Wind power plant simulation model construction method, system and device, and storage medium

Abstract

The invention provides a wind power plant simulation model construction method, system and device, and a storage medium, and belongs to the technical field of model construction, and the method comprises the steps: constructing a plurality of sub-models corresponding to each fan in a wind power plant; coupling and integrating the plurality of sub-models corresponding to each fan to obtain a fan complete machine model corresponding to each fan; clustering the fans in the wind power plant based on the operation parameters and the state information corresponding to the fans to obtain a plurality of fan groups; based on the operation parameters and the state information corresponding to each fan group in the multiple fan groups, equivalent model parameters corresponding to each fan group are determined, and a fan group equivalent model corresponding to each fan group is constructed; the fan complete machine model and the fan group equivalent model are both used for simulating a wind power plant. According to the wind power plant simulation model construction method, system and equipment, and the storage medium provided by the invention, reliable support can be provided for design, operation and maintenance of the wind power plant.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of model construction, and more particularly to a wind farm simulation model construction method, system, device and storage medium. BACKGROUND

[0002] With the rapid development of wind power, wind farm simulation models play an increasingly important role in planning and design, performance evaluation and control optimization. Traditional wind farm simulation models are usually constructed using simplified methods, such as wind resource assessment models based on empirical formulas, single-machine equivalent wind turbine models, and simplified electrical network models. However, the model structure of these methods is too simplified, resulting in low simulation accuracy and difficulty in accurately reflecting the complex flow field interaction and electrical characteristics of the wind farm, which makes it difficult to provide reliable support for the design and operation of the wind farm. SUMMARY

[0003] The purpose of the present application is to provide a wind farm simulation model construction method, system, device and storage medium to provide reliable support for the design and operation of the wind farm.

[0004] The first aspect of the embodiment of the present application provides a wind farm simulation model construction method, comprising: constructing a plurality of sub-models corresponding to each wind turbine in the wind farm, the plurality of sub-models being sub-models constructed based on aerodynamic data, structural mechanics data and electrical data corresponding to each wind turbine; the plurality of sub-models being used to represent operating parameters and state information corresponding to each wind turbine; coupling and integrating the plurality of sub-models corresponding to each wind turbine to obtain a wind turbine whole-machine model corresponding to each wind turbine; clustering the wind turbines in the wind farm based on the operating parameters and the state information corresponding to each wind turbine to obtain a plurality of wind turbine groups; determining equivalent model parameters corresponding to each wind turbine group based on the operating parameters and the state information corresponding to each wind turbine group in the plurality of wind turbine groups, and constructing a wind turbine group equivalent model corresponding to each wind turbine group; The wind turbine whole-machine model and the wind turbine group equivalent model are both used to simulate the wind farm.

[0005] The second aspect of the embodiment of the present application provides a wind farm simulation model construction system, comprising: a sub-model construction module for constructing a plurality of sub-models corresponding to each wind turbine in the wind farm, the plurality of sub-models being sub-models constructed based on aerodynamic data, structural mechanics data and electrical data corresponding to each wind turbine; the plurality of sub-models being used to represent operating parameters and state information corresponding to each wind turbine; The first model construction module is configured to couple and integrate the plurality of sub-models corresponding to the wind fans to obtain a wind fan whole-machine model corresponding to each wind fan; The clustering module is configured to cluster the wind fans in the wind farm based on the operation parameters and the state information corresponding to each wind fan to obtain a plurality of wind fan groups. The second model construction module is configured to determine equivalent model parameters corresponding to each wind fan group based on the operation parameters and the state information corresponding to each wind fan group in the plurality of wind fan groups, and construct a wind fan group equivalent model corresponding to each wind fan group. The wind fan whole-machine model and the wind fan group equivalent model are both configured to simulate the wind farm.

[0006] In a third aspect, an electronic device is provided, which includes a memory, a processor, and a computer program stored in the memory and running on the processor, and the processor implements the steps of the wind farm simulation model construction method described above when executing the computer program.

[0007] In a fourth aspect, a computer readable storage medium is provided, which stores a computer program, and the computer program is executed by a processor to implement the steps of the wind farm simulation model construction method described above.

[0008] The wind farm simulation model construction method, system, device, and storage medium provided by the embodiments of the present application have the following beneficial effects: the embodiments of the present application construct a simulation system in which a wind fan whole-machine model and a wind fan group equivalent model are used in cooperation, so that the balance between simulation accuracy and efficiency of a wind farm is achieved. The wind fan whole-machine model is coupled based on a plurality of sub-models, so that the interaction of aerodynamic force, structural mechanics, and electrical system of a single wind fan can be accurately obtained, and the details such as blade aerodynamic load, structural vibration, and electromechanical energy conversion can be accurately simulated, so as to ensure the simulation accuracy under key working conditions. The wind fan group equivalent model is clustered and aggregated according to operation parameters, so that the model complexity is greatly simplified, and the flow field wake superposition and electrical cooperative characteristics of a large-scale wind fan cluster can be efficiently processed. The two models are used in cooperation, so that the response of a single wind fan in a complex flow field can be accurately reflected, and the overall electrical dynamics of a wind farm can be quickly simulated, so as to meet the requirements of multiple scenarios such as single wind fan fault diagnosis and whole-farm power scheduling, and provide reliable support for wind farm design and operation and maintenance. BRIEF DESCRIPTION OF DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without any creative effort.

[0010] Figure 1A flowchart of a wind farm simulation model construction method provided by an embodiment of the present application is shown in FIG. 1. Figure 2 A structural block diagram of a wind farm simulation model construction system provided by an embodiment of the present application is shown in FIG. 2. Figure 3 A schematic block diagram of an electronic device provided by an embodiment of the present application is shown in FIG. 3. DETAILED DESCRIPTION

[0011] In the following description, specific details are set forth in order to provide a thorough understanding of embodiments of the present application. However, persons having ordinary skill in the art will readily recognize that embodiments of the present application can be practiced without these specific details. In other instances, well-known structures, circuits, and methods have not been described in detail in order to avoid obscuring the present application.

[0012] In order to make the objects, technical solutions and advantages of the present application clearer, the following will be described in detail with reference to the accompanying drawings.

[0013] Reference will be made to Figure 1 , Figure 1 A flowchart of a wind farm simulation model construction method provided by an embodiment of the present application can be executed by an electronic device, and the method can include the following steps. S101: Constructing a plurality of sub-models corresponding to each wind turbine in the wind farm, the plurality of sub-models being constructed based on aerodynamic data, structural mechanics data and electrical data corresponding to each wind turbine; the plurality of sub-models being used to represent operating parameters and state information corresponding to each wind turbine.

[0014] In the present embodiment, the sub-models are specialized models constructed for a specific functional module of the wind turbine. For example, an aerodynamic sub-model can be constructed based on aerodynamic data, simulating the relationship between wind speed, wind direction and blade aerodynamic load (such as lift and drag) based on blade element momentum theory or computational fluid dynamics (CFD); a structural mechanics sub-model can be constructed based on structural mechanics data, simulating the deformation, vibration and fatigue characteristics of blades, towers and other structures under load based on finite element analysis; an electrical sub-model can be constructed based on electrical data, simulating the electromagnetic characteristics, power conversion efficiency and fault response of electrical equipment such as generators and converters.

[0015] The operating parameters are quantitative indexes of real-time monitoring of the fan or fan group during operation, and are used to reflect the working state, and can include: environmental parameters (wind speed, wind direction, air density); performance parameters (output power, speed, pitch angle, voltage, current); state parameters (temperature, vibration amplitude, torque). The state information is qualitative or semi-quantitative information describing the operation mode, health status, etc. of the fan or fan group, for example: control mode (maximum wind energy tracking, constant power operation, shutdown state); health status (normal, minor fault, emergency maintenance); external coordination state (participating in grid frequency modulation, tail flow influence degree).

[0016] In this embodiment, the physical characteristics of a single fan can be disassembled into aerodynamics, structural mechanics, electrical systems, and other independent dimensions, and corresponding sub-models can be constructed based on respective professional data (such as aerodynamic data including wind speed, attack angle, aerodynamic load; structural mechanics data including material strength, vibration mode; electrical data including generator parameters, converter topology). The sub-models respectively describe the operation law of different systems of the fan.

[0017] S102: Coupling and integration of the multiple sub-models corresponding to each fan to obtain a fan whole machine model corresponding to each fan.

[0018] In this embodiment, the fan whole machine model is a complete model formed by the multiple sub-models of a single fan through dynamic coupling and integration, and the fan whole machine model can comprehensively reflect the whole process characteristics of the fan from wind energy capture, mechanical energy transmission to electrical energy output, and is used to simulate the dynamic response of a single fan under different working conditions (such as power fluctuation when wind speed suddenly changes, protection action when a fault occurs).

[0019] In this embodiment, the multiple sub-models of a single fan do not exist in isolation, but form an organic whole through physical field interaction (such as transmission of force, energy, and signal). For example: the aerodynamic load calculated by the aerodynamics sub-model is transmitted to the structural mechanics sub-model to drive the vibration of the blade and tower; the blade deformation caused by structural vibration feeds back to the aerodynamics sub-model to correct the aerodynamic parameters; the electrical sub-model receives the torque from the mechanical transmission sub-model and outputs electrical power, while the counter-torque is fed back to the mechanical system. Through standardized interfaces and multi-time scale collaborative solving, dynamic coupling of the sub-models is realized, and finally a whole machine model that can accurately reflect the operating characteristics of a single fan is formed.

[0020] S103: Clustering the fans in the wind farm based on the operating parameters and state information corresponding to each fan to obtain multiple fan groups.

[0021] The fan whole machine model and the fan group equivalent model are both used for simulation of the wind farm.

[0022] In this embodiment, the wind turbine group is divided into several groups based on the similarity of operating parameters and status information. Wind turbines in the same wind turbine group may have similar geographical locations (such as the same wind zone), similar environmental impacts (such as being affected by the wake of upstream wind turbines), or consistent control strategies, and their operating characteristics are highly correlated.

[0023] In this embodiment, the number of wind turbines in the wind farm is large (ranging from dozens to hundreds). If all of them were simulated using a whole-machine model, the computational workload would be enormous. Therefore, this embodiment can use clustering algorithms (such as similarity analysis based on operating parameters and state information such as wind speed response, output power curves, and control modes) to group wind turbines with similar characteristics into the same wind turbine group (for example, wind turbines located upstream in the same wind direction and similarly affected by wakes can be clustered).

[0024] S104: Based on the operating parameters and status information of each wind turbine group in multiple wind turbine groups, determine the equivalent model parameters of each wind turbine group and construct the equivalent model of each wind turbine group.

[0025] In this embodiment, the equivalent model parameters are aggregated parameters used to characterize the overall characteristics of the wind turbine group. They are the result of simplifying and fusing the dispersed parameters of all wind turbines in the group. For example: equivalent rated power (the weighted average of the rated power of all wind turbines in the group); equivalent inertia (reflecting the impact of the total rotational inertia of the entire wind turbine group on the grid frequency); equivalent response time (the average response speed of the wind turbines in the group to changes in wind speed).

[0026] The equivalent model of a wind turbine cluster is a simplified model built based on the parameters of the equivalent model, which can represent the macroscopic operating characteristics of the entire wind turbine cluster. The purpose is to significantly reduce the complexity of the model while retaining the key impacts on external systems (such as the power grid), and it is suitable for large-scale simulation calculations at the wind farm level (such as full-field power prediction of hundreds of wind turbines and power grid stability analysis).

[0027] In this embodiment, for each wind turbine group, common characteristics of the turbines within the group (such as average output power, equivalent inertia, and overall impedance) are extracted, and multiple refined whole-machine models are "aggregated" into an equivalent model. The equivalent model of the wind turbine group needs to retain the overall impact of the wind turbine group on the external power grid or wind farm (such as power fluctuations and voltage response), while ignoring individual differences within the group (such as the minor vibrations of a single turbine). For example, principal component analysis is used to map the operating parameters of all turbines in the group to parameters such as equivalent rated power and equivalent pitch angle, ultimately constructing a simplified model that represents the macroscopic characteristics of the entire wind turbine group.

[0028] In this embodiment, the wind turbine whole-unit model can be used for scenarios requiring high-precision analysis (such as single wind turbine fault diagnosis and control strategy verification), while the wind turbine group equivalent model can be used for large-scale simulation at the wind farm level (such as grid stability analysis and full-field power dispatch). The combined use of the two different models ensures the accuracy of key details while improving the efficiency of large-scale simulation, achieving a balance between accuracy and efficiency.

[0029] As can be seen from the above, this embodiment achieves a balance between the accuracy and efficiency of wind farm simulation by constructing a simulation system that coordinates the overall wind turbine model and the equivalent model of the wind turbine group. The overall wind turbine model, based on the coupling of multiple sub-models, accurately captures the interaction of aerodynamics, structural mechanics, and electrical systems of a single wind turbine, and can accurately simulate details such as blade aerodynamic loads, structural vibrations, and electromechanical energy conversion, ensuring the accuracy of simulation under critical operating conditions. The equivalent model of the wind turbine group, on the other hand, is clustered and aggregated based on operating parameters, greatly simplifying the model complexity and efficiently handling the superposition of flow field wakes and electrical coordination characteristics of large-scale wind turbine clusters. The combined use of the two can accurately reflect the response of a single wind turbine in a complex flow field and quickly simulate the overall electrical dynamics of the wind farm, meeting the needs of multiple scenarios from single wind turbine fault diagnosis to overall power dispatching, and providing reliable support for wind farm design and operation and maintenance.

[0030] In one embodiment of this application, the multiple sub-models include an aerodynamic sub-model, a structural mechanics sub-model, and an electrical sub-model; By coupling and integrating multiple sub-models corresponding to each wind turbine, a complete wind turbine model corresponding to each wind turbine is obtained, including: For each wind turbine, determine the coupling relationship between multiple sub-models corresponding to that wind turbine. The coupling relationship includes the load transfer relationship between the aerodynamic sub-model and the structural mechanics sub-model, and the vibration-electrical response correlation between the structural mechanics sub-model and the electrical sub-model. Based on the coupling relationship between multiple sub-models corresponding to the wind turbine, a data interaction interface is established between the multiple sub-models. The data interaction interface is used to realize the data transmission between different sub-models during the simulation process. By integrating multiple sub-models based on the data interaction interface, the complete wind turbine model corresponding to the wind turbine is obtained.

[0031] In this embodiment, the aerodynamic sub-model calculates the aerodynamic loads (such as lift, drag, and torque) on the blade surface based on parameters such as wind speed and angle of attack. These loads are transferred to the structural mechanics sub-model as force boundary conditions, driving the elastic deformation and vibration of the blade and tower. For example, when the wind speed changes abruptly, the aerodynamic load increases sharply, triggering the structural mechanics sub-model to calculate the flapping and swaying responses of the blade through the load transfer relationship.

[0032] Vibration parameters calculated by the structural mechanics sub-model (such as the generator base vibration frequency and main shaft torque fluctuation) affect the electromagnetic conversion efficiency and power quality in the electrical sub-model. For example, excessive mechanical vibration may lead to uneven air gap in the generator, which in turn causes voltage fluctuations and power harmonics. This electromechanical coupling effect is quantified and transmitted through the vibration-electrical response correlation.

[0033] In this embodiment, the interface type can include a unidirectional data flow interface (e.g., aerodynamic load → structural stress) and a bidirectional feedback interface (e.g., blade deformation → aerodynamic angle of attack correction). The interface protocol needs to define the data format (e.g., floating-point array, time series), units (e.g., Newtons, meters), and transmission frequency (e.g., millisecond-level real-time transmission). The interface has a built-in buffer to handle differences in solution step sizes between different sub-models (e.g., the aerodynamic sub-model uses a 0.1-second step size, and the electrical sub-model uses a 0.001-second step size), and data synchronization is achieved through interpolation algorithms. For example, the vibration data of the structural mechanics sub-model at t=1 second needs to be interpolated to discrete point values ​​such as t=1.001 seconds and t=1.002 seconds required by the electrical sub-model.

[0034] In this embodiment, loose coupling can be used for slowly changing processes (such as load changes caused by gradual wind speed variations), with sub-models solving independently at their respective time steps and exchanging data periodically through an interface. For rapidly changing processes (such as electromechanical transients caused by power grid faults), tight coupling can be used, forcing all sub-models to iterate within the same time step to ensure data consistency. Within each solution step, the parameters passed through the interface must satisfy physical conservation laws (such as energy conservation and momentum conservation). For example, the aerodynamic power output by the aerodynamic sub-model and the mechanical power input by the electrical sub-model must converge within an error threshold (such as ±0.5%); otherwise, iterative correction is triggered.

[0035] As can be seen from the above, this embodiment achieves integration by clearly defining the load transfer and vibration-electrical response correlation between sub-models and constructing a data interaction interface, accurately capturing the multi-physics coupling effect inside the wind turbine. This ensures the coordinated feedback of aerodynamic, structural, and electrical characteristics in single wind turbine simulations and improves model integration efficiency through standardized interfaces.

[0036] In one embodiment of this application, wind turbines within a wind farm are clustered based on their corresponding operating parameters and status information to obtain multiple wind turbine groups, including: The weight of each wind turbine is determined based on its capacity within the wind farm. Based on the weights corresponding to each wind turbine, and based on the operating parameters and status information of each wind turbine, the wind turbines in the wind farm are clustered to obtain multiple wind turbine groups.

[0037] In this embodiment, the wind turbine capacity (rated power) can reflect its ability to impact the power grid. Larger capacity wind turbines play a more significant role in scenarios such as power fluctuations and fault ride-through, and therefore can be given higher weight.

[0038] This embodiment introduces a weighting factor into the distance calculation of traditional clustering algorithms (such as K-means). For example, when calculating the Euclidean distance between wind turbines i and j:

[0039] in, This represents the weighted Euclidean distance between wind turbines i and j. This represents the weight coefficient of the k-th parameter. and denoted as the kth operating parameter values ​​(such as power, wind speed, status indicators, etc.) for wind turbines i and j, respectively, and n represents the total number of parameters participating in the clustering.

[0040] Euclidean distance can be used to calculate the weighted sum of squares of the differences in different parameters and then take the square root, thus achieving a distance metric that takes into account the influence of wind turbine capacity. This ensures that wind turbines with larger capacities have higher decision weights in the clustering process.

[0041] Capacity-weighted clustering can distinguish large-capacity wind turbines from small-capacity turbines operating under the same conditions, forming a more rational turbine group. For example, turbines with similar grid support capabilities can be grouped together, facilitating the unified formulation of frequency and voltage regulation strategies; turbines with similar capacities can be grouped together, reducing parameter errors in equivalent models and improving the accuracy of group-level simulations; and the "average effect" caused by mixed clustering of large-capacity and small-capacity turbines can be avoided, better reflecting the actual power fluctuation characteristics.

[0042] The wind turbine clusters obtained by capacity weight clustering have smaller differences in the capacity of the turbines within them. When constructing the equivalent model, parameter calculation can be simplified (e.g., the equivalent power can be directly taken as the capacity weighted average). At the same time, the overall impact characteristics of the turbines in the cluster on the power grid are preserved, and the mapping accuracy from the whole turbine model to the cluster model is improved.

[0043] As can be seen from the above, this embodiment optimizes clustering by introducing wind turbine capacity weights, making the wind turbine group division more closely reflect engineering realities. Larger capacity wind turbines receive higher weights in clustering decisions, avoiding simple averaging with smaller capacity turbines and improving the consistency of characteristics among similar turbines. This ensures the accuracy of equivalent model parameters while reflecting the differences in the impact of wind turbines of different capacities on the power grid, providing a more reliable grouping basis for wind farm simulation and scheduling.

[0044] In one embodiment of this application, the wind farm simulation model construction method further includes, before obtaining multiple wind turbine clusters: The weights of each wind turbine are updated based on the degree of wake influence of each wind turbine, resulting in new weights for each wind turbine. Based on the weights associated with each wind turbine and their corresponding operating parameters and status information, the wind turbines within the wind farm are clustered to obtain multiple wind turbine groups, including: Based on the new weights corresponding to each wind turbine, and based on the operating parameters and status information of each wind turbine, the wind turbines in the wind farm are clustered to obtain multiple wind turbine groups.

[0045] In this embodiment, the wake effect refers to the phenomenon where, when a wind turbine absorbs wind energy to generate electricity, a wake region is formed downstream due to energy loss, resulting in reduced wind speed and enhanced turbulence, which in turn leads to a decrease in the power generation efficiency of the downstream wind turbine. Therefore, the wake effect can alter the actual operating characteristics of the wind turbine.

[0046] In this embodiment, the degree of influence of wake on each wind turbine can be calculated using a wake model (such as the Jensen model). For example, if a downstream wind turbine loses 10% of its power generation due to wake, its wake influence coefficient is adjusted to 1.1. This coefficient is then integrated with the original capacity weight to obtain a new weight, allowing wind turbines that are strongly affected by wake interference to obtain a more suitable weight in clustering.

[0047] During clustering, the operating parameters and status information of the wind turbines are used as clustering features. Combined with the updated weights, the similarity of the wind turbines is measured by a weighted distance algorithm (such as weighted K-Means, which uses the new weights to weight the differences of different features when calculating the distance between wind turbines).

[0048] For example, wind turbines with large capacity and strong wake effects have higher weight in distance calculations due to differences in parameters such as power and wind speed. This promotes the clustering of wind turbines with similar characteristics (such as consistent wake patterns and synchronized operating states) into the same group, so that cluster division considers both the scale of equipment capacity and the physical scenario of wake interaction in wind farms.

[0049] As can be seen from the above, this embodiment, by introducing the wake effect to dynamically adjust the wind turbine weights, avoids the misclassification of wind turbines with similar capacities but vastly different wake effects in traditional clustering, and makes wind turbines of the same type more consistent in terms of flow field response and power characteristics. The generated equivalent model of the wind turbine group can more accurately reflect the power fluctuations and cooperative characteristics caused by the wake, providing a grouping basis that is more in line with the actual physical scenario for wind farm simulation.

[0050] In one embodiment of this application, the method further includes: determining the wake influence of each wind turbine based on a first formula; The first formula is:

[0051] in, Indicates the downstream wind speed. This indicates the wind speed of the upstream flow. This represents the wake attenuation coefficient. Indicates the diameter of the upstream wind turbine. Indicates the wake diffusion coefficient. This indicates the distance between the upstream and downstream wind turbines. This represents the correction factor.

[0052] In a wind farm, after the upstream wind turbines capture wind energy, a wake region with reduced wind speed is formed downstream. (Upstream wind speed) After passing through the wind turbine, the downstream wind speed decreases due to the wind energy captured by the blades. attenuation.

[0053] In this embodiment, the upstream incoming wind speed is the base wind speed at the wind farm inlet or in the undisturbed area, serving as the initial input for wake calculation and determining the total wind energy that the upstream turbines can capture. The diameter of the upstream turbines is directly related to the initial influence range of the wake (the larger the diameter, the larger the initial wake coverage area, and the wider the reference area for downstream wind speed attenuation). The wake diffusion coefficient reflects the rate of wake diffusion with distance and is related to atmospheric stability and topography (e.g., a larger k under complex terrain results in faster wake diffusion). The distance between the upstream and downstream turbines determines the degree of wake diffusion, as shown in the formula. This reflects the equivalent range of effect after wake diffusion; as x increases, this value increases, along with the wind speed attenuation term. Reduce; the wake attenuation coefficient measures the wind turbine's efficiency in capturing wind energy and is related to the turbine's power coefficient Cp ( Correction factor In this embodiment, a correction coefficient is used to calibrate deviations between the model and actual measurements (such as terrain occlusion, wind turbine layout, etc.). It can be represented as:

[0054] in, Indicates the number of upstream wind turbines; This represents the weighting coefficient of the i-th upstream wind turbine; This represents the distance attenuation factor, which can be determined experimentally. This represents the relative distance between the downstream point and the i-th wind turbine.

[0055] From the above, it can be concluded that by introducing a cluster correction coefficient... It comprehensively considers the wake superposition effect of multiple upstream wind turbines in the wind farm (rather than the influence of a single wind turbine), so that the wake calculation can reflect both the wake characteristics of a single wind turbine and the wake interaction under the operation of the wind farm cluster, which is more in line with the actual scenario of large-scale wind farms.

[0056] In one embodiment of this application, based on the operating parameters and status information of each wind turbine group in multiple wind turbine groups, the equivalent model parameters corresponding to each wind turbine group are determined, and the equivalent model of each wind turbine group is constructed, including: The operating parameters and status information are preprocessed to obtain the initial model data; the preprocessing includes data cleaning and normalization. The target model data is obtained by extracting features from the initial model data based on principal component analysis. Based on the target model data and the preset mapping relationship, the equivalent model parameters corresponding to each wind turbine group are determined, and the equivalent model of each wind turbine group is constructed.

[0057] In this embodiment, outliers (such as sudden data changes caused by sensor malfunctions) and missing values ​​in the filter fan's operating parameters are filled by interpolation or fitting historical data to ensure the reliability of the original data. For example, if a fan's power suddenly jumps to a negative value, it is replaced with a smoothed value from an adjacent time period after cleaning.

[0058] Mapping multi-dimensional parameters (such as wind speed, power, and temperature) to a unified scale eliminates the interference of dimensional differences on subsequent analysis.

[0059] Extracting the most representative low-dimensional features from high-dimensional initial data preserves key information while reducing computational complexity. For example, 20+ parameters such as wind speed, wind direction, power, and temperature can be compressed into 3-5 principal components. First, the correlation between parameters is analyzed; for instance, wind speed and power are usually strongly positively correlated. Then, the direction with the largest data variance (i.e., the principal component) is determined. For example, the first principal component might represent "wind energy capture efficiency," which integrates parameters such as wind speed and blade angle. Finally, principal components with a cumulative contribution rate exceeding 85% (such as the first three principal components) are retained, while minor components are discarded.

[0060] In this embodiment, the correspondence between principal components and equivalent model parameters is established through mechanistic analysis or training with historical data. For example: The first principal component (wind energy capture efficiency) corresponds to the equivalent rated power; The second principal component (dynamic response characteristics) corresponds to the equivalent inertial time constant; The third principal component (control mode) corresponds to the equivalent frequency modulation coefficient; Substitute the target model data of the wind turbine group into the mapping relationship to solve for the equivalent parameters.

[0061] As can be seen from the above, by combining data-driven approaches with mechanistic modeling, an automated conversion from massive operational data to physically equivalent models has been achieved. The pre-defined mapping relationships ensure the physical interpretability of the equivalent parameters, providing an efficient and reliable cluster-level modeling solution for wind farm simulation.

[0062] In one embodiment of this application, the wind farm simulation model construction method further includes: The target wind farm simulation model is determined based on the complexity of the input simulation variables. The target wind farm simulation model is either a complete wind turbine model or an equivalent model of a wind turbine group. The target wind farm simulation model is determined based on the complexity of the input simulation variables, including: The complexity of determining the input simulation variables is based on the number of input variables and the number of wind turbines. In response to the complexity of the input simulation variables exceeding the complexity threshold, the wind turbine model is used as the target wind farm simulation model. In response to the complexity of the input simulation variables being less than or equal to the complexity threshold, the equivalent model of the wind turbine group is used as the target wind farm simulation model.

[0063] In this embodiment, the number of input variables refers to the number of parameter types involved in the simulation. For example, only basic environmental parameters such as wind speed and wind direction are input (few), or multiple parameters such as wind speed, blade pitch angle, power grid frequency, and fault type are input simultaneously (numerous).

[0064] The number of wind turbines for which input variables apply refers to the range of wind turbines on which the parameters apply. For example, it may be a local parameter for a single wind turbine (such as the blade damage status of a certain wind turbine), or a differentiated parameter for all 50 wind turbines in the field (such as the wake interference coefficient of each wind turbine).

[0065] By combining these two dimensions, the complexity of the simulation scenario can be quantified. For example: Low complexity scenario: Few input variables (only wind speed and wind direction) and uniform parameters for the entire field (all wind turbines share the same wind speed).

[0066] High complexity scenarios: There are many input variables (wind speed, fault type, pitch angle command) and differentiated parameters for a single or a few wind turbines (such as gearbox fault parameters for 3 specific wind turbines).

[0067] The complexity threshold is a preset quantitative standard (such as one set based on simulation accuracy requirements or computational resource limits) used to classify scenario types: when the number of input variables is large and the number of wind turbines is dispersed (i.e., the complexity exceeds the threshold), it indicates that the simulation needs to capture the detailed response of a single wind turbine (such as fault propagation and local flow field disturbances). When the input variables are simple and the range of wind turbines is uniform (i.e., the complexity is lower than or equal to the threshold), it indicates that the simulation focuses on the overall characteristics of the wind farm (such as total power output and grid stability).

[0068] When the complexity exceeds the threshold, the whole wind turbine model must be used. Because the whole model is composed of aerodynamic, structural mechanics, electrical and other sub-models, it can accurately simulate the detailed characteristics of a single wind turbine (such as the impact of blade vibration on power and the fault response of the converter), and is suitable for analyzing local complex operating conditions (such as the impact of a single wind turbine failure on the surrounding area and the flow field interaction under complex terrain).

[0069] When the complexity is below or equal to the threshold, the equivalent model of the wind turbine group can be enabled. Because the equivalent model simplifies the individual differences of wind turbines within the group through clustering, it retains only macroscopic characteristics (such as average power within the group and equivalent inertia), which can significantly reduce the amount of computation and is suitable for quickly simulating large-scale scenarios (such as power fluctuations of the entire field under typhoon weather and grid frequency regulation response).

[0070] As can be seen from the above, this embodiment selects the model by inputting the complexity of the simulation variables. When the simulation is complex, the whole wind turbine model is used to ensure accuracy, while when it is simple, the equivalent model of the wind turbine group is used to improve efficiency. This balances the simulation accuracy and efficiency, meets the needs of multiple scenarios, provides more reliable support for wind farm design and operation and maintenance, and improves the applicability and practicality of the simulation.

[0071] Corresponding to the wind farm simulation model construction method in the above embodiment, Figure 2 This is a structural block diagram of a wind farm simulation model construction system provided in one embodiment of this application. For ease of explanation, only the parts relevant to the embodiment of this application are shown. References Figure 2 The wind farm simulation model building system 20 includes: a sub-model building module 21, a first model building module 22, a clustering module 23, and a second model building module 24.

[0072] Among them, the sub-model construction module 21 is used to construct multiple sub-models corresponding to each wind turbine in the wind farm. The multiple sub-models are constructed based on the aerodynamic data, structural mechanics data and electrical data corresponding to each wind turbine. The multiple sub-models are used to represent the operating parameters and status information corresponding to each wind turbine. The first model construction module 22 is used to couple and integrate multiple sub-models corresponding to each wind turbine to obtain the complete wind turbine model corresponding to each wind turbine. Clustering module 23 is used to cluster the wind turbines in the wind farm based on the operating parameters and status information of each wind turbine, so as to obtain multiple wind turbine groups; The second model construction module 24 is used to determine the equivalent model parameters corresponding to each wind turbine group based on the operating parameters and status information of each wind turbine group in multiple wind turbine groups, and to construct the equivalent model of each wind turbine group. Both the complete wind turbine model and the equivalent model of the wind turbine group are used to simulate wind farms.

[0073] In one embodiment of this application, the first model building module 22 is specifically used for: For each wind turbine, determine the coupling relationship between multiple sub-models corresponding to that wind turbine. The coupling relationship includes the load transfer relationship between the aerodynamic sub-model and the structural mechanics sub-model, and the vibration-electrical response correlation between the structural mechanics sub-model and the electrical sub-model. Based on the coupling relationship between multiple sub-models corresponding to the wind turbine, a data interaction interface is established between the multiple sub-models. The data interaction interface is used to realize the data transmission between different sub-models during the simulation process. By integrating multiple sub-models based on the data interaction interface, the complete wind turbine model corresponding to the wind turbine is obtained; Multiple sub-models include an aerodynamic sub-model, a structural mechanics sub-model, and an electrical sub-model.

[0074] In one embodiment of this application, the clustering module 23 is specifically used for: The weight of each wind turbine is determined based on its capacity within the wind farm. Based on the weights corresponding to each wind turbine, and based on the operating parameters and status information of each wind turbine, the wind turbines in the wind farm are clustered to obtain multiple wind turbine groups.

[0075] In one embodiment of this application, the wind farm simulation model construction system 20 further includes a weight update module, specifically used to update the weights corresponding to each wind turbine based on the wake influence of each wind turbine, so as to obtain new weights corresponding to each wind turbine. Clustering module 23 is also specifically used for: Based on the new weights corresponding to each wind turbine, and based on the operating parameters and status information of each wind turbine, the wind turbines in the wind farm are clustered to obtain multiple wind turbine groups.

[0076] In one embodiment of this application, the weight update module is further configured to: The degree of wake impact of each wind turbine is determined based on the first formula; The first formula is:

[0077] in, Indicates the downstream wind speed. This indicates the wind speed of the upstream flow. This represents the wake attenuation coefficient. Indicates the diameter of the upstream wind turbine. Indicates the wake diffusion coefficient. This indicates the distance between the upstream and downstream wind turbines. This represents the correction factor.

[0078] In one embodiment of this application, the second model building module 24 is specifically used for: The operating parameters and status information are preprocessed to obtain the initial model data; the preprocessing includes data cleaning and normalization. The target model data is obtained by extracting features from the initial model data based on principal component analysis. Based on the target model data and the preset mapping relationship, the equivalent model parameters corresponding to each wind turbine group are determined, and the equivalent model of each wind turbine group is constructed.

[0079] In one embodiment of this application, the wind farm simulation model construction system 20 further includes: a selection module, specifically used for: The target wind farm simulation model is determined based on the complexity of the input simulation variables. The target wind farm simulation model is either a complete wind turbine model or an equivalent model of a wind turbine group. The target wind farm simulation model is determined based on the complexity of the input simulation variables, including: The complexity of determining the input simulation variables is based on the number of input variables and the number of wind turbines. In response to the complexity of the input simulation variables exceeding the complexity threshold, the wind turbine model is used as the target wind farm simulation model. In response to the complexity of the input simulation variables being less than or equal to the complexity threshold, the equivalent model of the wind turbine group is used as the target wind farm simulation model.

[0080] See Figure 3 , Figure 3 This is a schematic block diagram of an electronic device provided according to an embodiment of this application. Figure 3 The electronic device 300 in this embodiment may include one or more processors 301, one or more input devices 302, one or more output devices 303, and one or more memories 304. The processors 301, input devices 302, output devices 303, and memories 304 communicate with each other via a communication bus 305. The memories 304 store computer programs, including program instructions. The processors 301 execute the program instructions stored in the memories 304. Specifically, the processors 301 are configured to invoke the program instructions to perform the functions of the modules in the aforementioned system embodiments, for example... Figure 2 The functions of the sub-model building module 21, the first model building module 22, the clustering module 23, and the second model building module 24 are shown.

[0081] It should be understood that, in the embodiments of this application, the processor 301 may be a central processing unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0082] Input device 302 may include a touchpad, a fingerprint sensor (for collecting the user's fingerprint information and fingerprint orientation information), a microphone, etc., and output device 303 may include a display (LCD, etc.), a speaker, etc.

[0083] The memory 304 may include read-only memory and random access memory, and provides instructions and data to the processor 301. A portion of the memory 304 may also include non-volatile random access memory. For example, the memory 304 may also store information such as sub-models and wind turbine clusters.

[0084] In specific implementations, the processor 301, input device 302, and output device 303 described in the embodiments of this application can execute the implementation method described in the wind farm simulation model construction method provided in the embodiments of this application, or they can execute the implementation method of the electronic device described in the embodiments of this application, which will not be repeated here.

[0085] In another embodiment of this application, a computer-readable storage medium is provided. This computer-readable storage medium stores a computer program, which includes program instructions. When executed by a processor, the program instructions implement all or part of the processes in the methods described above. Alternatively, the computer program can instruct related hardware to implement these processes. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include any entity or system capable of carrying computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0086] The computer-readable storage medium can be an internal storage unit of the electronic device in any of the foregoing embodiments, such as a hard disk or memory of the electronic device. The computer-readable storage medium can also be an external storage device of the electronic device, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the electronic device. Furthermore, the computer-readable storage medium can include both internal and external storage units of the electronic device. The computer-readable storage medium is used to store computer programs and other programs and data required by the electronic device. The computer-readable storage medium can also be used to temporarily store data that has been output or will be output.

[0087] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this application.

[0088] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the electronic devices and units described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0089] In the several embodiments provided in this application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connections shown or discussed may be indirect coupling or communication connections through some interfaces or units, or they may be electrical, mechanical, or other forms of connection.

[0090] The units described as separate components may or may not be physically separate. 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 units can be selected to achieve the purpose of the embodiments of this application, depending on actual needs.

[0091] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing unit, or each module can exist physically separately, or two or more modules can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0092] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for constructing a wind farm simulation model, characterized in that, include: Multiple sub-models are constructed for each wind turbine in the wind farm. These multiple sub-models are constructed based on the aerodynamic data, structural mechanics data, and electrical data of each wind turbine. The multiple sub-models are used to represent the operating parameters and status information of each wind turbine; The multiple sub-models corresponding to each wind turbine are coupled and integrated to obtain the complete wind turbine model corresponding to each wind turbine. Based on the operating parameters and status information corresponding to each wind turbine, the wind turbines in the wind farm are clustered to obtain multiple wind turbine groups. Based on the operating parameters and status information of each wind turbine group in multiple wind turbine groups, the equivalent model parameters of each wind turbine group are determined, and the equivalent model of each wind turbine group is constructed. Both the complete wind turbine model and the equivalent model of the wind turbine group are used to simulate wind farms.

2. The wind farm simulation model construction method as described in claim 1, characterized in that, The multiple sub-models include an aerodynamic sub-model, a structural mechanics sub-model, and an electrical sub-model; The process of coupling and integrating multiple sub-models corresponding to each wind turbine to obtain a complete wind turbine model for each wind turbine includes: For each wind turbine, determine the coupling relationship between multiple sub-models corresponding to that wind turbine. The coupling relationship includes the load transfer relationship between the aerodynamic sub-model and the structural mechanics sub-model, and the vibration-electrical response correlation between the structural mechanics sub-model and the electrical sub-model. Based on the coupling relationship between multiple sub-models corresponding to the wind turbine, a data interaction interface is established between the multiple sub-models. The data interaction interface is used to realize the data transmission between different sub-models during the simulation process. Based on the data interaction interface, multiple sub-models are integrated to obtain the complete wind turbine model corresponding to the wind turbine.

3. The wind farm simulation model construction method as described in claim 1, characterized in that, The wind turbines in the wind farm are clustered based on their respective operating parameters and status information to obtain multiple wind turbine groups, including: The weight of each wind turbine is determined based on its capacity within the wind farm. Based on the weights corresponding to each wind turbine, and based on the operating parameters and status information corresponding to each wind turbine, the wind turbines in the wind farm are clustered to obtain multiple wind turbine groups.

4. The wind farm simulation model construction method as described in claim 3, characterized in that, Before acquiring multiple wind turbine clusters, it also included: The weights of each wind turbine are updated based on the degree of wake influence of each wind turbine, resulting in new weights for each wind turbine. The wind turbines in the wind farm are clustered based on their respective weights and the operating parameters and status information, resulting in multiple wind turbine groups, including: Based on the new weights corresponding to each wind turbine, and based on the operating parameters and status information corresponding to each wind turbine, the wind turbines in the wind farm are clustered to obtain multiple wind turbine groups.

5. The wind farm simulation model construction method as described in claim 4, characterized in that, Also includes: The degree of wake impact of each wind turbine is determined based on the first formula; The first formula is: in, Indicates the downstream wind speed. This indicates the wind speed of the upstream flow. This represents the wake attenuation coefficient. Indicates the diameter of the upstream wind turbine. Indicates the wake diffusion coefficient. This indicates the distance between the upstream and downstream wind turbines. This represents the correction factor.

6. The wind farm simulation model construction method as described in claim 1, characterized in that, The process of determining the equivalent model parameters for each wind turbine group based on the operating parameters and status information of each wind turbine group in multiple wind turbine groups, and constructing the equivalent model for each wind turbine group, includes: The operating parameters and the status information are preprocessed to obtain initial model data; the preprocessing includes data cleaning and normalization. The initial model data is used to extract features based on principal component analysis to obtain the target model data. Based on the target model data and the preset mapping relationship, the equivalent model parameters corresponding to each wind turbine group are determined, and the equivalent model of each wind turbine group is constructed.

7. The wind farm simulation model construction method as described in claim 1, characterized in that, Also includes: The target wind farm simulation model is determined based on the complexity of the input simulation variables. The target wind farm simulation model is either a complete wind turbine model or an equivalent model of a wind turbine group. The target wind farm simulation model is determined based on the complexity of the input simulation variables, including: The complexity of determining the input simulation variables is based on the number of input variables and the number of wind turbines. In response to the complexity of the input simulation variables being greater than the complexity threshold, the wind turbine model is used as the target wind farm simulation model. In response to the complexity of the input simulation variables being less than or equal to a complexity threshold, the equivalent model of the wind turbine group is used as the target wind farm simulation model.

8. A wind farm simulation model construction system, characterized in that, include: The sub-model construction module is used to construct multiple sub-models corresponding to each wind turbine in the wind farm. The multiple sub-models are constructed based on the aerodynamic data, structural mechanics data and electrical data corresponding to each wind turbine. The multiple sub-models are used to represent the operating parameters and status information of each wind turbine. The first model construction module is used to couple and integrate multiple sub-models corresponding to each wind turbine to obtain the complete wind turbine model corresponding to each wind turbine. The clustering module is used to cluster the wind turbines in the wind farm based on the operating parameters and status information corresponding to each wind turbine, so as to obtain multiple wind turbine groups. The second model construction module is used to determine the equivalent model parameters corresponding to each wind turbine group based on the operating parameters and status information of each wind turbine group in multiple wind turbine groups, and to construct the equivalent model of each wind turbine group. Both the complete wind turbine model and the equivalent model of the wind turbine group are used to simulate wind farms.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 7.

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

Images