Wind turbine yaw error correction method, device, equipment and medium

Abstract

The present application relates to the field of wind power generation technology, and more particularly to a wind turbine yaw error correction method, device, equipment and medium, the method obtains the real-time environment and the running information of the unit; then, based on the built-in wind direction yaw calculation model, the accurate yaw compensation amount for offsetting the environmental disturbance is obtained; then, the compensation amount is input into the multi-objective optimization strategy for global planning to generate a smooth instruction sequence; finally, the sequence is executed to drive the yaw system to complete accurate wind alignment. The whole process forms a closed-loop control from perception, decision-making to execution. This scheme can consider the balance between power generation efficiency and mechanical load, avoiding frequent or violent yaw action. Not only can effectively improve the energy capture efficiency of the unit, but also can significantly reduce the mechanical wear of the yaw system, and finally realize the cooperative optimization of the operation reliability and economy of the wind turbine in the whole life cycle.

Description

Technical Field

[0001] This invention relates to the field of wind power generation technology, and in particular to a method, device, equipment and medium for correcting yaw error of wind turbine generator sets. Background Technology

[0002] Wind turbine generators are the core equipment for converting wind energy, and their power generation efficiency directly affects the economic benefits of wind power projects. Theoretically, the swept surface of the turbine rotor should always be perpendicular to the incoming wind direction to maximize wind energy capture. This process relies on the precise wind control of the yaw system.

[0003] Currently, wind turbines generally rely on a weather vane installed at the rear of the nacelle to sense wind direction and drive the yaw system accordingly. However, this traditional method faces significant challenges in complex terrain areas such as hills and mountains. Due to topographical obstacles such as undulating terrain, mountains, and forests, the local flow field near the wind turbine is severely distorted, resulting in a significant deviation between the wind direction measured by the weather vane and the actual free-flowing wind direction acting on the entire rotor. To address this problem, existing technologies have employed compensation schemes based on historical data or initial simulations with fixed offset angles, but these schemes lack adaptability.

[0004] Therefore, how to achieve real-time, dynamic, and adaptive compensation for wind turbine generator set wind deflection error under complex terrain conditions in order to improve the wind alignment accuracy and power generation efficiency of the unit has become a technical problem that the industry urgently needs to solve. Summary of the Invention

[0005] The main objective of this invention is to provide a method, device, equipment, and medium for correcting the yaw error of a wind turbine generator set. The aim is to solve the technical problem in the prior art of how to achieve real-time, dynamic, and adaptive compensation for the yaw error of a wind turbine generator set under complex terrain conditions in order to improve the wind alignment accuracy and power generation efficiency of the unit.

[0006] To achieve the above objectives, the present invention provides a method for correcting the yaw error of a wind turbine generator set, the method comprising the following steps: To obtain real-time environmental and operational information of wind turbine generators; Based on the real-time environmental information, unit operation information, and wind direction yaw calculation model, the yaw compensation amount required to offset environmental disturbances is obtained. Based on the yaw compensation amount and the preset multi-objective optimization strategy, a yaw compensation command sequence is generated; The yaw compensation command sequence is executed to drive the yaw system to correct for wind yaw errors caused by complex terrain.

[0007] Optionally, the step of obtaining the yaw compensation amount required to offset environmental disturbances based on the real-time environmental information, unit operating information, and wind direction yaw calculation model includes: The flow field characteristics and static terrain information in the real-time environmental information are input into the wind direction yaw calculation model to obtain the wind yaw vector caused by the terrain where the unit is located; The actual wind direction angle is obtained based on the wind yaw vector and the current yaw angle in the unit operation information; The opposite angle of the actual wind direction angle is used as the yaw compensation amount.

[0008] Optionally, acquiring the real-time environmental information and unit operation information of the wind turbine generator includes: Acquire real-time environmental information, including flow field characteristic information in front of the unit collected by the front-end wind measurement equipment and static terrain information from the geographic information system; Obtain unit operation information, which includes the generator power, rotor speed and current yaw angle of the wind turbine generator set.

[0009] Optionally, generating a yaw compensation command sequence based on the yaw compensation amount and a preset multi-objective optimization strategy includes: The yaw compensation amount and the current unit operating status information are input into a preset yaw action planning model to generate a preliminary yaw action sequence. Obtain a multi-objective optimization function, and evaluate and correct the initial yaw action sequence based on the multi-objective optimization function to obtain a corrected yaw action sequence; The corrected yaw action sequence is subjected to smoothing filtering, and the yaw compensation command sequence is generated based on the filtering result.

[0010] Optionally, the step of obtaining a multi-objective optimization function and evaluating and correcting the initial yaw action sequence based on the multi-objective optimization function to obtain a corrected yaw action sequence includes: Construct a comprehensive cost function that includes the equivalent wear cost of the yaw bearing, the operation and maintenance cost of the yaw system, and the power generation loss; Based on the yaw compensation amount and the real-time status of the crew, a multi-step yaw action prediction sequence within the future time window is generated in a rolling manner, and the corresponding comprehensive cost function value is calculated based on the prediction sequence. Adjust the step size and timing of the initial yaw action sequence until the comprehensive cost function value meets the preset optimization convergence condition to obtain the corrected yaw action sequence.

[0011] Optionally, the step of generating a multi-step yaw action prediction sequence within a future time window based on the yaw compensation amount and the real-time status of the crew includes: The wind deflection vector is input into a local flow field disturbance model based on computational fluid dynamics to predict the equivalent wind direction deflection disturbance sequence caused by the terrain within a preset time window; The equivalent wind direction deflection disturbance sequence is superimposed with the yaw compensation amount and used as input to the yaw action planning model to generate the multi-step yaw action prediction sequence.

[0012] Optionally, the wind turbine generator yaw error correction method further includes: After executing the yaw compensation command sequence, the actual output power of the wind turbine generator and the load data of the key mechanical components of the yaw system are collected to form a feedback information set. The feedback information set is compared with the expected performance indicators based on the wind direction yaw calculation model and multi-objective optimization strategy to generate the correction amount of the model and strategy. Based on the correction amount, the flow field-wind yaw mapping relationship in the wind direction yaw calculation model and / or the weight of the comprehensive cost function in the multi-objective optimization strategy are corrected until the comprehensive evaluation index meets the preset iteration termination condition. The comprehensive evaluation index includes unit operating efficiency and mechanical load.

[0013] Furthermore, to achieve the above objectives, the present invention also proposes a yaw error correction device for a wind turbine generator set, the wind turbine generator set yaw error correction device comprising: The information acquisition module is used to acquire real-time environmental information and unit operation information of the wind turbine generator set; The compensation calculation module is used to obtain the yaw compensation amount required to offset environmental disturbances based on the real-time environmental information, unit operation information and wind direction yaw calculation model. The optimization decision module is used to generate a yaw compensation instruction sequence based on the yaw compensation amount and a preset multi-objective optimization strategy; The correction execution module is used to execute the yaw compensation command sequence to drive the yaw system to correct the wind yaw error caused by complex terrain.

[0014] Furthermore, to achieve the above objectives, the present invention also proposes a wind turbine yaw error correction device, which includes: a memory, a processor, and a wind turbine yaw error correction program stored in the memory and executable on the processor. The wind turbine yaw error correction program is configured to implement the steps of the wind turbine yaw error correction method described above.

[0015] In addition, to achieve the above objectives, the present invention also proposes a storage medium storing a wind turbine yaw error correction program, wherein when the wind turbine yaw error correction program is executed by a processor, the steps of the wind turbine yaw error correction method described above are implemented.

[0016] The present application proposes one or more technical solutions, which have at least the following technical effects: This application acquires real-time environmental and operational information of the wind turbine; subsequently, based on a built-in wind direction and yaw calculation model, it analyzes and derives the precise yaw compensation amount to offset environmental disturbances; then, it inputs the compensation amount into a multi-objective optimization strategy for global planning, generating a stable command sequence; finally, it executes this sequence to drive the yaw system to achieve precise wind alignment. The entire process forms a closed-loop control from perception and decision-making to execution. This solution can comprehensively consider the balance between power generation efficiency and mechanical load, avoiding frequent or drastic yaw actions. It not only effectively improves the energy capture efficiency of the unit but also significantly reduces the mechanical wear of the yaw system, ultimately achieving synergistic optimization of the reliability and economy of the wind turbine throughout its entire life cycle. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

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

[0019] Figure 1 This is a flowchart illustrating the first embodiment of the wind turbine generator yaw error correction method of the present invention. Figure 2 This is a flowchart illustrating the second embodiment of the wind turbine generator yaw error correction method of the present invention. Figure 3 This is a structural block diagram of the first embodiment of the wind turbine generator yaw error correction device of the present invention; Figure 4 This is a schematic diagram of the structure of the wind turbine generator yaw error correction device in the hardware operating environment involved in the embodiments of the present invention.

[0020] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0021] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0022] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods. The main solution of this application embodiment is: acquiring real-time environmental information and unit operation information of the wind turbine generator set; based on the real-time environmental information, unit operation information, and wind direction yaw calculation model, obtaining the yaw compensation amount required to offset environmental disturbances; generating a yaw compensation command sequence according to the yaw compensation amount and a preset multi-objective optimization strategy; and executing the yaw compensation command sequence to drive the yaw system to correct wind yaw errors caused by complex terrain.

[0023] Currently, wind turbines generally rely on a weather vane installed at the rear of the nacelle to sense wind direction and drive the yaw system accordingly. However, this traditional method faces significant challenges in complex terrain areas such as hills and mountains. Due to topographical obstacles such as undulating terrain, mountains, and forests, the local flow field near the wind turbine is severely distorted, resulting in a significant deviation between the wind direction measured by the weather vane and the actual free-flowing wind direction acting on the entire rotor. To address this issue, existing technologies have adopted schemes that use historical data or initial simulations to set a fixed offset angle for compensation, but their adaptability is insufficient. Therefore, how to achieve real-time, dynamic, and adaptive compensation for wind turbine yaw errors under complex terrain conditions to improve the turbine's wind alignment accuracy and power generation efficiency is a pressing technical problem that needs to be solved.

[0024] It should be noted that the executing entity of this invention can be a wind turbine yaw error correction device, or a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone. This embodiment does not specifically limit it in this way. The following uses a wind turbine yaw error correction device as the executing entity to describe this embodiment and the following embodiments.

[0025] Based on this, embodiments of this application provide a method for correcting the yaw error of a wind turbine generator set, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the wind turbine generator yaw error correction method of this application.

[0026] In this embodiment, the yaw error correction method for the wind turbine generator set includes steps S10 to S40: Step S10: Obtain real-time environmental information and unit operation information of the wind turbine generator set.

[0027] It should be noted that the real-time environmental information in this step refers to the dynamic parameters of the external flow field of the wind turbine generator set. Specifically, this includes the flow field characteristic information in front of the generator set collected by the front-end anemometer and the static terrain information from the geographic information system. Its function is to reflect the actual incoming wind direction and speed acting on the rotor plane. It is usually collected by the front-end anemometer device installed on the generator set, such as lidar or acoustic radar. The generator set operation information refers to the feedback data of the wind turbine generator set's own operating status, such as the rotor speed measured by the encoder, the current power output of the generator, and the actual angle position of the yaw system.

[0028] Understandably, the essence of this step is to build a comprehensive and accurate real-time wind field perception system. Since wind conditions change rapidly, especially due to turbulence and sudden changes in wind direction caused by complex terrain, only by obtaining the latest data can the effectiveness and timeliness of subsequent calculations and compensations be ensured.

[0029] It should be understood that this process requires synchronous data acquisition from multiple sensor sources, followed by preprocessing such as filtering, noise reduction, and timestamp alignment to ensure data consistency and reliability. Its ultimate goal is to provide high-quality, high-reliability input for subsequent steps, serving as a prerequisite for the correct initiation and effective execution of the entire calibration process.

[0030] Step S20: Based on the real-time environmental information, unit operation information, and wind direction yaw calculation model, obtain the yaw compensation amount required to offset environmental disturbances.

[0031] It should be noted that the wind yaw calculation model refers to a specifically trained data-driven model whose core function is to establish a nonlinear mapping relationship between real-time wind conditions, terrain features, and wind direction deviation. This model uses real-time environmental information acquired in the previous step, such as flow field disturbance characteristics detected by forward radar, the location and height of terrain obstacles provided by the geographic information system, and the current cabin wind direction and speed from the crew operation information, as inputs. Through an internal algorithm, it outputs a precise wind yaw vector, which quantifies the angular difference between the actual incoming wind direction caused by factors such as terrain and the wind direction measured in the cabin.

[0032] Understandably, the purpose of this step is to transform the raw data captured by environmental perception into compensation commands with clear control significance. For example, when the model identifies a mountain to the southwest of the wind turbine and the current wind direction is westerly, it will calculate the wind direction deflection angle caused by the flow around the mountain due to the learned fluid dynamics laws. This angle is the yaw compensation amount that needs to be compensated to ensure that the wind turbine plane is aligned with the actual effective wind direction after the terrain disturbance.

[0033] It should be understood that the calculation of yaw compensation is an intelligent inference process that integrates multiple factors. By integrating static terrain data with dynamic flow field information, this model can dynamically adapt to the impact of wind speed changes and wind direction fluctuations on the wind yaw angle, thus overcoming the limitations of traditional fixed offset compensation. This allows the compensation amount to accurately reflect the actual disturbance under the current instantaneous operating conditions, providing an accurate and reliable basis for subsequent optimization decisions.

[0034] In one embodiment, obtaining the yaw compensation amount required to offset environmental disturbances based on the real-time environmental information, unit operation information, and wind direction yaw calculation model includes: inputting the flow field characteristic information and static terrain information from the real-time environmental information into the wind direction yaw calculation model to obtain the wind deflection vector caused by the terrain where the unit is located; obtaining the actual wind direction angle based on the wind deflection vector and the current yaw angle in the unit operation information; and using the opposite angle of the actual wind direction angle as the yaw compensation amount.

[0035] It should be noted that flow field characteristic information refers to dynamic data such as upstream wind speed, wind direction, and turbulence intensity detected in real time by sensing devices such as radar or lidar; static terrain information refers to geographic data pre-built into the system, including mountain undulations and obstacle distribution. By fusing these two types of information, the wind yaw calculation model can output a wind yaw vector that accurately reflects the distorting effect of terrain on natural wind.

[0036] Understandably, the system specifically combines the wind direction offset angle indicated by the wind yaw vector with the current yaw angle read from the unit's yaw encoder to calculate the actual wind direction angle, unaffected by terrain. The opposite angle of the actual wind direction angle is set as the yaw compensation amount, the purpose of which is to directly offset the deviation caused by terrain, allowing the wind turbine axis to realign with the true incoming flow direction. For example, if the calculated actual wind direction is five degrees to the left of the current nacelle orientation, the system will generate a compensation command to yaw five degrees to the right. This calculation logic is clear and direct, ensuring the accuracy of the compensation action and ultimately achieving the goal of improving wind energy capture efficiency.

[0037] Step S30: Generate a yaw compensation command sequence based on the yaw compensation amount and the preset multi-objective optimization strategy.

[0038] It should be noted that the multi-objective optimization strategy refers to a decision-making mechanism that comprehensively balances power generation efficiency and equipment losses. Its core lies in balancing the power generation benefits brought by rapid wind shunting with the mechanical wear costs caused by frequent yaw maneuvers. This strategy uses a core tool called the comprehensive cost function to evaluate the initial sequence of actions generated by the yaw maneuver planning model. This function simultaneously considers the predicted increase in power generation over a future period, the equivalent cumulative fatigue of the yaw system bearings, and additional energy consumption.

[0039] Understandably, this step aims to translate the ideal compensation angle command into an economically feasible action plan in actual operation. For example, when the system calculates that a 20-degree yaw is needed to fully align with the wind direction, the optimized strategy may not immediately issue a one-time 20-degree turn command, but may break it down into a series of actions with smaller angles and longer intervals. While this slightly delays the time to full alignment, it significantly reduces the instantaneous impact and reciprocating stress on the drive system and bearings, making it more optimized from an overall lifecycle cost perspective.

[0040] It should be understood that the generation of command sequences is based on forward-looking rolling planning based on predictions of future wind conditions. In this way, the system can proactively smooth yaw movements, avoid unnecessary start-stop oscillations, and maximize the service life of key mechanical components of the yaw system while ensuring high wind capture efficiency, thus achieving a dynamic optimal balance between power generation revenue and operation and maintenance costs.

[0041] Step S40: Execute the yaw compensation command sequence to drive the yaw system to correct the wind yaw error caused by complex terrain.

[0042] It should be noted that the yaw compensation command sequence in this step refers to a series of specific control commands, including timing points and action details, generated by optimization in the previous step. This command sequence drives the yaw system's motor and brakes through industrial control units such as field-programmable logic controllers (FPGAs), causing it to perform rotational movements at predetermined speeds and angles. Its core value lies in directly and dynamically compensating for wind yaw errors caused by complex terrain. For example, when the command sequence indicates stepwise yaw, the yaw system will smoothly and gradually rotate the entire nacelle and rotor to the optimal windward angle, rather than abruptly, effectively avoiding mechanical shock. Through this real-time and flexible correction, the wind turbine can continuously maintain the optimal windward attitude, ultimately improving the unit's energy capture efficiency in complex wind fields. Simultaneously, the smooth movement protects the equipment structure, which is key to achieving the final technical benefits of the method.

[0043] In this embodiment, by comprehensively collecting real-time flow field characteristics, static geographic information, and unit operating status, the wind direction deviation caused by terrain is accurately quantified using a wind yaw calculation model to determine the yaw compensation amount. Subsequently, this compensation amount is not directly executed, but is planned into a smooth yaw action sequence through a multi-objective optimization strategy that simultaneously balances power generation benefits and mechanical fatigue. Finally, this command sequence drives the yaw system to execute, achieving dynamic and flexible correction of terrain-induced wind yaw errors.

[0044] In summary, this technical solution employs precise modeling that integrates dynamic wind conditions and static terrain. The system can perceive and calculate the actual wind direction deviation caused by complex terrain in real time, overcoming the inaccurate wind alignment issues resulting from traditional methods that rely solely on nacelle anemometers, thus directly improving wind energy capture efficiency. Secondly, the introduction of a multi-objective optimization strategy to generate a yaw command sequence transforms yaw action into an intelligent decision that balances power generation and equipment lifespan. Combined with large-angle compensation decomposition into multiple smooth micro-amplitude movements, it effectively suppresses the impact load and vibration of the yaw system, significantly reducing wear on key mechanical components, thereby extending equipment lifespan and reducing maintenance costs. In conclusion, this method, through end-to-end optimization of perception, decision-making, and execution, collaboratively achieves comprehensive technical benefits of increased power generation and enhanced equipment reliability in complex terrain environments.

[0045] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in the first embodiment described above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 2 In the wind turbine generator yaw error correction method, step S30 includes steps S301 to S305: Step S301: Input the yaw compensation amount and the current unit operating status information into the preset yaw action planning model to generate a preliminary yaw action sequence.

[0046] It should be noted that the yaw motion planning model refers to a decision-making module specifically designed to translate compensation quantities into concrete action plans. Current unit operating status information includes key parameters such as generator output power, transmission chain vibration level, and whether the yaw system is currently in braking or standby mode. Based on these real-time states and the required yaw compensation, the model plans a preliminary motion path that includes the timing of the action, the direction of rotation, and the segmented angles.

[0047] Understandably, the core task of this step is to transform an abstract angular target into a series of time-discrete instructions that can be directly executed by the control system. For example, if the system needs to compensate for a 15-degree angle, but the unit is currently experiencing high power output and the drive train is vibrating significantly, the planning model may not immediately execute all the compensation. Instead, it will first generate a preliminary sequence that decomposes the large action into multiple small steps, and insert short pauses between actions to observe the system response, thereby prioritizing operational stability while achieving the compensation target.

[0048] It should be understood that the generation of the initial action sequence is the foundation for subsequent multi-objective optimization. This sequence primarily considers the physical feasibility and basic safety of the actions, without deeply integrating economic objectives such as power generation efficiency and mechanical lifespan. It provides a library of alternative solutions for the next step of refined trade-offs and selection, and is a crucial link in the entire instruction sequence generation process.

[0049] Step S302: Construct a comprehensive cost function that includes the equivalent wear cost of the yaw bearing, the operation and maintenance cost of the yaw system, and the power generation loss.

[0050] It should be noted that the comprehensive cost function is a mathematical model used to quantitatively evaluate the overall advantages and disadvantages of different yaw maneuver schemes. The equivalent wear cost of the yaw bearing refers to the economic cost converted from the mechanical shock and fatigue damage caused by the yaw maneuver; the yaw system operation and maintenance cost covers the electrical energy consumed in performing the maneuver and potential component wear costs; power generation loss specifically refers to the power generation revenue corresponding to the energy lost during the yaw maneuver because the wind turbine fails to maintain the optimal windward angle at all times. This function unifies these interdependent cost items into a comparable numerical framework by assigning appropriate weights to them.

[0051] Understandably, the fundamental purpose of constructing this function is to achieve a trade-off between power generation efficiency and equipment durability. For example, an aggressive yaw scheme that pursues the fastest possible wind response may reduce power generation losses, but it may also lead to a sharp increase in bearing wear costs due to the violent movements; conversely, an overly slow and cautious scheme may protect the equipment, but it may cause significant power generation losses due to prolonged deviations from the optimal angle. The comprehensive cost function is precisely for objectively comparing the overall economics of these two extremes and all possible solutions in between.

[0052] It should be understood that this function is the core decision-making tool of the multi-objective optimization strategy, and its output directly determines the final selected yaw command sequence. By calculating the comprehensive cost corresponding to each preliminary action sequence, the system can discard those seemingly efficient or conservative but ultimately costly solutions, thereby intelligently selecting the globally optimal action plan under specific wind conditions and turbine status, ensuring the maximization of the wind turbine's full life-cycle operational benefits.

[0053] Step S303: Based on the yaw compensation amount and the real-time status of the unit, generate a multi-step yaw action prediction sequence within the future time window, and calculate the corresponding comprehensive cost function value based on the prediction sequence.

[0054] It should be noted that the rolling generation in this step is a dynamic predictive planning method. Its core lies in continuously deducing possible yaw action schemes in the future based on the latest yaw compensation requirements and the real-time operating status of the unit, such as the current yaw angle and power output, thereby forming a series of continuous action steps in time, namely a multi-step yaw action prediction sequence.

[0055] Understandably, the essence of this process is to conduct forward-looking decision-making simulations. For example, after calculating a 10-degree yaw compensation, the system doesn't simply plan how to compensate for that 10 degrees in one step. Instead, it continuously predicts the wind direction change trend over the next few minutes and generates multiple possible action sequences accordingly, such as "turn 5 degrees first, pause to observe, then turn 5 degrees again" or "turn at a constant speed in four small steps." Subsequently, the system uses the aforementioned constructed comprehensive cost function to evaluate each predicted sequence and calculate its corresponding comprehensive cost function value. This value quantifies the overall cost of the solution in terms of equipment wear, energy consumption, and power generation revenue.

[0056] It should be understood that this step, through quantitative evaluation of various future scenarios, enables the system to avoid making short-sighted decisions based solely on the current instantaneous state. This effectively avoids ineffective actions or equipment damage that may result from sudden changes in wind direction, providing solid data support for ultimately selecting a yaw command sequence that always approaches the optimal in a dynamically changing environment.

[0057] In one embodiment, the step of generating a multi-step yaw action prediction sequence within a future time window based on the yaw compensation amount and the real-time status of the unit includes: inputting the wind deflection vector into a local flow field disturbance model constructed based on computational fluid dynamics to predict the equivalent wind direction deflection disturbance sequence caused by the terrain within a preset time window; and superimposing the equivalent wind direction deflection disturbance sequence with the yaw compensation amount as input to the yaw action planning model to generate the multi-step yaw action prediction sequence.

[0058] It should be noted that the wind deflection vector here refers to a vector that integrates wind direction and wind speed information, used to accurately describe the characteristics of the incoming wind. The local flow field perturbation model built on computational fluid dynamics is a high-precision physical model capable of simulating the impact of complex terrain, such as ridges or valleys, on natural wind flow. The model's function is to predict the time-varying sequence of equivalent wind direction deflection angles caused by terrain perturbations within a predetermined future time window. This prediction refines macroscopic wind direction information, revealing the dynamic fluctuation details influenced by the local geographical environment.

[0059] Understandably, superimposing the predicted equivalent wind direction deflection disturbance sequence with the initial yaw compensation is to create a more realistic and dynamically changing overall compensation target. For example, the initial compensation might be a 10-degree deflection calculated based on the average wind direction, but the flow field model predicts that the terrain will cause a periodic fluctuation of plus or minus two degrees in the wind direction within the next minute. Through superposition, the yaw action planning model will no longer receive a fixed 10-degree instruction, but a dynamic target sequence such as "first compensate to 12 degrees, then revert to 8 degrees." The resulting multi-step yaw action prediction sequence can more intelligently predict and respond to subtle changes in the wind field.

[0060] It should be understood that the introduction of local flow field disturbance prediction is intended to enable yaw control to anticipate specific wind direction change patterns caused by terrain, thereby planning forward-looking and smooth actions. This method significantly improves the accuracy of the action sequence, effectively reducing power generation losses and mechanical wear caused by response lag or excessive actions, ultimately achieving more refined unit control.

[0061] Step S304: Adjust the step size and timing of the initial yaw action sequence until the value of the comprehensive cost function meets the preset optimization convergence condition to obtain the corrected yaw action sequence.

[0062] It should be noted that the step size refers to the rotation angle of each single step in the yaw action sequence, while the action sequence refers to the time interval and order between each action step. The preset optimization convergence condition is a technical standard for judging whether an acceptable optimal solution has been reached, usually set as the decrease in the comprehensive cost function value being less than a certain threshold or the maximum number of iterations being reached. This step aims to refine the initial sequence by iteratively adjusting these two key parameters.

[0063] Understandably, adjusting the step size and timing is a trade-off process seeking a global optimum. For example, if the initial sequence results in excessive bearing wear costs due to an overly large step size, the optimization process will attempt to reduce the step size and increase the number of steps. Although the increased time for each action may slightly increase power generation losses, the overall cost may be lower if wear is significantly reduced. Conversely, if the timing is too sparse, causing wind delays, the process will attempt to compress the action intervals. This process continuously calculates and compares the comprehensive costs under different parameter combinations to find the optimal balance point that minimizes the total cost.

[0064] It should be understood that this step is the core optimization stage for ultimately generating high-quality control commands. It ensures that the output yaw sequence not only theoretically fulfills the yaw compensation task, but also fully considers the stability, economy, and power generation efficiency of the unit in practice. Meeting the preset convergence conditions signifies that the sequence is the optimal or near-optimal solution obtainable under the current information and model, thus providing a direct and reliable execution basis for the intelligent yaw control of wind turbine units.

[0065] Step S305: Perform smoothing filtering on the corrected yaw action sequence, and generate the yaw compensation command sequence based on the filtering result.

[0066] It should be noted that the smoothing filtering process here aims to remove any abrupt changes or jitters that may exist in the corrected yaw sequence. Although the sequence has been optimized, its angle or timing changes may still be discontinuous at the microscopic level, and direct execution could easily cause mechanical shocks. The filtering process uses specific mathematical algorithms, such as low-pass filtering, to preserve the overall trend of the sequence while smoothing out high-frequency, large-amplitude jumps, thereby generating a smoother command transition.

[0067] In one embodiment, after executing the yaw compensation command sequence, the actual output power of the wind turbine generator and the load data of key mechanical components of the yaw system are collected to form a feedback information set. The feedback information set is compared with the expected performance indicators based on the wind direction yaw calculation model and the multi-objective optimization strategy to generate correction values ​​for the model and strategy. Based on the correction values, the flow field-wind yaw mapping relationship in the wind direction yaw calculation model and / or the weight of the comprehensive cost function in the multi-objective optimization strategy are corrected until the comprehensive evaluation index meets the preset iteration termination condition. The comprehensive evaluation index includes the unit operating efficiency and mechanical load.

[0068] It should be noted that this embodiment describes a closed-loop optimization process. The load data for key mechanical components refers to the stress information experienced by core structures such as yaw bearings and gears during operation. The feedback information set is a quantitative comparison between actual operating results and theoretical expectations. The expected performance indicators are a set of theoretically optimal values ​​for power generation and mechanical load, pre-calculated based on the wind direction and yaw calculation model and multi-objective optimization strategy. By comparing the actual results with the expected values, the required correction amounts for the model and strategy can be calculated.

[0069] Understandably, the purpose of generating correction values ​​is to make the theoretical model more closely reflect the actual conditions of a specific wind farm site. For example, if the actual measured output power is consistently lower than expected, while the mechanical load is higher than expected, it may indicate a deviation in the wind deflection mapping relationship in the model, underestimating the turbulence intensity. The correction values ​​generated accordingly will be used to correct this mapping relationship, making its prediction of future wind deflection more accurate. At the same time, the weight ratio between power generation efficiency and mechanical losses in the optimization strategy may also be adjusted to better protect the equipment in subsequent control.

[0070] It should be understood that this closed-loop process is the core mechanism for enabling the control system to learn and continuously optimize itself. By continuously utilizing real-time feedback data, the core model and strategy parameters are fine-tuned, allowing the entire yaw control system to gradually adapt to the unique flow field characteristics and unit operating conditions. This iterative correction continues until the comprehensive evaluation index composed of unit operating efficiency and mechanical load reaches the preset stability standard, thereby ensuring that the control system maintains an optimal or near-optimal operating state in the long term.

[0071] In this embodiment, a preliminary action sequence is generated through a planning model; then, a multi-objective cost function that comprehensively considers bearing wear, operation and maintenance costs, and power generation losses is constructed, and a multi-step action prediction sequence is generated by predicting local flow field disturbances for forward-looking evaluation; subsequently, the action step size and timing are iteratively optimized to minimize the comprehensive cost, and the optimized sequence is smoothed and filtered to improve execution stability; finally, a closed-loop feedback mechanism is introduced to continuously correct the prediction model and optimization strategy weights based on actual operating data until the comprehensive evaluation index meets the target.

[0072] In summary, this embodiment constructs a comprehensive cost function to perform multi-objective optimization on the initial sequence and introduces local flow field prediction based on computational fluid dynamics to achieve forward-looking planning. This allows the generated command sequence to effectively balance the contradiction between power generation efficiency and mechanical equipment durability while meeting basic yaw compensation requirements. Furthermore, smoothing filtering effectively suppresses command abrupt changes and reduces mechanical shock. This solution ultimately significantly improves the accuracy and intelligence of yaw control, thereby maximizing wind energy capture efficiency and total life-cycle power generation benefits while ensuring the safe and stable operation of the unit and extending the service life of key components.

[0073] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the yaw error correction method of wind turbine generator set of this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0074] This application also provides a yaw error correction device for wind turbine generator sets. Please refer to... Figure 3The wind turbine yaw error correction device includes: Information acquisition module 10 is used to acquire real-time environmental information and unit operation information of wind turbine generator set; The compensation calculation module 20 is used to obtain the yaw compensation amount required to offset environmental disturbances based on the real-time environmental information, unit operation information and wind direction yaw calculation model. The optimization decision module 30 is used to generate a yaw compensation instruction sequence based on the yaw compensation amount and a preset multi-objective optimization strategy; The correction execution module 40 is used to execute the yaw compensation command sequence to drive the yaw system to correct the wind yaw error caused by complex terrain.

[0075] In one embodiment, the compensation calculation module 20 is further configured to input the flow field feature information and static terrain information in the real-time environmental information into the wind direction yaw calculation model to obtain the wind yaw vector caused by the terrain where the unit is located; obtain the actual wind direction angle based on the wind yaw vector and the current yaw angle in the unit operation information; and use the opposite angle of the actual wind direction angle as the yaw compensation amount.

[0076] In one embodiment, the information acquisition module 10 is further configured to acquire real-time environmental information, including flow field characteristic information in front of the unit collected by the front-end wind measurement equipment and static terrain information from the geographic information system; and acquire unit operation information, including the generator power, rotor speed and current yaw angle of the wind turbine generator set.

[0077] In one embodiment, the optimization decision module 30 is further configured to input the yaw compensation amount and the current unit operating status information into a preset yaw action planning model to generate a preliminary yaw action sequence; obtain a multi-objective optimization function, and evaluate and correct the preliminary yaw action sequence according to the multi-objective optimization function to obtain a corrected yaw action sequence; perform smoothing filtering on the corrected yaw action sequence, and generate the yaw compensation command sequence according to the filtering result.

[0078] In one embodiment, the optimization decision module 30 is further configured to construct a comprehensive cost function that includes the equivalent wear cost of the yaw bearing, the operation and maintenance cost of the yaw system, and the power generation loss; based on the yaw compensation amount and the real-time status of the unit, to generate a multi-step yaw action prediction sequence within a future time window, and to calculate the corresponding comprehensive cost function value according to the prediction sequence; to adjust the step size and action timing of the initial yaw action sequence until the comprehensive cost function value meets the preset optimization convergence condition, thereby obtaining the corrected yaw action sequence.

[0079] In one embodiment, the optimization decision module 30 is further configured to input the wind deflection vector into a local flow field disturbance model constructed based on computational fluid dynamics, predict the equivalent wind direction deflection disturbance sequence caused by the terrain within a preset time window; and superimpose the equivalent wind direction deflection disturbance sequence with the yaw compensation amount as input to the yaw action planning model to generate the multi-step yaw action prediction sequence.

[0080] In one embodiment, the optimization decision module 30 is further configured to, after executing the yaw compensation command sequence, collect the actual output power of the wind turbine generator set and the load data of key mechanical components of the yaw system to form a feedback information set; compare the feedback information set with the expected performance indicators based on the wind direction yaw calculation model and the multi-objective optimization strategy to generate a correction amount for the model and strategy; and, based on the correction amount, correct the flow field-wind yaw mapping relationship in the wind direction yaw calculation model and / or the weight of the comprehensive cost function in the multi-objective optimization strategy until the comprehensive evaluation index meets the preset iteration termination condition, wherein the comprehensive evaluation index includes the unit operating efficiency and mechanical load.

[0081] The wind turbine yaw error correction device provided in this application employs the wind turbine yaw error correction method described in the above embodiments. It addresses the technical problem of how to achieve real-time, dynamic, and adaptive compensation for wind turbine yaw error under complex terrain conditions to improve the turbine's wind alignment accuracy and power generation efficiency. Compared with the prior art, the beneficial effects of the wind turbine yaw error correction device provided in this application are the same as those of the wind turbine yaw error correction method provided in the above embodiments. Furthermore, other technical features of the wind turbine yaw error correction device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0082] This application provides a yaw error correction device for a wind turbine generator set. The yaw error correction device for a wind turbine generator set includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the yaw error correction method for a wind turbine generator set in the first embodiment described above.

[0083] The following is for reference. Figure 4This document illustrates a structural schematic diagram of a wind turbine yaw error correction device suitable for implementing embodiments of this application. The wind turbine yaw error correction device in this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), and vehicle terminals (e.g., vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 4 The wind turbine yaw error correction device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0084] like Figure 4 As shown, the wind turbine yaw error correction device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the wind turbine yaw error correction device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. Communication device 1009 allows the wind turbine yaw error correction equipment to communicate wirelessly or wiredly with other devices to exchange data. Although the figure shows a wind turbine yaw error correction equipment with various systems, it should be understood that it is not required to implement or possess all the systems shown. More or fewer systems can be implemented alternatively.

[0085] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0086] The wind turbine yaw error correction device provided in this application, employing the wind turbine yaw error correction method described in the above embodiments, solves the technical problem of how to achieve real-time, dynamic, and adaptive compensation for wind turbine yaw error under complex terrain conditions to improve the turbine's wind alignment accuracy and power generation efficiency. Compared with the prior art, the beneficial effects of the wind turbine yaw error correction device provided in this application are the same as those of the wind turbine yaw error correction method provided in the above embodiments, and other technical features of this wind turbine yaw error correction device are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0087] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0088] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0089] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, which are used to execute the wind turbine yaw error correction method in the above embodiments.

[0090] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0091] The aforementioned computer-readable storage medium may be included in the yaw error correction device of the wind turbine generator set; or it may exist independently and not be assembled into the yaw error correction device of the wind turbine generator set.

[0092] The aforementioned computer-readable storage medium carries one or more programs. When these programs are executed by the wind turbine yaw error correction device, the wind turbine yaw error correction device: acquires real-time environmental information and turbine operation information; based on the real-time environmental information, turbine operation information, and wind direction yaw calculation model, obtains the yaw compensation amount required to offset environmental disturbances; generates a yaw compensation command sequence according to the yaw compensation amount and a preset multi-objective optimization strategy; and executes the yaw compensation command sequence to drive the yaw system to correct wind yaw errors caused by complex terrain.

[0093] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0094] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0095] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0096] The readable storage medium provided in this application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-described wind turbine yaw error correction method. This solves the technical problem of how to achieve real-time, dynamic, and adaptive compensation for wind turbine yaw error under complex terrain conditions to improve the turbine's wind alignment accuracy and power generation efficiency. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the wind turbine yaw error correction method provided in the above embodiments, and will not be repeated here.

[0097] The computer program product provided in this application can solve the technical problem of yaw error correction for wind turbine generator sets. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the wind turbine generator set yaw error correction method provided in the above embodiments, and will not be repeated here.

[0098] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A method for correcting yaw error of a wind turbine generator set, characterized in that, The method for correcting the yaw error of the wind turbine generator set includes: To obtain real-time environmental and operational information of wind turbine generators; Based on the real-time environmental information, unit operation information, and wind direction yaw calculation model, the yaw compensation amount required to offset environmental disturbances is obtained. Based on the yaw compensation amount and the preset multi-objective optimization strategy, a yaw compensation command sequence is generated; The yaw compensation command sequence is executed to drive the yaw system to correct for wind yaw errors caused by complex terrain.

2. The method for correcting yaw error of a wind turbine generator set according to claim 1, characterized in that, The yaw compensation amount required to offset environmental disturbances, based on the real-time environmental information, unit operation information, and wind direction yaw calculation model, includes: The flow field characteristics and static terrain information in the real-time environmental information are input into the wind direction yaw calculation model to obtain the wind yaw vector caused by the terrain where the unit is located; The actual wind direction angle is obtained based on the wind yaw vector and the current yaw angle in the unit operation information; The opposite angle of the actual wind direction angle is used as the yaw compensation amount.

3. The method for correcting yaw error of a wind turbine generator set according to claim 2, characterized in that, The acquisition of real-time environmental information and unit operation information of the wind turbine generator includes: Acquire real-time environmental information, including flow field characteristic information in front of the unit collected by the front-end wind measurement equipment and static terrain information from the geographic information system; Obtain unit operation information, which includes the generator power, rotor speed and current yaw angle of the wind turbine generator set.

4. The method for correcting yaw error of a wind turbine generator set according to claim 1, characterized in that, The step of generating a yaw compensation command sequence based on the yaw compensation amount and a preset multi-objective optimization strategy includes: The yaw compensation amount and the current unit operating status information are input into a preset yaw action planning model to generate a preliminary yaw action sequence. Obtain a multi-objective optimization function, and evaluate and correct the initial yaw action sequence based on the multi-objective optimization function to obtain a corrected yaw action sequence; The corrected yaw action sequence is subjected to smoothing filtering, and the yaw compensation command sequence is generated based on the filtering result.

5. The method for correcting yaw error of a wind turbine generator set according to claim 4, characterized in that, The process of obtaining a multi-objective optimization function and evaluating and correcting the initial yaw sequence based on the multi-objective optimization function to obtain a corrected yaw sequence includes: Construct a comprehensive cost function that includes the equivalent wear cost of the yaw bearing, the operation and maintenance cost of the yaw system, and the power generation loss; Based on the yaw compensation amount and the real-time status of the crew, a multi-step yaw action prediction sequence within the future time window is generated in a rolling manner, and the corresponding comprehensive cost function value is calculated based on the prediction sequence. Adjust the step size and timing of the initial yaw action sequence until the comprehensive cost function value meets the preset optimization convergence condition to obtain the corrected yaw action sequence.

6. The method for correcting yaw error of a wind turbine generator set according to claim 5, characterized in that, The step of generating a multi-step yaw action prediction sequence within a future time window based on the yaw compensation amount and the real-time status of the crew includes: The wind deflection vector is input into a local flow field disturbance model based on computational fluid dynamics to predict the equivalent wind direction deflection disturbance sequence caused by the terrain within a preset time window; The equivalent wind direction deflection disturbance sequence is superimposed with the yaw compensation amount and used as input to the yaw action planning model to generate the multi-step yaw action prediction sequence.

7. The method for correcting yaw error of a wind turbine generator set according to any one of claims 1 to 6, characterized in that, The wind turbine yaw error correction method further includes: After executing the yaw compensation command sequence, the actual output power of the wind turbine generator and the load data of the key mechanical components of the yaw system are collected to form a feedback information set. The feedback information set is compared with the expected performance indicators based on the wind direction yaw calculation model and multi-objective optimization strategy to generate the correction amount of the model and strategy. Based on the correction amount, the flow field-wind yaw mapping relationship in the wind direction yaw calculation model and / or the weight of the comprehensive cost function in the multi-objective optimization strategy are corrected until the comprehensive evaluation index meets the preset iteration termination condition. The comprehensive evaluation index includes unit operating efficiency and mechanical load.

8. A yaw error correction device for a wind turbine generator set, characterized in that, The wind turbine yaw error correction device includes: The information acquisition module is used to acquire real-time environmental information and unit operation information of the wind turbine generator set; The compensation calculation module is used to obtain the yaw compensation amount required to offset environmental disturbances based on the real-time environmental information, unit operation information and wind direction yaw calculation model. The optimization decision module is used to generate a yaw compensation instruction sequence based on the yaw compensation amount and a preset multi-objective optimization strategy; The correction execution module is used to execute the yaw compensation command sequence to drive the yaw system to correct the wind yaw error caused by complex terrain.

9. A yaw error correction device for a wind turbine generator set, characterized in that, The wind turbine yaw error correction device includes: a memory, a processor, and a wind turbine yaw error correction program stored in the memory and executable on the processor, wherein the wind turbine yaw error correction program is configured to implement the wind turbine yaw error correction method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that, The storage medium stores a yaw error correction program for a wind turbine generator set, which, when executed by a processor, implements the yaw error correction method for a wind turbine generator set as described in any one of claims 1 to 7.

Images