field module simulates the impact of particulate matter (such as dust and hail) on the wind turbine structure and the resulting mechanical effects. The coupling interface refers to the connection mechanism for data exchange and information transmission between different physics field modules in a multiphysics coupling model. Bidirectional data exchange means that different physics field modules can exchange data with each other through the coupling interface, and this transmission is bidirectional, meaning that the output of one module can be used as the input of another module, and vice versa, thereby realizing the mutual influence and feedback between the various physics fields. The target operating condition refers to the specific operating conditions or environmental state set when performing load prediction, such as the combination of wind speed, temperature, and particulate matter concentration at a specific moment.

[0039] In one feasible implementation, step S20 may include steps S21 to S23: Step S21: Based on the geometric parameters, material property parameters, and environmental parameter characteristic ranges, construct the basic control functions for the temperature field module, structural mechanics field module, airflow field module, and particle impact field module, respectively. The fundamental control functions for constructing the temperature field module, structural mechanics field module, airflow field module, and particle impact field module refer to establishing a separate mathematical model or set of equations for each physical field module. These models or sets of equations can describe the behavior of the physical field under given conditions. These fundamental control functions are the core of the multiphysics coupling model. They are based on physical laws and customized in combination with the geometric parameters, material properties, and environmental parameter ranges of the wind turbine structure to be predicted. For example, they can be represented by partial differential equations or ordinary differential equations, such as the heat conduction equation, the elasticity equation, and the Navier-Stokes equation. In practical applications, these control functions can be discretized using numerical methods (such as the finite element method, finite volume method, or finite difference method) and transformed into a computable set of algebraic equations. In addition, surrogate models can be constructed as fundamental control functions based on experimental data or high-precision simulation data using data-driven methods (such as machine learning models) to improve computational efficiency. This embodiment does not impose specific limitations on this.

[0040] When constructing the basic control functions for the temperature field module, structural mechanics field module, airflow field module, and particle impact field module based on geometric parameters, material property parameters, and environmental parameter characteristic ranges, the geometric boundary coefficients, material property coefficients, and environmental load coefficients of the basic control functions for each physical field module can be determined based on the geometric parameters, material property parameters, and environmental parameter characteristic ranges, respectively. These coefficients are then substituted into the general expression of the corresponding control function for each physical field module to obtain the basic control functions for the temperature field module, structural mechanics field module, airflow field module, and particle impact field module, respectively.

[0041] Among them, geometric boundary coefficients are parameters used to describe the structural geometric boundary conditions in the control functions of each physics field module. These parameters transform the actual geometry and boundary constraints of the wind turbine structure into specific values ​​in the mathematical model. For example, in the structural mechanics field module, it can be the definition of a fixed boundary, a free boundary, or a supported boundary; in the airflow field module, it can be the shape and location of the inlet, outlet, or wall boundary; and in the temperature field module, it can be the area of ​​the heat transfer surface, shape factor, etc.

[0042] Material property coefficients are parameters used to describe the material properties in the control functions of each physics field module. These parameters translate the physical and mechanical properties of the material into specific values ​​in the mathematical model. For example, in the structural mechanics field module, these can be elastic modulus, Poisson's ratio, etc.; in the temperature field module, they can be thermal conductivity, specific heat capacity, etc.; and in the particle impact field module, they can be impact resistance parameters such as hardness and toughness of the material.

[0043] The environmental load factor is a parameter used to describe the external environmental load in the control function of each physical field module. These parameters transform the environmental impact on the wind turbine structure into specific values ​​in the mathematical model. For example, in the temperature field module, it can be the convective heat transfer coefficient, the radiative heat transfer coefficient, etc.; in the airflow field module, it can be the wind pressure coefficient, the drag coefficient, etc.; and in the particle impact field module, it can be the particle impact force coefficient, the wear coefficient, etc.

[0044] The general expression of the control function refers to the mathematical equations describing the fundamental physical laws of each physical field, which form the theoretical foundation of the physical field modules. For example, the temperature field module can be based on the Fourier heat conduction equation or the energy conservation equation; the structural mechanics field module can be based on the elasticity equations (such as the Navier-Cauchy equation) or the structural dynamics equation; the airflow field module can be based on the Navier-Stokes equation or the continuity equation; and the particle impact field module can be based on the particle motion equation or the impact dynamics equation. These expressions are usually in the form of partial differential equations or integral equations. "Substitution" refers to embedding the determined geometric boundary coefficients, material property coefficients, and environmental load coefficients as specific parameters or boundary conditions into the general expression of the control function corresponding to each physical field module, thereby transforming the general equation into a specific mathematical model for a specific wind turbine structure and environmental conditions. This process can be completed through the preprocessor of numerical simulation software, such as setting material properties, boundary conditions, and load parameters in finite element analysis or computational fluid dynamics software. The basic control function refers to the customized mathematical model describing the behavior of each physical field for a specific wind turbine structure and environmental conditions to be predicted after the coefficients have been substituted.

[0045] Understandably, based on the geometric parameters, material property parameters, and environmental parameter ranges of the wind turbine structure to be predicted, the geometric boundary coefficients, material property coefficients, and environmental load coefficients required for the basic control functions of each physical field module are systematically determined. This process ensures that the physical meaning of the model parameters is clear and closely related to the actual characteristics of the wind turbine structure and the complex environmental conditions it faces. For example, geometric parameters directly affect the setting of geometric boundary coefficients, ensuring that the model accurately captures the shape and size of the structure; material property parameters determine material property coefficients, enabling the model to realistically reflect the material's response under different physical fields; and the environmental parameter range provides a basis for the environmental load coefficient, enabling the model to simulate the impact of actual environmental loads. Subsequently, these precisely determined coefficients are substituted into the general expression of the control function corresponding to each physical field module. This substitution process transforms abstract physical laws into specific mathematical models for specific wind turbine structures and environmental conditions, thereby obtaining the basic control functions for the temperature field module, structural mechanics field module, airflow field module, and particle impact field module, respectively. These customized basic control functions, compared to general or simplified models, can more accurately describe the temperature distribution, stress and strain, airflow dynamics, and particle impact effects of the wind turbine structure in complex environments, thereby improving the prediction accuracy and reliability of the subsequent multiphysics coupling model.

[0046] Step S22: Establish a first bidirectional coupling interface, a second bidirectional coupling interface, a third bidirectional coupling interface, a fourth bidirectional coupling interface, and a fifth bidirectional coupling interface between the temperature field module and the structural mechanics field module, between the temperature field module and the airflow field module, between the airflow field module and the structural mechanics field module, between the airflow field module and the particle impact field module, and between the particle impact field module and the structural mechanics field module, respectively. The establishment of the first, second, third, fourth, and fifth bidirectional coupling interfaces refers to the establishment of mechanisms for data exchange and mutual influence between different physics modules. The bidirectional coupling interface allows the output of one physics field to serve as the input of another, while the output of the other physics field can also influence the first, thus simulating the interactions of various physical phenomena in the real world. For example, the first bidirectional coupling interface can realize the transmission of structural thermal stress and deformation caused by temperature changes to the structural mechanical field, as well as the feedback of the influence of structural deformation on the heat transfer path or convective heat transfer in the temperature field. The second bidirectional coupling interface can realize the influence of airflow on convective heat transfer on the structural surface, and the influence of structural surface temperature on the airflow boundary layer. The third bidirectional coupling interface can realize the transmission of aerodynamic loads (such as wind pressure and shear force) generated by airflow to the structural mechanical field, and the influence of structural deformation (such as vibration and flutter) on the airflow field. The fourth bidirectional coupling interface can realize the driving effect of airflow on particle trajectories, and the feedback influence of high-concentration particles on the flow state of the airflow field. The fifth bidirectional coupling interface enables the transfer of impact loads generated by particle impacts to the structural mechanical field, as well as the feedback of particle impact behavior to surface wear or deformation. These interfaces can be implemented through explicit coupling, implicit coupling, or iterative coupling to ensure accurate and timely bidirectional exchange of data between various physical fields.

[0047] Step S23: Based on the basic control functions of the temperature field module, structural mechanics field module, airflow field module, and particle impact field module, as well as the first bidirectional coupling interface, the second bidirectional coupling interface, the third bidirectional coupling interface, the fourth bidirectional coupling interface, and the fifth bidirectional coupling interface, a multi-physics coupling model is formed.

[0048] In this embodiment, basic control functions are constructed for the temperature field module, structural mechanics field module, airflow field module, and particle impact field module based on the geometric parameters, material properties, and environmental parameters of the wind turbine structure to be predicted. This lays a solid physical foundation for subsequent coupled simulations, ensuring that each physical field module can accurately describe its own physical behavior. Based on this, key bidirectional coupling interfaces are established between the temperature field module and the structural mechanics field module, between the temperature field module and the airflow field module, between the airflow field module and the structural mechanics field module, between the airflow field module and the particle impact field module, and between the particle impact field module and the structural mechanics field module, respectively. This enables crucial and specific bidirectional data exchange between the various physical fields. This refined coupling mechanism allows the model to comprehensively capture the dynamic response of the wind turbine structure in complex environments, such as the interaction of multiple factors including temperature changes, wind loads, and particle impacts. For example, temperature changes not only directly affect material properties and structural stress, but also influence convective heat transfer through the airflow field, thus affecting the structural temperature distribution. Simultaneously, wind loads generated by the airflow field cause structural deformation, which in turn alters the airflow field, creating aeroelastic effects. Particle impacts not only directly generate local loads, but their impact process is also influenced by the airflow field, and structural deformation can change the impact angle and energy. By integrating these fundamental control functions and bidirectional coupling interfaces, a collaborative, highly integrated multiphysics coupling model is formed. This model can more accurately simulate the interactions between various physical fields, overcoming the limitations of insufficient physical field interactions in traditional models. It significantly improves the simulation accuracy and reliability of the model's response to the mechanical structure of wind turbines, thereby enhancing prediction accuracy and reliability.

[0049] Step S30: Obtain the environmental parameter values ​​of the wind turbine structure to be predicted under the target operating conditions; Environmental parameter values ​​refer to the specific environmental conditions that are actually measured or set under the target operating conditions, such as the actual temperature, wind speed, and particulate matter concentration at a certain moment.

[0050] When obtaining the environmental parameter values ​​of the wind turbine structure to be predicted under the target operating conditions, the current wind speed, ambient temperature, and particulate matter concentration in the air can be monitored in real time by sensors installed on the wind turbine, and these monitoring data can be used as the environmental parameter values ​​under the target operating conditions. Alternatively, a set of expected environmental parameter values ​​can be set based on short-term weather forecasts or specific operating plans; this embodiment does not specifically limit this.

[0051] Step S40: Input the environmental parameter values ​​into the multiphysics coupling model to obtain the mechanical response data of the wind turbine structure to be predicted under the target operating conditions. Mechanical response data refers to the physical quantities such as stress, strain, displacement, vibration frequency, and vibration acceleration of the internal structure and surface of the wind turbine structure under target operating conditions, calculated by a multiphysics coupling model. These may include, but are not limited to, stress distribution data, strain distribution data, displacement distribution data, vibration frequency, and vibration acceleration of the wind turbine structure; this embodiment does not specifically limit these quantities.

[0052] Among these, stress distribution data for the wind turbine structure refers to the internal force per unit area borne by each point within the wind turbine structure, reflecting the stress state of the material and potential failure risk; strain distribution data refers to the relative deformation of each point within the wind turbine structure under stress, reflecting the degree of material deformation; displacement distribution data refers to the movement of each point in the wind turbine structure relative to its initial position, reflecting the overall deformation and stability of the structure; vibration frequency refers to the natural frequency or response frequency exhibited by the wind turbine structure under excited vibration, which is closely related to the dynamic characteristics and fatigue life of the structure; vibration acceleration refers to the instantaneous acceleration of each point in the wind turbine structure during vibration, reflecting the intensity and impact effect of the vibration. These data can typically be obtained through numerical simulation (such as finite element analysis) or actual sensor monitoring (such as strain gauges, accelerometers, and displacement sensors).

[0053] Step S50: Determine the predicted load data of the wind turbine structure to be predicted based on the mechanical response data.

[0054] Predicted load data refers to quantitative data obtained by converting or calculating mechanical response data through specific methods, used to characterize the equivalent load or equivalent damage borne by the wind turbine structure under target operating conditions.

[0055] When determining the predicted load data for the wind turbine structure based on the mechanical response data, extreme value data can be extracted from the mechanical response data. These extreme value data include maximum stress, maximum strain, maximum displacement, maximum vibration frequency, and maximum vibration acceleration. Based on a preset mapping relationship between the extreme value data of the mechanical response and the wind turbine structure load data, the extreme value data undergoes a load equivalence transformation to obtain the predicted load data for the wind turbine structure. Alternatively, the extracted extreme value data can be directly used as the predicted load data for the wind turbine structure; this embodiment does not specifically limit this approach.

[0056] The mapping relationship between the extreme values ​​of the mechanical response and the structural load data of the wind turbine can be recorded using relational tables, relational functions, etc., and this embodiment does not impose specific limitations on this.

[0057] Understandably, by extracting extreme values ​​from the mechanical response data, such as maximum stress, maximum strain, maximum displacement, maximum vibration frequency, and maximum vibration acceleration, it is possible to focus on key load points and effectively reduce the amount of data, significantly improving the efficiency of subsequent processing. Then, based on the preset mapping relationship between the extreme mechanical response data and the wind turbine structural load data, these extreme values ​​are transformed into load data with engineering significance, ensuring the scientific nature and accuracy of the conversion process. This structured data processing and conversion process makes it possible to efficiently and accurately obtain the wind turbine structural load from complex physical simulation results, greatly improving the practicality and reliability of load forecasting.

[0058] Based on the above, this embodiment provides a structural load prediction method. First, the geometric parameters, material property parameters, and environmental parameter characteristic ranges of the wind turbine structure to be predicted are obtained. Then, a multiphysics coupling model including a temperature field module, a structural mechanical field module, an airflow field module, and a particle impact field module is constructed based on the above parameters. The physical field modules exchange data bidirectionally through a coupling interface. After that, the environmental parameter values ​​under the target operating condition are input into the multiphysics coupling model to obtain mechanical response data, and finally the predicted load data is determined. Compared to conventional methods, the multi-physics coupling model constructed in this embodiment, through bidirectional data exchange between various physics modules, can accurately reproduce the real dynamic interaction process between temperature, airflow, particle impact, and structural mechanics in a complex natural environment. For example, changes in temperature distribution in the temperature field can be transmitted to the structural mechanics field through the coupling interface to correct the relevant parameters of the structural mechanics field; changes in wind speed in the airflow field can be transmitted to the particle impact field to adjust the impact velocity and trajectory of particles, and then fed back to the structural mechanics field to update the stress state of the structure. This solves the problem that existing technologies cannot accurately depict the interaction of multiple fields, thereby improving the accuracy of load data prediction for wind turbine structures. It can provide a reliable basis for the design strength verification, service life assessment, and operation and maintenance strategy formulation of wind turbine structures, effectively avoiding the risk of over-design cost waste or structural fatigue damage caused by under-design due to prediction deviations, and ensuring the safe and efficient operation of wind turbine structures in wind farms.

[0059] Based on the first embodiment described above, a second embodiment of the structural load prediction method of this application is proposed. For the second embodiment, please refer to... Figure 2 After step S50, the structural load prediction method may further include steps S60 to S80: Step S60: Obtain the actual load monitoring data of the wind turbine structure to be predicted; Actual load monitoring data refers to the data on physical quantities such as stress, strain, and vibration of the wind turbine structure under actual operating conditions, collected in real time or periodically by installing sensors on the wind turbine structure. This data can come from sources such as strain gauges, accelerometers, displacement sensors, or fiber optic sensors installed at the root of the wind turbine blades, the tower, or the nacelle, and is recorded and stored through a data acquisition system.

[0060] Step S70: By comparing the actual load monitoring data with the predicted load data, the prediction error value of the load data is determined; When determining the prediction error of load data by comparing actual load monitoring data with predicted load data, the root mean square error, mean absolute error, maximum absolute error, or percentage error between the actual load monitoring data and the predicted load data can be used as the prediction error value of the load data.

[0061] Step S80: If the prediction error value is greater than the preset error threshold, adjust the coupling parameters and / or the coefficients of the basic control function associated with the bidirectional coupling interface in the multiphysics coupling model to iteratively optimize the multiphysics coupling model until the determined prediction error value is less than or equal to the prediction error value.

[0062] The preset error threshold is an upper limit set based on actual application requirements and acceptable prediction accuracy. Adjusting the coefficients of coupling parameters and / or basic control functions aims to correct the description of physical laws within the model or the interaction strength between various physical fields. For example, these parameters can be systematically adjusted using algorithms such as sensitivity analysis, gradient descent, genetic algorithms, or Bayesian optimization to make the model's output closer to actual monitoring data. Iterative optimization refers to repeatedly performing the process of prediction, error calculation, and parameter adjustment until the prediction error value meets the preset requirements, thereby achieving continuous improvement and accuracy enhancement of the model.

[0063] When adjusting the coefficients of the coupling parameters and / or basic control functions associated with the bidirectional coupling interface in a multiphysics coupling model, error distribution data can be generated based on the deviation between the predicted load data and the actual load monitoring data. The first contribution weight of each physical field module in the multiphysics coupling model to the error distribution data can be determined through an error tracing algorithm. The coefficients of the basic control function of the physical field module with the largest first contribution weight in the multiphysics coupling model can then be adjusted. And / or, through an error tracing algorithm, determine the second contribution weight of each bidirectional coupling interface in the multiphysics coupling model to the error distribution data; adjust the coupling parameters associated with the bidirectional coupling interface with the largest second contribution weight in the multiphysics coupling model.

[0064] This process generates error distribution data based on the deviation between predicted load data and actual load monitoring data, aiming to quantify and visualize the difference between the predicted results and the actual situation. By determining the differences between the predicted load data and the actual load monitoring data at different time points and different spatial locations (e.g., different cross-sections of wind turbine blades, different heights of the tower), a series of discrete error values ​​can be obtained. These error values ​​can be further processed, for example, through interpolation and smoothing, to generate continuous error distribution data, such as error heatmaps, error time series graphs, or error histograms, thereby intuitively showing the magnitude, direction, and distribution characteristics of the errors on the wind turbine structure.

[0065] Error source attribution algorithms are techniques used to identify the contribution of each component in a multiphysics coupled model to the overall prediction error. The algorithm's role is to intelligently analyze and quantify the relative impact of each physical field module (such as temperature field module, structural mechanics field module, airflow field module, and particle impact field module) and / or each bidirectional coupling interface on these errors when there are deviations between the model's prediction results and actual monitoring data. One approach to analyzing and quantifying the relative impact of each physical field module on these errors is to employ sensitivity analysis methods. For example, by systematically perturbing the key input parameters or internal state variables of each physical field module and observing how these perturbations affect the final error distribution data, the greater the impact, the higher the contribution weight of that module (e.g., variance decomposition methods such as the Sobol index can be used to quantify the contribution of the input uncertainty of each module to the output error variance). Another approach is based on machine learning. For example, a supervised learning model can be built, using the internal outputs or key parameters of each physical field module as features and the error distribution data as the target variable for training. By analyzing the importance of the features learned by the model, the contribution weight of each physical field module to the error can be indirectly inferred (e.g., decision tree or random forest models can provide feature importance scores, thereby indicating which physical field modules have the greatest impact on the prediction error).

[0066] When adjusting the coefficients of the fundamental control function of the physics module with the largest contribution weight in a multiphysics coupling model, gradient descent or Newton's method can be used. Based on the gradient information of the coefficients of the fundamental control function of this physics module using error distribution data, the coefficients can be iteratively adjusted to minimize the prediction error. Alternatively, under expert guidance, a small-scale parameter scan or empirical adjustment can be performed on the coefficients of the physics module with the largest weight that are highly correlated with the error type. This embodiment does not impose specific limitations on this approach.

[0067] Besides errors within the physics modules, data exchange between modules (i.e., bidirectional coupling interfaces) can also introduce or propagate errors. Therefore, error sourcing algorithms can be used to determine the second contribution weight of each bidirectional coupling interface in a multiphysics coupling model to the error distribution data. Specifically, one approach is to perform interface data perturbation analysis. For example, at each bidirectional coupling interface, a systematic, small perturbation or simulation error is introduced into the transmitted data. This perturbation is then observed to propagate through the coupling mechanism and affect the final error distribution data; the greater the impact, the higher the second contribution weight of that interface. Another approach is to analyze the data consistency and transmission efficiency of the bidirectional coupling interfaces. For example, by evaluating the accuracy of data interpolation, mapping, or boundary condition processing at the bidirectional coupling interfaces, the potential errors introduced can be quantified, thereby determining the contribution weight of the bidirectional coupling interfaces to the error.

[0068] When adjusting the coupling parameters associated with the bidirectional coupling interface that has the largest second contribution weight in a multiphysics coupling model, a small-scale parameter space search or adaptive adjustment based on error feedback can be performed on the coupling parameters associated with the bidirectional coupling interface to find the parameter combination that minimizes the error. Alternatively, the associated coupling parameters can be modified according to the continuity requirements of the bidirectional coupling interface or the convergence conditions of the numerical calculation to ensure the accuracy and stability of data exchange.

[0069] Understandably, generating error distribution data based on the deviation between predicted load data and actual load monitoring data allows for a comprehensive and detailed understanding of the error characteristics, laying the foundation for subsequent precise corrections. Furthermore, introducing an error source tracing algorithm can intelligently identify the physical field modules and bidirectional coupling interfaces that contribute the most to the overall error, thereby enabling targeted adjustments to model parameters. This weight-based adjustment mechanism avoids the resource waste and inefficiency of indiscriminately modifying all parameters, significantly improving the efficiency and convergence speed of model optimization.

[0070] Based on the above, in this embodiment, after predicting the load data of the wind turbine structure under the target operating condition, the actual load monitoring data of the wind turbine structure during actual operation is further acquired. Then, by comparing the actual load monitoring data with the predicted load data, the prediction error value of the load data is determined. If the prediction error value is greater than a preset error threshold, it indicates that the current multiphysics coupling model has certain deficiencies and cannot accurately capture the true response of the wind turbine structure in complex environments. At this time, the coupling parameters associated with the bidirectional coupling interface and / or the coefficients of the basic control function in the multiphysics coupling model can be adjusted to iteratively optimize the multiphysics coupling model, so that the model can better reflect the actual physical processes and interactions, thereby generating more accurate load data in the next prediction, until the prediction error value is reduced to less than or equal to the prediction error value. This closed-loop optimization process based on actual feedback enables the multiphysics coupling model to continuously learn and adapt to the complex and variable environment in which the wind turbine structure is located, significantly improving the accuracy and robustness of load prediction. This not only provides a more reliable load input for the refined design of wind turbine structures, but also provides a high-precision predictive basis for health monitoring, fault diagnosis and maintenance strategy formulation during wind turbine operation, thereby effectively reducing over-design costs, avoiding the risk of structural fatigue damage, and ensuring the safe and efficient operation of wind farms.

[0071] This application also provides a structural load prediction device; please refer to... Figure 3 The structural load prediction device includes: Data acquisition module 10 is used to acquire the geometric parameters, material property parameters, and environmental parameter characteristic range of the environment in which the wind turbine structure to be predicted is located; the environmental parameter characteristic range includes temperature change range, wind speed range, particulate matter concentration range and / or particle size distribution range; The model building module 20 is used to construct a multi-physics coupling model based on geometric parameters, material property parameters, and environmental parameter characteristic ranges. The multi-physics coupling model includes a temperature field module, a structural mechanics field module, an airflow field module, and a particle impact field module. The various physics field modules exchange data bidirectionally through a coupling interface to simulate the interaction between the various physics fields. The data acquisition module 30 is also used to acquire the environmental parameter values ​​of the wind turbine structure to be predicted under the target operating conditions; The load prediction module 40 is used to input environmental parameter values ​​into the multiphysics coupling model to obtain the mechanical response data of the wind turbine structure to be predicted under the target operating conditions; and to determine the predicted load data of the wind turbine structure to be predicted based on the mechanical response data.

[0072] In one embodiment, the model building module 20 is further configured to: Based on the geometric parameters, material property parameters, and environmental parameter characteristic ranges, the basic control functions of the temperature field module, structural mechanics field module, airflow field module, and particle impact field module are constructed respectively. A first bidirectional coupling interface, a second bidirectional coupling interface, a third bidirectional coupling interface, a fourth bidirectional coupling interface, and a fifth bidirectional coupling interface are established between the temperature field module and the structural mechanics field module, between the temperature field module and the airflow field module, between the airflow field module and the structural mechanics field module, between the airflow field module and the particle impact field module, and between the particle impact field module and the structural mechanics field module, respectively. Based on the fundamental control functions of the temperature field module, structural mechanics field module, airflow field module, and particle impact field module, as well as the first bidirectional coupling interface, the second bidirectional coupling interface, the third bidirectional coupling interface, the fourth bidirectional coupling interface, and the fifth bidirectional coupling interface, a multiphysics coupling model is formed.

[0073] In one embodiment, the model building module 20 is further configured to: Based on the characteristic ranges of geometric parameters, material property parameters, and environmental parameters, the geometric boundary coefficients, material property coefficients, and environmental load coefficients of the basic control functions of each physical field module are determined. Substitute the geometric boundary coefficients, material property coefficients, and environmental load coefficients of each physical field module into the general expression of the control function corresponding to each physical field module to obtain the basic control functions of the temperature field module, structural mechanics field module, airflow field module, and particle impact field module, respectively.

[0074] In one embodiment, the mechanical response data includes stress distribution data, strain distribution data, displacement distribution data, vibration frequency, and vibration acceleration of the wind turbine structure; the load prediction module 40 is also used for: Extract extreme value data from the mechanical response data, including maximum stress, maximum strain, maximum displacement, maximum vibration frequency, and maximum vibration acceleration; Based on the pre-defined mapping relationship between the extreme values ​​of mechanical response and the load data of the wind turbine structure, the extreme values ​​are converted into load equivalents to obtain the predicted load data of the wind turbine structure to be predicted.

[0075] In one embodiment, the data acquisition module 10 is further configured to: Acquire material property test data of the materials used in the wind turbine structure to be predicted at multiple temperature gradient points, with each temperature gradient point covering the temperature change range in the characteristic range of environmental parameters. Based on material property test data, a continuous function of material properties changing with temperature is obtained through nonlinear fitting; The parameterized data of material properties characterized by continuous functions as a function of temperature are used as material property parameters.

[0076] In one embodiment, the structural load prediction device may further include a model optimization module 50, used for: Obtain actual load monitoring data for the wind turbine structure to be predicted; By comparing actual load monitoring data with predicted load data, the prediction error value of the load data can be determined. If the prediction error value is greater than the preset error threshold, the coupling parameters and / or coefficients of the basic control function associated with the bidirectional coupling interface in the multiphysics coupling model are adjusted to iteratively optimize the multiphysics coupling model until the determined prediction error value is less than or equal to the prediction error value.

[0077] In one embodiment, the model optimization module 50 is further configured to: Error distribution data is generated based on the deviation between predicted load data and actual load monitoring data. The first contribution weight of each physics module in the multiphysics coupling model to the error distribution data is determined by the error source tracing algorithm. Adjust the coefficients of the basic control function of the physics module with the largest contribution weight in the multiphysics coupling model; And / or, through an error tracing algorithm, determine the second contribution weight of each bidirectional coupling interface in the multiphysics coupling model to the error distribution data; Adjust the coupling parameters associated with the bidirectional coupling interface that has the largest second contribution weight in the multiphysics coupling model.

[0078] The structural load prediction device provided in this application, employing the structural load prediction method described in the above embodiments, can improve the accuracy of load data prediction for wind turbine structures. Compared with the prior art, the beneficial effects of the structural load prediction device provided in this application are the same as those of the structural load prediction method described in the above embodiments, and other technical features in this structural load prediction device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0079] This application also provides an electronic device, which may include: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the structural load prediction method described above.

[0080] The following is for reference. Figure 4 It shows a schematic diagram of the structure of an electronic device suitable for implementing the embodiments of this application. Figure 4 The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0081] like Figure 4As shown, the electronic device may include a processing unit 101 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in read-only memory 102 or a program loaded from storage device 103 into random access memory 104. Random access memory 104 also stores various programs and data required for the operation of the electronic device. The processing unit 101, read-only memory 102, and random access memory 104 are interconnected via bus 105. Input / output interface 106 is also connected to bus 105. Typically, the following systems can be connected to input / output interface 106: input devices 107 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 108 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 103 including, for example, magnetic tape, hard disks, etc.; and communication devices 109. Communication device 109 allows the electronic device to communicate wirelessly or wiredly with other devices to exchange data. Although the diagrams show electronic devices with various systems, it should be understood that it is not required to implement or have all of the systems shown. More or fewer systems may be implemented alternatively.

[0082] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure 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 103, or installed from read-only memory 102. When the computer program is executed by processing device 101, it performs the functions defined in the methods of the embodiments of this application.

[0083] The electronic device provided in this application, employing the structural load prediction method described in the above embodiments, can improve the accuracy of load data prediction for wind turbine structures. Compared with the prior art, the beneficial effects of the electronic device provided in this application are the same as those of the structural load prediction method described in the above embodiments, and other technical features of the electronic device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0084] It should be understood that various parts of the embodiments of 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.

[0085] The above description is merely a specific implementation of the embodiments of this application, but the protection scope of the embodiments 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 protection scope of the embodiments of this application. Therefore, the protection scope of the embodiments of this application should be determined by the protection scope of the above claims.

[0086] This application also provides a computer-readable storage medium storing a computer program that can run on a processor. The computer program is used to execute the structural load prediction method described in the above embodiments.

[0087] The computer-readable storage medium provided in this application embodiment 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 with 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 fibers, 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, 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.

[0088] The aforementioned computer-readable storage medium may be included in an electronic device or may exist independently without being assembled into an electronic device.

[0089] The aforementioned computer-readable storage medium carries one or more programs. When these programs are executed by an electronic device, the electronic device causes the following to occur: acquire the geometric parameters, material property parameters, and environmental parameter characteristic ranges of the environment in which the wind turbine structure is located; the environmental parameter characteristic ranges include temperature variation range, wind speed range, particulate matter concentration range, and / or particle size distribution range; construct a multiphysics coupling model based on the geometric parameters, material property parameters, and environmental parameter characteristic ranges; the multiphysics coupling model includes a temperature field module, a structural mechanics field module, an airflow field module, and a particle impact field module, and the various physics field modules exchange data bidirectionally through a coupling interface to simulate the interaction between the various physics fields; acquire the environmental parameter values ​​of the wind turbine structure under the target operating condition; input the environmental parameter values ​​into the multiphysics coupling model to obtain the mechanical response data of the wind turbine structure under the target operating condition; and determine the predicted load data of the wind turbine structure based on the mechanical response data.

[0090] Computer program code for performing the operations of this disclosure 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).

[0091] 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.

[0092] 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.

[0093] The computer-readable storage medium provided in this application embodiment stores computer-readable program instructions for executing the above-described structural load prediction method, which can improve the accuracy of load data prediction for wind turbine structures. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application embodiment are the same as the beneficial effects of the structural load prediction method provided in the above embodiments, and will not be repeated here.

[0094] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the structural load prediction method described above.

[0095] The computer program product provided in this application can improve the accuracy of load data prediction for wind turbine structures. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the structural load prediction method provided in the above embodiments, and will not be repeated here.

[0096] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent scope of this application.

Claims

1. A structural load prediction method, characterized in that, The method includes: Obtain the geometric parameters, material property parameters, and environmental parameter characteristic ranges of the environment in which the wind turbine structure is located; the environmental parameter characteristic ranges include temperature variation range, wind speed range, particulate matter concentration range, and / or particle size distribution range. Based on the geometric parameters, material property parameters, and environmental parameter characteristic ranges, a multiphysics coupling model is constructed. The multiphysics coupling model includes a temperature field module, a structural mechanics field module, an airflow field module, and a particle impact field module. The physical field modules exchange data bidirectionally through a coupling interface to simulate the interaction between the physical fields. Obtain the environmental parameter values ​​of the wind turbine structure to be predicted under the target operating conditions; The environmental parameter values ​​are input into the multiphysics coupling model to obtain the mechanical response data of the wind turbine structure to be predicted under the target operating condition. Based on the mechanical response data, the predicted load data of the wind turbine structure to be predicted is determined.

2. The method as described in claim 1, characterized in that, The step of constructing a multiphysics coupling model based on the geometric parameters, the material property parameters, and the characteristic range of the environmental parameters includes: Based on the geometric parameters, the material property parameters, and the characteristic range of the environmental parameters, the basic control functions of the temperature field module, the structural mechanics field module, the airflow field module, and the particle impact field module are constructed respectively. A first bidirectional coupling interface, a second bidirectional coupling interface, a third bidirectional coupling interface, a fourth bidirectional coupling interface, and a fifth bidirectional coupling interface are respectively established between the temperature field module and the structural mechanics field module, between the temperature field module and the airflow field module, between the airflow field module and the structural mechanics field module, between the airflow field module and the particle impact field module, and between the particle impact field module and the structural mechanics field module. Based on the basic control functions of the temperature field module, the structural mechanics field module, the airflow field module, and the particle impact field module, as well as the first bidirectional coupling interface, the second bidirectional coupling interface, the third bidirectional coupling interface, the fourth bidirectional coupling interface, and the fifth bidirectional coupling interface, the multiphysics coupling model is integrated to form the multiphysics coupling model.

3. The method as described in claim 2, characterized in that, The step of constructing the basic control functions for the temperature field module, the structural mechanics field module, the airflow field module, and the particle impact field module based on the geometric parameters, the material property parameters, and the environmental parameter characteristic ranges includes: Based on the geometric parameters, material property parameters, and environmental parameter characteristic ranges, the geometric boundary coefficients, material property coefficients, and environmental load coefficients of the basic control functions of each physical field module are determined respectively. Substitute the geometric boundary coefficients, material property coefficients, and environmental load coefficients of each physical field module into the general expression of the control function corresponding to each physical field module to obtain the basic control functions of the temperature field module, structural mechanics field module, airflow field module, and particle impact field module, respectively.

4. The method as described in claim 1, characterized in that, The mechanical response data includes stress distribution data, strain distribution data, displacement distribution data, vibration frequency, and vibration acceleration of the wind turbine structure; The step of determining the predicted load data of the wind turbine structure to be predicted based on the mechanical response data includes: Extract the extreme value data from the mechanical response data, which includes the maximum stress, maximum strain, maximum displacement, maximum vibration frequency, and maximum vibration acceleration; Based on the preset mapping relationship between the extreme values ​​of mechanical response and the load data of the wind turbine structure, the extreme value data is subjected to load equivalent transformation to obtain the predicted load data of the wind turbine structure to be predicted.

5. The method as described in claim 1, characterized in that, The steps for obtaining the material property parameters of the wind turbine structure to be predicted include: Obtain material property test data of the material used in the wind turbine structure to be predicted at multiple temperature gradient points, where each temperature gradient point covers the temperature change range in the environmental parameter characteristic range. Based on the material property test data, a continuous function of material property change with temperature is obtained through nonlinear fitting; The parameterized data of the material properties characterized by the continuous function as a function of temperature are used as the material property parameters.

6. The method according to any one of claims 1 to 5, characterized in that, After the step of determining the predicted load data of the wind turbine structure to be predicted based on the mechanical response data, the method further includes: Obtain the actual load monitoring data of the wind turbine structure to be predicted; The prediction error value of the load data is determined by comparing the actual load monitoring data with the predicted load data. If the prediction error value is greater than the preset error threshold, the coupling parameters and / or coefficients of the basic control function associated with the bidirectional coupling interface in the multiphysics coupling model are adjusted to iteratively optimize the multiphysics coupling model until the determined prediction error value is less than or equal to the prediction error value.

7. The method as described in claim 6, characterized in that, The step of adjusting the coupling parameters and / or coefficients of the fundamental control function associated with the bidirectional coupling interface in the multiphysics coupling model includes: Based on the deviation between the predicted load data and the actual load monitoring data, error distribution data is generated; The first contribution weight of each physical field module in the multiphysics coupling model to the error distribution data is determined by the error source tracing algorithm. Adjust the coefficients of the basic control function of the first physics module with the largest contribution weight in the multiphysics coupling model; And / or, through an error tracing algorithm, determine the second contribution weight of each bidirectional coupling interface in the multiphysics coupling model to the error distribution data; Adjust the coupling parameters associated with the bidirectional coupling interface that has the largest second contribution weight in the multiphysics coupling model.

8. A structural load prediction device, characterized in that, The device includes: The data acquisition module is used to acquire the geometric parameters, material property parameters, and environmental parameter characteristic ranges of the environment in which the wind turbine structure to be predicted is located; the environmental parameter characteristic ranges include temperature variation range, wind speed range, particulate matter concentration range, and / or particle size distribution range. The model building module is used to construct a multiphysics coupling model based on the geometric parameters, the material property parameters, and the characteristic range of the environmental parameters. The multiphysics coupling model includes a temperature field module, a structural mechanics field module, an airflow field module, and a particle impact field module. The physical field modules exchange data bidirectionally through a coupling interface to simulate the interaction between the physical fields. The data acquisition module is also used to acquire the environmental parameter values ​​of the wind turbine structure to be predicted under the target operating conditions; The load prediction module is used to input the environmental parameter values ​​into the multiphysics coupling model to obtain the mechanical response data of the wind turbine structure to be predicted under the target operating condition; and to determine the predicted load data of the wind turbine structure to be predicted based on the mechanical response data.

9. An electronic device, characterized in that, The electronic 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 structural load prediction method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the structural load prediction method as described in any one of claims 1 to 7.

Images