A method, system, device and medium for optimizing wind energy capture efficiency

Abstract

This application relates to a method, system, device, and medium for optimizing wind energy capture efficiency. The method includes: acquiring environmental parameters, configuration parameters, and efficiency parameters of a wind energy capture device; performing correlation analysis based on the environmental parameters, configuration parameters, and efficiency parameters to construct an environment-configuration-efficiency correlation model; acquiring the current environmental parameters of the wind energy capture device and generating a configuration optimization scheme based on the model; performing multi-objective optimization based on the configuration optimization scheme to generate a configuration adjustment scheme for the wind energy capture device; and generating adjustment instructions for the wind energy capture device based on the configuration adjustment scheme. This method can effectively improve wind energy capture efficiency through dynamic modeling and intelligent optimization, achieving adaptive adjustment in complex environments and overcoming the problems of low efficiency and slow response of traditional methods.

Description

Technical Field

[0001] This invention belongs to the field of wind power generation technology, and in particular relates to a method, system, equipment and medium for optimizing wind energy capture efficiency. Background Technology

[0002] With the development of wind power generation technology, the technology for the large-scale development and utilization of wind energy as a clean and renewable energy source is becoming increasingly mature. Wind energy capture efficiency, as a core indicator determining the power generation efficiency and energy utilization rate of wind turbine generators, has made related optimization technologies a key research focus in the wind power field. In traditional technologies, wind energy capture efficiency optimization often adopts preset blade aerodynamic parameters under fixed operating conditions and constant speed control within the rated wind speed range. This can only achieve basic efficiency optimization under standard steady-state wind conditions. Some schemes use linear fitting of a single wind condition parameter to make limited range adjustments to the device configuration.

[0003] Existing optimization methods cannot adapt to the complex and unsteady wind conditions of turbulent fluctuations and temporal changes in wind speed in natural wind fields. It is difficult to establish a precise coupling mapping relationship between environmental parameters, device configuration and capture efficiency. These methods suffer from poor dynamic adaptability of optimization schemes, limited efficiency improvement under multiple operating conditions, and an inability to balance optimization benefits with execution costs. As a result, it is difficult to achieve precise optimization of wind energy capture efficiency under all operating conditions. Summary of the Invention

[0004] Therefore, it is necessary to provide a method, system, device, and medium for optimizing wind energy capture efficiency that can solve the above problems.

[0005] Firstly, this application provides a method for optimizing wind energy capture efficiency, including:

[0006] Acquire environmental parameters, configuration parameters, and efficiency parameters of the wind energy harvesting device;

[0007] Based on environmental parameters, configuration parameters, and efficiency parameters, a correlation analysis is performed to construct an environment-configuration-efficiency correlation model;

[0008] Obtain the current environmental parameters of the wind energy harvesting device, and based on the current environmental parameters, generate a configuration optimization scheme according to the environment-configuration-efficiency correlation model;

[0009] Based on the configuration optimization scheme, multi-objective optimization is performed to generate a wind energy capture device configuration adjustment scheme;

[0010] Based on the wind energy capture device configuration adjustment scheme, wind energy capture device adjustment instructions are generated.

[0011] In one embodiment, a correlation analysis is performed based on environmental parameters, configuration parameters, and efficiency parameters to construct an environment-configuration-efficiency correlation model, including:

[0012] The environmental parameters are segmented over time to obtain segmented environmental parameters, and turbulence intensity features are extracted based on the segmented environmental parameters.

[0013] Hydrodynamic characteristics when acquiring the operating configuration parameters of a wind energy harvesting device;

[0014] Based on turbulence intensity characteristics and fluid dynamics characteristics, combined with preset fluid dynamics boundary conditions, a three-dimensional flow field fingerprint database is constructed using a finite element-proxy hybrid simulation model.

[0015] The 3D flow field fingerprint database is fused with efficiency parameters to generate a parameter-coupled feature matrix.

[0016] Based on the parameter coupling feature matrix, an environment-configuration-efficiency correlation model is constructed.

[0017] In one embodiment, an environment-configuration-efficiency correlation model is constructed based on the parameter-coupled feature matrix, including:

[0018] An attention mechanism is used to assign weights to the parameter-coupled feature matrix, resulting in a weighted feature matrix.

[0019] The weighted feature matrix is ​​input into a pre-defined fully connected neural network to construct the initial mapping network architecture;

[0020] The backpropagation algorithm is used to calculate the gradient of the loss function of the initial mapped network architecture, where the loss function includes an environmental feature fitting loss term, a configuration parameter constraint loss term, and an efficiency mapping matching loss term;

[0021] Based on the function gradient, the Adam optimization algorithm is used to iteratively train the initial mapping network architecture until the gradient of the loss function of the initial mapping network architecture converges to the preset error threshold, thus obtaining the environment-configuration-efficiency correlation model.

[0022] In one embodiment, the current environmental parameters include wind speed fluctuation curves, temporal distribution of turbulence intensity, and air density parameters; the configuration optimization scheme includes blade rotation speed limit parameters, aerodynamic angle parameters, and electromagnetic drag parameters.

[0023] Based on the current environment parameters and according to the environment-configuration-efficiency correlation model, a configuration optimization plan is generated, including:

[0024] By integrating wind speed fluctuation curves, temporal distribution of turbulence intensity, and air density parameters, the current environmental parameter vector is obtained;

[0025] The current environmental parameter vector is input into the environment-configuration-efficiency correlation model, and the finite element-proxy hybrid simulation model is used for simulation to obtain a multi-condition configuration-efficiency mapping dataset.

[0026] Based on a multi-condition configuration-efficiency mapping dataset, with the goal of maximizing efficiency parameters, a gradient descent algorithm is used to obtain a set of candidate configuration parameters.

[0027] Based on preset configuration boundary conditions, configuration parameters that meet the configuration boundary conditions are selected from the candidate configuration parameter set, and a configuration optimization scheme is generated.

[0028] In one embodiment, based on the configuration optimization scheme, multi-objective optimization is performed to generate a wind energy capture device configuration adjustment scheme, including:

[0029] Obtain multiple optimization objectives, and based on these objectives, generate a multi-objective optimization weight matrix using a preset weight allocation rule;

[0030] Based on the multi-objective optimization weight matrix and combined with the configuration optimization scheme, a multi-objective optimization parameter constraint space is constructed.

[0031] Based on the multi-objective optimization parameter constraint space, a non-dominated sorting genetic algorithm is used to generate a sequence of configuration parameters to be optimized.

[0032] Each sequence of parameters to be optimized is input into the environment-configuration-efficiency correlation model, and the efficiency mapping result set is obtained through Monte Carlo simulation; the efficiency mapping result set includes efficiency confidence intervals and efficiency sensitivity curves;

[0033] Based on the efficiency mapping result set, a quantitative evaluation of the configuration execution cost-efficiency benefit is performed on the sequence of configuration parameters to be optimized, and the quantitative evaluation result is obtained.

[0034] Based on the quantitative evaluation results, wind energy capture device configuration adjustment schemes are generated from the sequence of parameters to be optimized.

[0035] In one embodiment, the formula for quantitatively evaluating the configuration execution cost-efficiency benefits of the preferred configuration parameter sequence is as follows:

[0036]

[0037] in, To configure a quantitative evaluation function for execution cost-efficiency benefits, For the expected efficiency weight, Let P be the expected efficiency value of the parameter sequence to be optimized. As a cost weight, The configuration execution cost is the parameter sequence P to be optimized. For variance weights, Let P be the efficiency variance of the parameter sequence P to be optimized and the random sampling variable S under Monte Carlo simulation.

[0038] In one embodiment, generating wind energy capture device adjustment instructions based on a wind energy capture device configuration adjustment scheme further includes:

[0039] Obtain the current configuration parameters of the wind energy harvesting device;

[0040] Based on the current configuration parameters and the wind energy capture device configuration adjustment plan, calculate the adjustment amount of each configuration parameter;

[0041] Based on the adjustment amount and combined with the current environmental parameters, determine the parameter adjustment strategy;

[0042] Based on the parameter adjustment strategy, adjustment instructions for the wind energy capture device are generated.

[0043] Secondly, this application also provides a wind energy capture efficiency optimization system, comprising:

[0044] The parameter acquisition module is used to acquire environmental parameters, configuration parameters, and efficiency parameters of the wind energy capture device.

[0045] The model building module is used to perform correlation analysis based on environmental parameters, configuration parameters, and efficiency parameters, and to build an environment-configuration-efficiency correlation model.

[0046] The scheme generation module is used to obtain the current environmental parameters of the wind energy capture device and generate a configuration optimization scheme based on the current environmental parameters and the environment-configuration-efficiency correlation model.

[0047] The multi-objective optimization module is used to perform multi-objective optimization based on the configuration optimization scheme and generate a wind energy capture device configuration adjustment scheme.

[0048] The instruction generation module is used to generate wind energy capture device adjustment instructions based on the wind energy capture device configuration adjustment scheme.

[0049] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the above-described steps for optimizing wind energy capture efficiency.

[0050] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-described steps for optimizing wind energy capture efficiency.

[0051] The aforementioned wind energy capture efficiency optimization method, system, equipment, and medium provide comprehensive basic data support for wind energy capture efficiency optimization by acquiring environmental parameters, configuration parameters, and efficiency parameters of the wind energy capture device. Based on the correlation analysis of these three types of parameters, an environment-configuration-efficiency correlation model is constructed, establishing a precise coupling mapping relationship between the environment, device configuration, and capture efficiency. Current environmental parameters are acquired, and a configuration optimization scheme is generated based on the model, enabling rapid matching of configuration parameters under different wind conditions and solving the problems of delayed optimization response and poor dynamic adaptability in traditional methods. Based on the configuration optimization scheme, multi-objective optimization is performed to generate a configuration adjustment scheme, balancing optimization benefits and execution costs, addressing the problem of limited efficiency improvement under multiple operating conditions in traditional schemes. Based on the configuration adjustment scheme, adjustment instructions are generated to achieve adaptive closed-loop optimization of the wind energy capture device, effectively improving wind energy capture efficiency under all operating conditions. Attached Figure Description

[0052] To more clearly illustrate the technical solutions in the embodiments or related technologies of this application, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0053] Figure 1 This is a flowchart of a wind energy capture efficiency optimization method according to the present invention;

[0054] Figure 2 This is a structural diagram of a wind energy capture efficiency optimization system according to the present invention. Detailed Implementation

[0055] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0056] In one embodiment, such as Figure 1As shown, a method for optimizing wind energy capture efficiency is provided. This embodiment illustrates the application of this method to an optimization terminal. It is understood that this method can also be applied to a server, or to a system including both a terminal and a server, and is implemented through interaction between the terminal and the server. The relevant hardware architecture of this embodiment includes wind speed, direction, and turbulence monitoring sensors, a wind turbine main control PLC, blade pitch actuators, a generator converter, a condition data acquisition unit, an edge computing terminal, and a central control cloud server. The application scenario includes: under unsteady turbulent wind conditions in natural wind fields, where there is a need for adaptive optimization of wind energy capture efficiency across all operating conditions of the wind turbine, the monitoring sensors and condition data acquisition unit collect environmental, configuration, and efficiency parameters, which are transmitted to the edge computing terminal for preprocessing. After model training and multi-objective optimization are completed by the central control cloud server, the adjustment scheme is transmitted back to the terminal, and the wind turbine main control PLC issues adjustment commands to the actuators to achieve closed-loop control for optimizing wind energy capture efficiency.

[0057] In this embodiment, the method includes the following steps:

[0058] S01, acquire the environmental parameters, configuration parameters and efficiency parameters of the wind energy harvesting device.

[0059] Optionally, the wind energy capture device can be a horizontal axis wind turbine, a vertical axis wind turbine, or other wind energy collection equipment capable of converting wind energy into mechanical or electrical energy. Environmental parameters refer to various environmental operating condition parameters affecting the wind energy capture process; configuration parameters refer to the adjustable operation and structural configuration parameters of the wind energy capture device; and efficiency parameters are quantitative parameters characterizing the device's wind energy capture and energy conversion efficiency. In implementation, the optimization terminal can acquire the above three types of parameters through channels such as sensor acquisition units, the device's main control system, local data storage units, and remote centralized control platforms, using methods such as real-time online acquisition, periodic sampling, historical operating condition data retrieval, and offline test data import. It can also perform preprocessing operations such as data denoising, outlier removal, time series alignment, and dimensional normalization on the acquired raw parameters, providing compliant basic data for subsequent correlation analysis and model construction.

[0060] S02. Based on environmental parameters, configuration parameters, and efficiency parameters, perform correlation analysis to construct an environment-configuration-efficiency correlation model.

[0061] Optionally, correlation analysis refers to the data analysis process of mining the interaction mechanism, nonlinear coupling characteristics, causal mapping relationship, and correlation rules among environmental parameters, configuration parameters, and efficiency parameters. The environment-configuration-efficiency correlation model refers to a mathematical, numerical simulation, or data-driven model that can output efficiency prediction results for corresponding configuration parameters based on input environmental parameters, or reverse-match the optimal configuration parameters. The optimization terminal can employ methods such as mathematical statistical analysis, fluid dynamics numerical simulation, and machine learning modeling to extract features and normalize data from environmental parameters, configuration parameters, and efficiency parameters, mine the correlation characteristics between parameters, construct a mapping model based on the obtained correlation rules, and complete the training, verification, and optimization of the model through a validation dataset to improve the model's prediction accuracy, generalization ability, and adaptability to all operating conditions.

[0062] S03: Obtain the current environmental parameters of the wind energy harvesting device, and based on the current environmental parameters, generate a configuration optimization scheme according to the environment-configuration-efficiency correlation model.

[0063] Optionally, the current environmental parameters are comprehensive environmental parameters that characterize the current operating conditions of the wind field where the wind energy capture device is located, obtained through real-time acquisition or short-term prediction. The configuration optimization scheme refers to a set of candidate optimizations of adjustable configuration parameters that adapt to the current environmental conditions, aim to improve wind energy capture efficiency, and meet the basic operating constraints of the device. The optimization terminal can acquire the current environmental parameters through on-site sensing units, wind field prediction systems, unit main control platforms, or remote centralized control centers. After standardized preprocessing consistent with the model training phase, the parameters are input into the environment-configuration-efficiency correlation model. Through the model's mapping solution and efficiency optimization process, a configuration optimization scheme adapted to the current operating conditions is generated, ensuring the operational adaptability and response timeliness of the optimization scheme.

[0064] S04. Based on the configuration optimization scheme, perform multi-objective optimization to generate a wind energy capture device configuration adjustment scheme.

[0065] Optionally, multi-objective optimization refers to the optimization decision-making process that simultaneously considers multiple optimization objectives with coupled constraints, and solves for the globally optimal solution set within a preset constraint boundary. The wind energy harvesting device configuration adjustment scheme is the final optimal combination of adjustable configuration parameters that satisfies the device's safe operation boundary, adapts to the current operating conditions, and considers multi-dimensional optimization objectives. The optimization terminal can employ intelligent optimization algorithms, mathematical programming methods, multi-attribute decision analysis, and other methods to determine the set of optimization objectives and parameter constraints, construct a mathematical model and parameter feasible region for the multi-objective optimization problem, complete the global optimization solution within the candidate parameter range of the configuration optimization scheme, and filter and verify the optimal solution through preset decision rules to generate a configuration adjustment scheme that meets the requirements of full-condition operation.

[0066] S05, Based on the wind energy capture device configuration adjustment scheme, generate wind energy capture device adjustment instructions.

[0067] Optionally, the wind energy harvesting device adjustment command refers to a standardized control command that can be directly received and executed by units such as the device's main control system, pitch actuator, and converter system to regulate corresponding configuration parameters. This command may include parameter adjustment amplitude, adjustment timing, execution priority, and safety verification rules. The optimization terminal can combine the device's current operating status and real-time configuration parameters to determine the adjustment rules and execution constraints for each parameter based on the configuration adjustment scheme. Then, according to the device's communication protocol, actuator control logic, and safety operation specifications, it encodes the adjustment command, verifies and encapsulates it, generating adjustment commands adapted to the device's hardware architecture and control system. Simultaneously, it can set up anomaly feedback and safety interlock mechanisms to ensure the executability, safety, and control accuracy of the commands.

[0068] In one embodiment, a correlation analysis is performed based on environmental parameters, configuration parameters, and efficiency parameters to construct an environment-configuration-efficiency correlation model, including:

[0069] S11, perform time-series segmentation of environmental parameters to obtain segmented environmental parameters, and extract turbulence intensity features based on segmented environmental parameters;

[0070] S12, Acquire the hydrodynamic characteristics when the wind energy harvesting device is operating and configured;

[0071] S13, based on turbulence intensity characteristics and fluid dynamics characteristics, combined with preset fluid dynamics boundary conditions, adopts a finite element-proxy hybrid simulation model to construct a three-dimensional flow field fingerprint database;

[0072] S14, the 3D flow field fingerprint database and efficiency parameters are fused to generate a parameter coupling feature matrix;

[0073] S15, based on the parameter coupling feature matrix, constructs an environment-configuration-efficiency correlation model.

[0074] Specifically, the optimization terminal can segment environmental parameters according to preset equally spaced time windows to obtain segmented environmental parameters corresponding to different time scales. Based on the wind speed time-series data within each segment, it uses fluid dynamics algorithms to calculate turbulence intensity and extracts turbulence intensity features that include the time-series variation of turbulence intensity, turbulence scale, and turbulence spectrum characteristics, thus completing the feature quantification of unsteady wind conditions. For each set of configuration parameters, the optimization terminal can obtain fluid dynamics features such as pressure distribution on the surface of the wind energy harvesting device blades, velocity gradient of the wake flow field, and angle of attack distribution through computational fluid dynamics simulation combined with wind tunnel test data calibration, characterizing the flow field response characteristics of the device under different configurations. Using the wind field inlet wind speed and turbulence intensity as inlet boundary conditions, combined with the device structural boundary constraints, the optimization terminal can use a finite element-surrogate hybrid simulation model to perform batch simulation calculations of the three-dimensional flow field under different combinations of turbulence intensity and fluid dynamics features, constructing a three-dimensional flow field fingerprint database containing the feature mapping relationship of the flow field under all operating conditions. The optimized terminal can use feature splicing and dimension normalization processing methods to fuse the flow field feature vectors of the three-dimensional flow field fingerprint database with the efficiency parameters of the corresponding working conditions to generate a parameter coupling feature matrix. Based on this matrix, a nonlinear mapping model between environment, configuration and efficiency can be constructed through machine learning algorithms to obtain the environment-configuration-efficiency correlation model.

[0075] In one embodiment, an environment-configuration-efficiency correlation model is constructed based on the parameter-coupled feature matrix, including:

[0076] S21, an attention mechanism is used to assign weights to the parameter coupling feature matrix to obtain a weighted feature matrix;

[0077] S22, input the weighted feature matrix into the preset fully connected neural network to construct the initial mapping network architecture;

[0078] S23, The backpropagation algorithm is used to calculate the function gradient of the loss function of the initial mapping network architecture, wherein the loss function includes an environmental feature fitting loss term, a configuration parameter constraint loss term, and an efficiency mapping matching loss term;

[0079] S24. Based on the function gradient, the Adam optimization algorithm is used to iteratively train the initial mapping network architecture until the gradient of the loss function of the initial mapping network architecture converges to the preset error threshold, thus obtaining the environment-configuration-efficiency correlation model.

[0080] For example, the optimization terminal can adaptively allocate weights to features in each dimension of the parameter-coupled feature matrix through a channel attention mechanism (e.g., extracting global features of each feature channel through global average pooling, completing weight learning through two fully connected layers, outputting the weight coefficients of each feature channel, and multiplying the weight coefficients with the original feature matrix channel by channel to obtain a weighted feature matrix that can represent the core coupled features), thus reducing the interference of redundant features on model accuracy. The optimization terminal can input the weighted feature matrix into a preset multi-layer fully connected neural network according to a preset batch size to build an initial mapping network architecture with environmental features as input, configuration parameters as intermediate variables, and efficiency parameters as output, and determine the number of neurons and ReLU activation function in each layer of the initial mapping network architecture. The optimization terminal can use the backpropagation algorithm to calculate the function gradient of the loss function with respect to the weights and biases of each layer along the network. The loss function simultaneously incorporates environmental feature fitting loss terms, configuration parameter constraint loss terms, and efficiency mapping matching loss terms, comprehensively constraining the model's fitting accuracy and generalization ability. The optimized terminal can use the Adam optimization algorithm to iteratively update the network weights and biases based on the calculated function gradient. After each iteration, the gradient of the loss function is verified until it converges to within a preset error threshold (such as 1e-5), thus completing the model training and obtaining an environment-configuration-efficiency correlation model with full-condition mapping capability.

[0081] In one embodiment, the current environmental parameters include wind speed fluctuation curves, temporal distribution of turbulence intensity, and air density parameters; the configuration optimization scheme includes blade rotation speed limit parameters, aerodynamic angle parameters, and electromagnetic drag parameters.

[0082] Based on the current environment parameters and according to the environment-configuration-efficiency correlation model, a configuration optimization plan is generated, including:

[0083] S31 integrates wind speed fluctuation curves, temporal distribution of turbulence intensity, and air density parameters to obtain the current environmental parameter vector;

[0084] S32, input the current environmental parameter vector into the environment-configuration-efficiency correlation model, and use the finite element-proxy hybrid simulation model to perform simulation to obtain a multi-condition configuration-efficiency mapping dataset;

[0085] S33, based on a multi-condition configuration-efficiency mapping dataset, aims to maximize efficiency parameters and uses the gradient descent algorithm to obtain the candidate configuration parameter set;

[0086] S34. Based on the preset configuration boundary conditions, select configuration parameters that meet the configuration boundary conditions from the candidate configuration parameter set and generate a configuration optimization scheme.

[0087] Specifically, the optimization terminal can perform time-series alignment preprocessing on real-time collected wind speed fluctuation curves, turbulence intensity temporal distributions, and air density parameters. Then, it performs vector concatenation according to a preset feature dimension order to obtain a current environmental parameter vector whose dimensions match the input layer of the environment-configuration-efficiency association model. The optimization terminal can input this current environmental parameter vector into the trained environment-configuration-efficiency association model, call a pre-calibrated finite element-surrogate hybrid simulation model, and perform batch simulations across the entire feasible domain of blade speed, aerodynamic angle, and electromagnetic drag. It outputs the efficiency prediction values ​​corresponding to different combinations of configuration parameters, constructing a multi-condition configuration-efficiency mapping dataset. The optimization terminal can construct a single-objective optimization function with maximizing wind energy capture efficiency as the optimization goal, and iteratively solve the optimization function using a gradient descent algorithm to obtain a set of candidate configuration parameters that satisfy the efficiency maximization objective. Based on preset boundary conditions for safe device operation, including upper and lower limits of blade speed, pitch angle travel range, and generator electromagnetic drag constraint thresholds, the optimization terminal can perform compliance screening on the candidate configuration parameter set, eliminating parameter combinations that exceed boundary constraints, and generating a configuration optimization scheme adapted to the current wind conditions.

[0088] In one embodiment, based on the configuration optimization scheme, multi-objective optimization is performed to generate a wind energy capture device configuration adjustment scheme, including:

[0089] S41, obtain multiple optimization objectives, and generate a multi-objective optimization weight matrix based on the multiple optimization objectives using a preset weight allocation rule;

[0090] S42, based on the multi-objective optimization weight matrix and combined with the configuration optimization scheme, constructs the multi-objective optimization parameter constraint space;

[0091] S43. Based on the multi-objective optimization parameter constraint space, a non-dominated sorting genetic algorithm is used to generate a sequence of configuration parameters to be optimized.

[0092] S44. Input the sequence of each configuration parameter to be optimized into the environment-configuration-efficiency correlation model, and obtain the efficiency mapping result set through Monte Carlo simulation; the efficiency mapping result set includes efficiency confidence intervals and efficiency sensitivity curves.

[0093] S45. Based on the efficiency mapping result set, perform a quantitative evaluation of the configuration execution cost-efficiency benefit of the sequence of configuration parameters to be optimized, and obtain the quantitative evaluation result.

[0094] S46. Based on the quantitative evaluation results, select and generate wind energy capture device configuration adjustment schemes from the sequence of configuration parameters to be optimized.

[0095] For example, the optimization terminal can acquire multiple optimization objectives (such as maximizing wind energy capture efficiency, minimizing configuration execution costs, and optimizing device operational stability). Based on pre-defined analytic hierarchy process (AHP) methods from wind power engineering experience, it can determine the weight proportion of each objective, generate a multi-objective optimization weight matrix, and determine the optimization priority of each objective. The optimization terminal can use the multi-objective optimization weight matrix as a core constraint, combined with the parameter value range in the configuration optimization scheme, to define the upper and lower limits and adjustment step sizes for blade speed limits, aerodynamic angles, and electromagnetic drag, constructing a multi-objective optimization parameter constraint space and limiting the parameter optimization range. Within the multi-objective optimization parameter constraint space, the optimization terminal can employ a non-dominated sorting genetic algorithm, undergoing population initialization, fast non-dominated sorting, crowding calculation, and an elite retention strategy to complete multiple generations of iterations, generating a sequence of configuration parameters to be optimized corresponding to the Pareto optimal solution. The optimization terminal can input the sequence of parameters to be optimized into the environment-configuration-efficiency correlation model. Through Monte Carlo simulation, it samples the parameters of random disturbance factors in the wind field more than 1,000 times and outputs an efficiency mapping result set including efficiency confidence intervals and efficiency sensitivity curves. The optimization terminal can complete the quantitative calculation of configuration execution cost-efficiency benefit for each sequence according to the preset quantitative evaluation formula, obtain the quantitative evaluation result, and select the parameter sequence with the best evaluation value to generate a wind energy capture device configuration adjustment scheme.

[0096] In one embodiment, S51, the formula for the quantitative evaluation of the configuration execution cost-efficiency benefits of the preferred configuration parameter sequence is:

[0097]

[0098] in, To configure a quantitative evaluation function for execution cost-efficiency benefits, For the expected efficiency weight, Let P be the expected efficiency value of the parameter sequence to be optimized. As a cost weight, The configuration execution cost is the parameter sequence P to be optimized. For variance weights, Let P be the efficiency variance of the parameter sequence P to be optimized and the random sampling variable S under Monte Carlo simulation.

[0099] Specifically, this formula is used to comprehensively and quantitatively evaluate the parameter sequence P of the optimal configuration, balancing multiple objectives such as efficiency improvement, execution cost, and system robustness. It integrates the expected efficiency, cost term, and variance integral into a single scalar index through a linear combination, allowing different configuration schemes to be compared under a unified metric. Optionally, the expected efficiency weight in the formula... Cost weight and variance weight The preset positive coefficient reflects the decision-making preference for efficiency gains, economy, and stability. This represents the average efficiency obtained through Monte Carlo simulation under a given parameter sequence P, reflecting the expected performance of the configuration scheme; The quantitative values ​​of energy consumption, wear and tear, and operation and maintenance costs required to perform P can be calculated based on historical data of the device or physical models; The term is the full-range integral of the efficiency variance of a randomly sampled variable S (e.g., under fluctuating wind conditions), used to characterize the robustness of the configuration scheme against environmental uncertainty. This formula combines positive benefits (expected efficiency) with negative costs (execution costs, variance) through a weighted combination, and its value... A higher value indicates better overall performance of the configuration sequence. The efficiency mapping result set (including efficiency confidence intervals and sensitivity curves) generated based on the environment-configuration-efficiency correlation model and Monte Carlo simulation is shown below. The formula output can be directly extracted from this result set. As a quantitative basis for selecting configuration adjustment schemes, different parameter sequences are compared. The optimal solution is selected from the Pareto solution set generated by the non-dominated sorting genetic algorithm, based on a preset threshold or sorting rule. This ensures that the final solution maximizes efficiency while also considering feasibility and adaptability to dynamic wind conditions. The calculation formula can be numerically solved using an embedded system or cloud computing platform. Monte Carlo simulation provides probability distribution data, and the weighting coefficients are preset by domain experts according to the wind farm's operation strategy. The cost item... Based on the physical model of the actuators such as the blade pitch mechanism and generator converter, real-time estimation is performed, and decision-making is completed through scalar comparison, forming a repeatable and verifiable evaluation link in the closed-loop optimization.

[0100] In one embodiment, generating wind energy capture device adjustment instructions based on a wind energy capture device configuration adjustment scheme further includes:

[0101] S61, Obtain the current configuration parameters of the wind energy harvesting device;

[0102] S62, Based on the current configuration parameters and the wind energy capture device configuration adjustment scheme, calculate the adjustment amount of each configuration parameter;

[0103] S63, based on the adjustment amount and combined with the current environmental parameters, determine the parameter adjustment strategy;

[0104] S64 generates adjustment commands for the wind energy capture device based on the parameter adjustment strategy.

[0105] For example, the optimization terminal can read the configuration parameters of the current operating state in real time through the main control system (such as a PLC controller) of the integrated wind energy capture device. These parameters include adjustable variables such as blade speed, aerodynamic angle, and electromagnetic drag. The data source can be the local sensor acquisition unit of the device or a historical operation database. The optimization terminal can compare the acquired current configuration parameters with the configuration adjustment scheme generated by the aforementioned multi-objective optimization, and determine the adjustment amount of each configuration parameter one by one through difference calculation. For example, it can determine the increase in blade speed or the adjustment angle of aerodynamic angle through arithmetic subtraction. The optimization terminal can combine the adjustment amount with the current environmental parameters (such as the aerodynamic angle adjustment amount with the real-time wind speed fluctuation curve and turbulence intensity) to determine the parameter adjustment strategy. The parameter adjustment strategy can comprehensively evaluate the impact of environmental dynamics on the adjustment safety, such as using gradual adjustment in high turbulence conditions to avoid sudden increases in mechanical stress, or optimizing the adjustment sequence according to wind speed trends to synchronize command execution with wind condition changes. The optimization terminal can encode adjustment strategies into standardized wind energy capture device adjustment instructions (including target parameter values, adjustment rates, execution priorities, and security check codes), and distribute them to hardware units such as pitch actuators and converters via edge computing terminals or centralized control centers to achieve closed-loop optimization control. Through real-time data interaction, quantitative calculation, and strategy adaptation, the implementation of instructions from scheme to execution is realized, improving the adaptive optimization capability of wind energy capture efficiency under all operating conditions.

[0106] The aforementioned wind energy capture efficiency optimization method provides comprehensive data support for the optimization process by acquiring environmental, configuration, and efficiency parameters of the wind energy capture device. Based on these parameters, a correlation analysis is performed to construct an environment-configuration-efficiency correlation model. This model employs time-series segmentation to extract turbulence intensity features and combines a finite element-surrogate hybrid simulation model to generate a three-dimensional flow field fingerprint database. High-precision mapping relationships are obtained through attention mechanisms and fully connected neural network training, overcoming the shortcomings of traditional methods in establishing accurate coupling mappings under complex and unsteady wind conditions, thus achieving dynamic correlation between environment, configuration, and efficiency. Current environmental parameters are acquired, and a configuration optimization scheme is generated based on the model. A gradient descent algorithm is used to solve for the candidate parameter set, enabling the scheme to quickly match the current wind conditions and solving the problem of lag in traditional optimization response. Multi-objective optimization is performed based on the configuration optimization scheme. A non-dominated sorting genetic algorithm is used to generate a sequence of candidates for optimization, and Monte Carlo simulation is combined to obtain the efficiency confidence interval. A quantitative evaluation function balances the efficiency expectation, execution cost, and variance weights, achieving multi-objective decision-making that considers both benefits and costs, and improving efficiency gains under various operating conditions. Based on the configuration adjustment scheme, the parameter adjustment amount is calculated and the adjustment command is generated. Combined with the current environmental parameters, the safety strategy is determined to form a closed-loop adaptive control, which effectively improves the wind energy capture efficiency under all operating conditions and overcomes the shortcomings of traditional methods such as poor dynamic adaptability and limited optimization benefits.

[0107] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0108] Based on the same inventive concept, this application also provides a wind energy capture efficiency optimization system for implementing the wind energy capture efficiency optimization method described above. The solution provided by this system is similar to the implementation scheme described in the above method; therefore, the specific limitations of one or more embodiments of the wind energy capture efficiency optimization system provided below can be found in the limitations of the wind energy capture efficiency optimization method described above, and will not be repeated here.

[0109] In one exemplary embodiment, such as Figure 2 As shown, a wind energy capture efficiency optimization system is provided, comprising:

[0110] The parameter acquisition module 101 is used to acquire environmental parameters, configuration parameters, and efficiency parameters of the wind energy capture device.

[0111] The model building module 102 is used to perform correlation analysis based on environmental parameters, configuration parameters, and efficiency parameters to build an environment-configuration-efficiency correlation model;

[0112] The scheme generation module 103 is used to obtain the current environmental parameters of the wind energy capture device and generate a configuration optimization scheme based on the current environmental parameters and the environment-configuration-efficiency correlation model.

[0113] The multi-objective optimization module 104 is used to perform multi-objective optimization based on the configuration optimization scheme and generate a wind energy capture device configuration adjustment scheme.

[0114] The instruction generation module 105 is used to generate wind energy capture device adjustment instructions based on the wind energy capture device configuration adjustment scheme.

[0115] In one embodiment, the model building module 102 can also be used for:

[0116] The environmental parameters are segmented over time to obtain segmented environmental parameters, and turbulence intensity features are extracted based on the segmented environmental parameters.

[0117] Hydrodynamic characteristics when acquiring the operating configuration parameters of a wind energy harvesting device;

[0118] Based on turbulence intensity characteristics and fluid dynamics characteristics, combined with preset fluid dynamics boundary conditions, a three-dimensional flow field fingerprint database is constructed using a finite element-proxy hybrid simulation model.

[0119] The 3D flow field fingerprint database is fused with efficiency parameters to generate a parameter-coupled feature matrix.

[0120] Based on the parameter coupling feature matrix, an environment-configuration-efficiency correlation model is constructed.

[0121] In one embodiment, the model building module 102 can also be used for:

[0122] An attention mechanism is used to assign weights to the parameter-coupled feature matrix, resulting in a weighted feature matrix.

[0123] The weighted feature matrix is ​​input into a pre-defined fully connected neural network to construct the initial mapping network architecture;

[0124] The backpropagation algorithm is used to calculate the gradient of the loss function of the initial mapped network architecture, where the loss function includes an environmental feature fitting loss term, a configuration parameter constraint loss term, and an efficiency mapping matching loss term;

[0125] Based on the function gradient, the Adam optimization algorithm is used to iteratively train the initial mapping network architecture until the gradient of the loss function of the initial mapping network architecture converges to the preset error threshold, thus obtaining the environment-configuration-efficiency correlation model.

[0126] In one embodiment, the current environmental parameters in the scheme generation module 103 include wind speed fluctuation curves, turbulence intensity temporal distribution, and air density parameters; the configuration optimization scheme includes blade speed limit parameters, aerodynamic angle parameters, and electromagnetic drag parameters.

[0127] The solution generation module 103 can also be used for:

[0128] By integrating wind speed fluctuation curves, temporal distribution of turbulence intensity, and air density parameters, the current environmental parameter vector is obtained;

[0129] The current environmental parameter vector is input into the environment-configuration-efficiency correlation model, and the finite element-proxy hybrid simulation model is used for simulation to obtain a multi-condition configuration-efficiency mapping dataset.

[0130] Based on a multi-condition configuration-efficiency mapping dataset, with the goal of maximizing efficiency parameters, a gradient descent algorithm is used to obtain a set of candidate configuration parameters.

[0131] Based on preset configuration boundary conditions, configuration parameters that meet the configuration boundary conditions are selected from the candidate configuration parameter set, and a configuration optimization scheme is generated.

[0132] In one embodiment, the multi-objective optimization module 104 can also be used for:

[0133] Obtain multiple optimization objectives, and based on these objectives, generate a multi-objective optimization weight matrix using a preset weight allocation rule;

[0134] Based on the multi-objective optimization weight matrix and combined with the configuration optimization scheme, a multi-objective optimization parameter constraint space is constructed.

[0135] Based on the multi-objective optimization parameter constraint space, a non-dominated sorting genetic algorithm is used to generate a sequence of configuration parameters to be optimized.

[0136] Each sequence of parameters to be optimized is input into the environment-configuration-efficiency correlation model, and the efficiency mapping result set is obtained through Monte Carlo simulation; the efficiency mapping result set includes efficiency confidence intervals and efficiency sensitivity curves;

[0137] Based on the efficiency mapping result set, a quantitative evaluation of the configuration execution cost-efficiency benefit is performed on the sequence of configuration parameters to be optimized, and the quantitative evaluation result is obtained.

[0138] Based on the quantitative evaluation results, wind energy capture device configuration adjustment schemes are generated from the sequence of parameters to be optimized.

[0139] In one embodiment, the instruction generation module 105 can also be used to:

[0140] Obtain the current configuration parameters of the wind energy harvesting device;

[0141] Based on the current configuration parameters and the wind energy capture device configuration adjustment plan, calculate the adjustment amount of each configuration parameter;

[0142] Based on the adjustment amount and combined with the current environmental parameters, determine the parameter adjustment strategy;

[0143] Based on the parameter adjustment strategy, adjustment instructions for the wind energy capture device are generated.

[0144] In one embodiment, a computer device is provided, including a memory and a processor, the memory storing a computer program, the processor executing the computer program to implement the steps of the wind energy capture efficiency optimization method as described above.

[0145] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps in the above method embodiments.

[0146] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The device embodiments described above are merely illustrative. The components described as separate parts may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this disclosure according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0147] The above-described embodiments are merely illustrative of several implementation methods of the embodiments of this application, and their descriptions are relatively specific and detailed. However, they should not be construed as limiting the scope of the patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the embodiments of this application, and these modifications and improvements all fall within the protection scope of the embodiments of this application.

Claims

1. A method for optimizing wind energy capture efficiency, characterized in that, The method includes: Acquire environmental parameters, configuration parameters, and efficiency parameters of the wind energy harvesting device; Based on the environmental parameters, configuration parameters, and efficiency parameters, a correlation analysis is performed to construct an environment-configuration-efficiency correlation model; Obtain the current environmental parameters of the wind energy harvesting device, and based on the current environmental parameters, generate a configuration optimization scheme according to the environment-configuration-efficiency correlation model; Based on the configuration optimization scheme, multi-objective optimization is performed to generate a wind energy capture device configuration adjustment scheme; Based on the wind energy capture device configuration adjustment scheme, an adjustment command for the wind energy capture device is generated.

2. The method according to claim 1, characterized in that, The step of performing correlation analysis based on the environmental parameters, configuration parameters, and efficiency parameters to construct an environment-configuration-efficiency correlation model includes: The environmental parameters are segmented over time to obtain segmented environmental parameters, and turbulence intensity features are extracted based on the segmented environmental parameters. Obtain the hydrodynamic characteristics of the wind energy harvesting device when it operates with the specified configuration parameters; Based on the turbulence intensity characteristics and the fluid dynamics characteristics, and combined with the preset fluid dynamics boundary conditions, a three-dimensional flow field fingerprint database is constructed using a finite element-proxy hybrid simulation model. The three-dimensional flow field fingerprint database and the efficiency parameters are fused to generate a parameter-coupled feature matrix. Based on the parameter coupling feature matrix, the environment-configuration-efficiency correlation model is constructed.

3. The method according to claim 2, characterized in that, The construction of the environment-configuration-efficiency correlation model based on the parameter coupling feature matrix includes: An attention mechanism is used to assign weights to the parameter-coupled feature matrix to obtain a weighted feature matrix. The weighted feature matrix is ​​input into a preset fully connected neural network to construct an initial mapping network architecture; The gradient of the loss function of the initial mapping network architecture is calculated using the backpropagation algorithm, wherein the loss function includes an environmental feature fitting loss term, a configuration parameter constraint loss term, and an efficiency mapping matching loss term; Based on the gradient of the function, the Adam optimization algorithm is used to iteratively train the initial mapping network architecture until the gradient of the loss function of the initial mapping network architecture converges to a preset error threshold, thus obtaining the environment-configuration-efficiency correlation model.

4. The method according to claim 2, characterized in that, The current environmental parameters include wind speed fluctuation curves, turbulence intensity temporal distribution, and air density parameters; the configuration optimization scheme includes blade rotation speed limit parameters, aerodynamic angle parameters, and electromagnetic drag parameters. Based on the current environment parameters, and according to the environment-configuration-efficiency correlation model, a configuration optimization scheme is generated, including: By integrating the wind speed fluctuation curve, the temporal distribution of turbulence intensity, and the air density parameter, the current environmental parameter vector is obtained; The current environment parameter vector is input into the environment-configuration-efficiency correlation model, and the finite element-proxy hybrid simulation model is used for simulation to obtain a multi-condition configuration-efficiency mapping dataset. Based on the multi-condition configuration-efficiency mapping dataset, with the goal of maximizing the efficiency parameters, a gradient descent algorithm is used to obtain a set of candidate configuration parameters. Based on preset configuration boundary conditions, configuration parameters that meet the configuration boundary conditions are selected from the candidate configuration parameter set, and the configuration optimization scheme is generated.

5. The method according to claim 4, characterized in that, The step of performing multi-objective optimization based on the configuration optimization scheme to generate a wind energy harvesting device configuration adjustment scheme includes: Obtain multiple optimization objectives, and based on the multiple optimization objectives, generate a multi-objective optimization weight matrix using a preset weight allocation rule; Based on the multi-objective optimization weight matrix and the configuration optimization scheme, a multi-objective optimization parameter constraint space is constructed. Based on the multi-objective optimization parameter constraint space, a non-dominated sorting genetic algorithm is used to generate a sequence of configuration parameters to be optimized. Each of the proposed optimal configuration parameter sequences is input into the environment-configuration-efficiency correlation model, and an efficiency mapping result set is obtained through Monte Carlo simulation; the efficiency mapping result set includes efficiency confidence intervals and efficiency sensitivity curves. Based on the efficiency mapping result set, the configuration execution cost-efficiency benefit of the sequence of configuration parameters to be optimized is quantitatively evaluated to obtain the quantitative evaluation result; Based on the quantitative evaluation results, the wind energy capture device configuration adjustment scheme is generated by selecting from the sequence of configuration parameters to be optimized.

6. The method according to claim 5, characterized in that, The formula for the quantitative evaluation of the configuration execution cost-efficiency benefit of the sequence of parameters to be optimized is as follows: in, To configure a quantitative evaluation function for execution cost-efficiency benefits, For the expected efficiency weight, Let P be the expected efficiency value of the parameter sequence to be optimized. As a cost weight, The configuration execution cost is the parameter sequence P to be optimized. For variance weights, Let P be the efficiency variance of the parameter sequence P to be optimized and the random sampling variable S under Monte Carlo simulation.

7. The method according to claim 5, characterized in that, The step of generating wind energy harvesting device adjustment instructions based on the wind energy harvesting device configuration adjustment scheme further includes: Obtain the current configuration parameters of the wind energy harvesting device; Based on the current configuration parameters and the wind energy capture device configuration adjustment scheme, calculate the adjustment amount of each configuration parameter; Based on the adjustment amount and the current environmental parameters, a parameter adjustment strategy is determined. Based on the parameter adjustment strategy, adjustment instructions for the wind energy capture device are generated.

8. A wind energy capture efficiency optimization system, characterized in that, The system includes: The parameter acquisition module is used to acquire environmental parameters, configuration parameters, and efficiency parameters of the wind energy capture device; The model building module is used to perform correlation analysis based on the environmental parameters, the configuration parameters, and the efficiency parameters to build an environment-configuration-efficiency correlation model; The scheme generation module is used to obtain the current environmental parameters of the wind energy harvesting device, and based on the current environmental parameters, generate a configuration optimization scheme according to the environment-configuration-efficiency correlation model; The multi-objective optimization module is used to perform multi-objective optimization based on the configuration optimization scheme to generate a wind energy capture device configuration adjustment scheme; The instruction generation module is used to generate wind energy capture device adjustment instructions based on the wind energy capture device configuration adjustment scheme.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images