Wind turbine generator control method based on wind conditions

Abstract

The invention provides a wind turbine generator control method based on wind conditions. The wind turbine generator control method comprises the steps that operation data and wind condition data of a wind turbine generator are obtained; preprocessing the operation data and the wind regime data; performing feature extraction on the preprocessed operation data and wind regime data to obtain operation feature data and wind regime feature data; identifying a wind regime type represented by the wind regime feature data; when the wind regime characteristic data represents that the current wind regime is a preset wind regime type, a corresponding unit control rule is selected in combination with the preset wind regime type and the operation characteristic data; the wind turbine generator is controlled based on the generator set control rule, the adaptive capacity of the wind turbine generator under the complex wind condition can be effectively improved, through dynamic feature recognition and self-adaptive control strategy selection, the operation safety of the generator set is guaranteed, the power generation efficiency is maintained, the technical defects of response lag and single strategy are avoided, and the method is suitable for large-scale popularization and application. And intelligentization and refinement of the control strategy of the wind turbine generator are realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of wind power generation control, in particular to a wind turbine control method based on wind conditions. BACKGROUND

[0002] As a renewable energy generation device, wind turbines often face various complex and variable special wind conditions, such as gusts, turbulence, wind shear, and sudden strong winds, during operation. These special wind conditions can have a significant impact on the operational performance, safety, and service life of wind turbines.

[0003] Traditional wind turbine control methods are usually designed based on steady-state wind conditions and are difficult to effectively respond to these complex and variable special wind conditions. Although there are some control methods for special wind conditions in the prior art, these methods mostly have deficiencies, such as single control strategy, slow response speed, poor adaptability, etc., making it difficult to respond to multiple special wind conditions simultaneously and unable to adjust the control strategy in real time according to the dynamic changes of wind conditions, thereby limiting the operational performance and safety of wind turbines in complex wind conditions. SUMMARY

[0004] The present application provides a wind turbine control method based on wind conditions to solve the technical problem of single control strategy and poor adaptability of wind turbines in complex wind conditions in the prior art.

[0005] In one aspect, the present application provides a wind turbine control method based on wind conditions, comprising: obtaining operational data and wind condition data of a wind turbine; preprocessing the operational data and the wind condition data; extracting features from the preprocessed operational data and wind condition data to obtain operational feature data and wind condition feature data; identifying the wind condition type represented by the wind condition feature data; when the wind condition feature data represents the current wind condition as a preset wind condition type, combining the preset wind condition type and the operational feature data to select a corresponding turbine control rule; controlling the wind turbine based on the turbine control rule.

[0006] According to the wind turbine control method based on wind conditions provided by the present application, when the preset wind condition type is a storm, the turbine control rule includes: if the current wind speed is greater than the preset cut-out wind speed, limiting the upper limit of the power of the wind turbine, and dynamically adjusting the power set value according to a pre-created wind speed-power interpolation table; The wind speed-power interpolation table comprises a plurality of mapping relationships between wind speed values and corresponding power limit values, and the power limit value decreases with the increase of the wind speed, so that the unit maintains a power generation operation state.

[0007] According to the application, when the preset wind condition type is gust, the unit control rule comprises: monitoring the acceleration of the generator speed; if the acceleration continues to rise and exceeds a preset threshold, limiting the pitch angle to a preset minimum angle limit value; The minimum angle limit value is determined by load iteration optimization to accelerate the response speed of the pitch system.

[0008] According to the application, when the preset wind condition type is wind direction mutation, the unit control rule comprises: detecting the current yaw deviation; if the yaw deviation exceeds a preset limit value, lifting the pitch angle to a corresponding value according to a pre-created minimum pitch angle interpolation table for wind deviation; The interpolation table comprises a plurality of mapping relationships between yaw deviation values and minimum pitch angles, and the pitch angle increases with the increase of the deviation to reduce the unbalanced load of the unit.

[0009] According to the application, when the preset wind condition type is emergency crosswind, the unit control rule comprises: if the generator speed of the wind turbine generator exceeds a safety threshold and the pitch system feedbacks a fault signal, controlling the yaw drive of the wind turbine generator to perform a crosswind 90° action and locking the yaw state until manual reset.

[0010] According to the application, when the preset wind condition type is turbulence, the unit control rule comprises: based on a wind speed sequence of a preset time length, calculating the turbulence intensity; according to the turbulence intensity and a pre-created turbulence limit power interpolation table, dynamically adjusting the upper limit of the power of the wind turbine generator; The turbulence limit power interpolation table comprises a plurality of mapping relationships between turbulence intensity values and power limit values, and the power limit value decreases with the increase of the turbulence intensity to reduce the fatigue load of the unit.

[0011] According to the application, when the preset wind condition type is a composite wind condition, the unit control rule comprises: according to a preset priority rule, dynamically integrating a plurality of unit control rules; Wherein, the composite wind condition is a wind condition in which at least two preset wind condition types exist simultaneously; The priority rules are sorted based on the degree of impact of wind conditions on the safety and power generation efficiency of the unit, and the control rules with the greatest impact on safety are executed first.

[0012] According to a wind condition-based control method for a wind turbine generator set provided by the present invention, when the preset wind condition type is a composite wind condition, the turbine generator set control rules include: When the current wind condition type is identified as one of the preset wind condition types, but its matching degree is lower than the preset matching threshold, the system enters the fuzzy recognition mode; In the fuzzy recognition mode, multiple unit control rules with similar wind conditions are called, and weights are assigned to each control rule based on the operating data to generate fusion control instructions.

[0013] According to a wind condition-based control method for a wind turbine generator system provided by the present invention, a plurality of wind condition-based control rules are called, and weights are assigned to the control rules according to operating data to generate a fusion control instruction, including: Calculate the fuzzy membership between the current wind condition characteristic data and the preset wind condition type, and select the wind condition type whose fuzzy membership is greater than or equal to the preset fuzzy threshold as the candidate control rule set; Determine the applicable weight of each candidate control rule based on the unit safety status, grid dispatch requirements, and historical success rate in the operating data; wherein the applicable weight reflects the adaptability of the control rule to the current operating data, and the higher the weight value, the higher the priority; The output control parameters of each control rule are weighted and fused to generate the final fusion control instruction.

[0014] According to a wind condition-based wind turbine control method provided by the present invention, when it is identified that the current wind condition type is a transitional wind condition, the turbine control rules include: According to the changing trend of wind condition characteristics within the preset time window, the wind condition is divided into multiple evolution process stages; Based on the dynamic coupling relationship between different evolution process stages and operation characteristic data, stage-by-stage response rules are defined.

[0015] The wind turbine control method based on wind conditions provided by the application can accurately distinguish different wind condition types and their combined states by establishing a wind condition recognition mechanism of a multi-dimensional feature space, adopts a dynamic rule selection mechanism to replace a static control strategy, can match optimal control parameters according to real-time operation features, can effectively improve the adaptability of the wind turbine under complex wind conditions, and through dynamic feature recognition and adaptive control strategy selection, ensures the operation safety of the wind turbine and maintains the power generation efficiency, solves the technical defects of response lag and single strategy, and realizes the intelligentization and refinement of the wind turbine control strategy. BRIEF DESCRIPTION OF DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description are some embodiments of the application, and those skilled in the art can obtain other drawings according to these drawings without creative labor.

[0017] Figure 1 is a flowchart of the wind turbine control method based on wind conditions provided by the embodiment of the application. Figure 2 is a structural schematic diagram of the wind turbine control device based on wind conditions provided by the embodiment of the application. Figure 3 is a structural schematic diagram of the electronic device provided by the embodiment of the application. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical scheme and advantages of the application more clear, the technical scheme in the application will be clearly and completely described below in combination with the drawings in the application. Obviously, the described embodiments are some embodiments of the application, not all embodiments. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor belong to the protection scope of the application.

[0019] Figure 1 is a flowchart of the wind turbine control method based on wind conditions provided by the embodiment of the application.

[0020] Referring to Figure 1 , the wind turbine control method based on wind conditions can include the following steps 101 to 106.

[0021] Step 101, obtaining operation data and wind condition data of the wind turbine.

[0022] In this step, the operation data refers to a set of parameters reflecting the operating state of the unit, which can be realized by using real-time monitoring data such as generator speed, pitch angle position, power output, etc., to represent the current operating state of the unit. The wind condition data refers to a set of parameters reflecting the environmental wind force, which can be realized by using anemometers, wind vanes, three-dimensional ultrasonic wind meters and other sensors to collect data, to represent the current wind field environment characteristics.

[0023] Step 102, pre-processing operation data and wind condition data.

[0024] In this step, pre-processing refers to the process of standardizing the original data, which can be realized by using data cleaning, outlier removal, time series alignment and other methods to ensure the effectiveness and consistency of the subsequent analysis data. On the basis of pre-processed data, a filter can be applied for further processing to remove noise and smooth the data.

[0025] Step 103, feature extraction of pre-processed operation data and wind condition data to obtain operation feature data and wind condition feature data.

[0026] In this step, feature extraction refers to the process of extracting key information from pre-processed data, which can be realized by using time domain statistical analysis, frequency domain transformation, wavelet decomposition and other algorithms to construct the association features of wind conditions and unit states.

[0027] Step 104, identifying the wind condition type represented by the wind condition feature data.

[0028] In this step, the pre-set wind condition type refers to the pre-defined wind condition classification system, which can be realized by dividing the categories such as gale, gust and turbulence according to the meteorological standards, and each category corresponds to a specific set of control strategies.

[0029] Step 105, when the wind condition feature data represents the current wind condition as a pre-set wind condition type, combining the pre-set wind condition type and the operation feature data, selecting the corresponding unit control rule.

[0030] Step 106, controlling the wind turbine based on the unit control rule.

[0031] In this embodiment, specifically, the unit operating parameters and environmental wind condition parameters are collected in real time through the sensor network, and the raw data are timestamp aligned and dimensionally normalized. A sliding window mechanism is used to extract features from continuous time series data, such as calculating feature vectors such as the mean variance of wind speed, wind direction change rate, and power fluctuation amplitude. A wind condition classification model based on machine learning is established to match and identify real-time feature data with a feature library of preset wind condition types. When it is detected that the current wind condition belongs to a preset type, the corresponding control rule library is called, such as adopting a power limitation strategy for storm conditions and a pitch angle rapid adjustment strategy for gust conditions. The control instruction generation module dynamically adjusts the control parameters according to the real-time operating characteristics to ensure that the unit maintains the optimal operating state within the safety threshold.

[0032] This embodiment establishes a wind condition recognition mechanism in a multidimensional feature space, enabling accurate distinction between different wind condition types and their combined states. By replacing the static control strategy with a dynamic rule selection mechanism, optimal control parameters can be matched based on real-time operating characteristics. The above technical solution effectively enhances the adaptability of wind turbines to complex wind conditions. Through dynamic feature recognition and adaptive control strategy selection, it ensures both operational safety and power generation efficiency. This solution addresses the technical shortcomings of traditional methods, such as delayed response and a single strategy, and achieves intelligent and refined wind turbine control strategies.

[0033] In one embodiment of this specification, when the preset wind condition type is a storm, the unit control rules include: If it is detected that the current wind speed is greater than the preset cut-out wind speed, the power upper limit of the wind turbine is limited, and the power setting value is dynamically adjusted according to the pre-created wind speed power interpolation table; The wind speed power interpolation table includes a mapping relationship between multiple sets of wind speed values ​​and corresponding power limits, and the power limit decreases as the wind speed increases, so that the unit maintains a power generation operation state.

[0034] In this embodiment, the cut-out wind speed refers to the maximum safe operating wind speed threshold allowed by the wind turbine design. It can be set through wind turbine model parameters or historical operating data and is used to determine whether to trigger the power limit mechanism. The wind speed power interpolation table refers to a database that stores the relationship between different wind speeds and corresponding power limits. It can be generated using a linear interpolation or polynomial fitting algorithm and is used to dynamically adjust the power output when the wind speed exceeds the cut-out wind speed. The power limit decreases with increasing wind speed, which means that the power limit is gradually reduced as the wind speed increases. It can be achieved through a piecewise function or a gradient descent model to balance the safety of the unit and the continuity of power generation.

[0035] Specifically, when the storm working condition is identified, the real-time collected wind speed data is compared with the preset cut-out wind speed. If the current wind speed exceeds the cut-out wind speed, the dynamic power control mode is entered. At this time, the power upper limit is limited to a value lower than the rated power, avoiding triggering the shutdown protection of the unit due to overload. At the same time, based on the mapping relationship stored in the wind speed-power interpolation table, the corresponding power limit value is matched according to the current wind speed value. For example, when the wind speed reaches 105% of the cut-out wind speed, the power limit value can be adjusted to 80% of the rated power; when the wind speed reaches 110% of the cut-out wind speed, the power limit value is further reduced to 60% of the rated power. Through this decreasing mechanism, the power generation operation state is maintained under the premise of ensuring the safety of the mechanical structure of the unit.

[0036] The embodiment adjusts the power upper limit dynamically to continuously output controllable electric energy under the storm working condition, while avoiding frequent start-stop caused by instantaneous wind speed fluctuations. In addition, the power adjustment method based on the interpolation table can realize smooth transition and is more suitable for the nonlinear variation characteristics of wind speed than the fixed threshold control strategy. Through the above technical solutions, the safety operation of the unit and the continuity demand of power generation are effectively balanced under the storm working condition, and the power generation loss caused by direct shutdown is avoided. Through the dynamic decreasing mechanism of the power limit value, the load impact of the transmission system under extreme wind speed is reduced, and the service life of the key components is prolonged. At the same time, the application of the interpolation table makes the power adjustment process predictable and controllable, providing a stable power output reference for grid dispatching.

[0037] In an embodiment of the present specification, when the preset wind condition type is gust, the unit control rule comprises: monitoring the generator speed acceleration; if the acceleration continues to rise and exceeds the preset threshold value, the pitch angle is limited to a preset minimum angle limit value; wherein the minimum angle limit value is determined by load iterative optimization to accelerate the response speed of the pitch system.

[0038] In the embodiment, the generator speed acceleration refers to the change amount of the generator speed per unit time, which can be realized by collecting real-time data through a speed sensor and through difference calculation, and is used to represent the dynamic response state of the unit under the impact of gust. The preset threshold value refers to the critical acceleration value for triggering pitch angle adjustment, which can be determined by analyzing historical operation data combined with simulation test, and is used to identify the abnormal acceleration state caused by gust. The minimum angle limit value refers to the minimum pitch angle allowed by the pitch system to adjust, which can be determined by multi-condition load simulation combined with iterative optimization of measured data, and is used to realize fast response under the premise of ensuring structural safety. The load iterative optimization refers to the calculation process of repeatedly adjusting parameters based on structural load data under different pitch angles, which can be realized by closed-loop feedback of finite element model and measured data, and is used to balance the contradiction between pitch speed and bearing capacity of the unit.

[0039] Specifically, when the generator speed acceleration is detected to continuously exceed the preset threshold, it indicates that the wind gust causes the unit to enter a non-steady state operation. At this time, the pitch angle is limited to the minimum angle limit value optimized through load iteration, the wind energy capture efficiency is reduced by increasing the pitch angle, so as to suppress the speed mutation. The minimum angle limit value is formed by comparing the simulation data with the measured data through multiple rounds of load simulation, which ensures that the pitch system can quickly respond, and avoids the problem of structural overload caused by excessive adjustment. This control mode can intervene at the initial stage of the wind gust, and can suppress the speed fluctuation earlier.

[0040] The embodiment realizes precise intervention under the premise of ensuring structural safety by dynamically monitoring the acceleration trend and combining the minimum angle limit value optimized and verified. The load iterative optimization process effectively solves the contradiction between the pitch speed and the mechanical strength, and avoids the problems of conservatism or overconfidence caused by the setting of empirical parameters in the prior art. Through the above technical scheme, the unit instability problem caused by the generator speed mutation under the wind gust condition is effectively solved, the minimum pitch angle limit value optimized is used to identify the abnormal acceleration trend in advance, and the mechanical impact is reduced while the power generation state is maintained. The load iterative optimization method ensures the dynamic matching of the pitch action and the structural bearing capacity, and improves the adaptability and reliability of the control system.

[0041] In an embodiment of the present specification, when the preset wind condition type is wind direction mutation, the unit control rule comprises: detecting a current yaw deviation; if the yaw deviation exceeds a preset limit value, lifting the pitch angle to a corresponding value according to a pre-created minimum pitch angle interpolation table of wind alignment deviation; wherein the interpolation table comprises a plurality of mapping relationships between yaw deviation values and minimum pitch angles, and the pitch angle increases with the increase of the deviation to reduce the unbalanced load of the unit.

[0042] In the embodiment, the yaw deviation refers to the angle difference between the actual wind direction and the orientation of the wind turbine nacelle, which can be realized by synchronous measurement of the wind direction sensor and the yaw encoder, and the deviation value is used to judge whether the unit is in the abnormal state of wind alignment. The minimum pitch angle interpolation table of wind alignment deviation refers to a two-dimensional data table storing yaw deviation values and corresponding pitch angle setting values, which can be generated by offline simulation or historical operation data fitting. Its role is to establish a quantitative relationship between the deviation value and the pitch angle adjustment amount, avoiding the delay caused by real-time calculation. The pitch angle increases with the increase of the deviation refers to that when the yaw deviation exceeds the preset limit value, the pitch angle setting value is increased linearly or nonlinearly according to the interpolation table, which can be realized by table lookup method combined with linear interpolation algorithm. This mechanism can quickly respond to the load imbalance problem caused by wind direction mutation.

[0043] Specifically, when a sudden change in wind direction causes the yaw deviation to exceed a preset limit, such as 5 degrees, the pre-generated interpolation table of the minimum pitch angle for wind deviation is immediately called. For example, when the deviation value is 6 degrees, the corresponding pitch angle is raised to 3 degrees, and when the deviation value is 10 degrees, the corresponding pitch angle is raised to 8 degrees. After obtaining the target pitch angle by looking up the table, the pitch system performs a rapid pitch change action to increase the blade angle of attack and thereby reduce the load area of ​​the wind rotor, thereby reducing the aerodynamic imbalance torque caused by the yaw deviation. In this process, the mapping relationship of the interpolation table is verified by load optimization to ensure that the power generation power is maintained within an acceptable range while reducing the load.

[0044] This embodiment uses a dynamic pitch angle adjustment mechanism to prioritize reducing aerodynamic loads through variable pitch operations before the yaw system completes its wind-facing action, thereby forming a dual protection mechanism. At the same time, the data-driven method of the interpolation table can more accurately match the optimal pitch angle setting value under different degrees of deviation compared to the traditional proportional control strategy. Through the above technical solution, the problem of a surge in structural loads caused by yaw lag under conditions of sudden changes in wind direction is effectively solved. By raising the pitch angle in advance, the blade force is reduced, and the transmission chain components are prevented from being subjected to torque fluctuations beyond the design range. At the same time, the preset mapping relationship of the interpolation table ensures the real-time and accuracy of the control response, and realizes dynamic load balance control while maintaining continuous power generation of the unit.

[0045] In one embodiment of this specification, when the preset wind condition type is emergency crosswind, the unit control rules include: If it is detected that the generator speed of the wind turbine exceeds the safety threshold and the pitch system feedback fault signal, the yaw drive of the wind turbine is controlled to perform a 90° sidewind action and lock the yaw state until it is manually reset.

[0046] In this embodiment, the emergency crosswind refers to a wind condition in which the wind direction changes drastically in a short time, causing the unit to bear abnormal lateral load, which can be monitored by combining a wind speed sensor and a wind vane, and this feature is used to identify extreme wind conditions that may cause structural instability. The safety threshold refers to the pre-set upper limit of the generator speed, which can be calculated by superimposing a dynamic margin coefficient on the rated speed of the unit, or it can be set according to experience, and this threshold is used to determine whether to trigger an emergency protection mechanism to prevent mechanical overload. The pitch system feedback fault signal refers to the abnormal state code returned by the pitch drive or sensor, which can be parsed through the bus communication protocol, and this signal is used to confirm that the pitch system cannot normally adjust the pitch angle. The 90° crosswind action refers to the rotation of the nacelle driven by the yaw system to make the blade plane perpendicular to the wind direction, which can be achieved by encoder positioning and servo motor linkage, and this action is used to quickly reduce the windward area of the blade to reduce the wind load. The locked yaw state refers to the prohibition of the yaw system to automatically adjust the nacelle angle, which can be achieved by interlocking the electromagnetic brake and the controller, and this measure is used to maintain mechanical stability in emergency situations. The manual reset refers to the need for on-site confirmation by the operator to release the system lock state, which can be achieved by combining the safety switch and the permission verification module, and this mechanism is used to ensure that automatic operation is not restored before the fault is eliminated.

[0047] Specifically, when the wind turbine is in an emergency crosswind condition, the generator speed is monitored in real time to determine whether it exceeds the safety threshold, and the pitch system feedback fault signal is used for double verification. If both the speed overrun and the pitch system failure conditions are met, the yaw drive is triggered to perform a 90° crosswind action, making the blade plane perpendicular to the wind direction to minimize the aerodynamic load. During this process, the yaw system enters a locked state to avoid accidental rotation, and sends an alarm signal to the monitoring center. This state will continue to be maintained until the equipment inspection is completed by the operation and maintenance personnel, and the lock is manually released by the physical switch. Through this control logic, the wind energy input can be actively cut off when the pitch system fails, avoiding mechanical damage caused by uncontrolled speed.

[0048] This embodiment actively adjusts the nacelle angle to form aerodynamic protection, maintains mechanical stability of the unit in the locked state, avoids overload risk, and reduces power generation loss caused by unnecessary shutdown. Through the above technical solution, when the pitch system fails and encounters an emergency crosswind, a double protection mechanism is formed by active yawing and state locking, effectively preventing mechanical damage caused by generator overspeed, providing a safe operation window for manual intervention, and significantly improving the reliability of the equipment in extreme conditions.

[0049] In an embodiment of the present specification, when the preset wind condition type is turbulence, the unit control rule includes: Based on the wind speed sequence of the preset time length, the turbulence intensity is calculated; as shown in the following formula (1): (1); wherein, is the turbulence intensity at time t, is the average wind speed in the preset time window, is the wind speed sequence standard deviation in the preset time window. The preset time window can be set, for example, to 10 seconds or 10 minutes, etc.

[0050] When the preset time window is 10 minutes, the wind speed sequence standard deviation can be obtained by formula (2): (2); wherein, each second can be regarded as a time point, and 10 minutes can have 600 time points, is the wind speed at the i-th time point, i takes a value of 1 to 600, that is, 600 wind speed data.

[0051] According to the turbulence intensity and the pre-created turbulence limited power interpolation table, the power upper limit of the wind turbine generator is dynamically adjusted; wherein, the turbulence limited power interpolation table includes a plurality of mapping relationships between turbulence intensity values and power limit values, and the power limit value decreases with the increase of the turbulence intensity, so as to reduce the fatigue load of the unit.

[0052] In this embodiment, the turbulence intensity refers to a flow fluctuation degree quantitative index calculated by the ratio of the wind speed sequence standard deviation to the average wind speed in the preset time window, which can be specifically realized by a sliding time window statistical method, and is used to represent the influence level of the current turbulence on the unit structure. The turbulence limited power interpolation table refers to a two-dimensional data table storing the corresponding relationship between the turbulence intensity and the power limit value, which can be specifically realized by a piecewise linear interpolation algorithm, and the power output under high turbulence intensity is reduced to reduce the stress cycle times of the unit components. The dynamic adjustment of the power upper limit refers to matching the power limit value in the interpolation table according to the real-time calculated turbulence intensity, and updating the generator torque or pitch angle control instruction, which can be specifically realized by a closed-loop feedback control strategy, so that the unit maintains stable operation under turbulence working conditions.

[0053] Specifically, when the turbulence wind condition is detected, first, continuous wind speed data sequence is collected at a fixed sampling period, for example, the sampling value of wind speed per second in a 10-second time window. The ratio of the standard deviation of the sequence to the average wind speed is calculated to obtain the current turbulence intensity value. Then, the pre-established turbulence limited power interpolation table is queried to match the power limit value corresponding to the current turbulence intensity, for example, when the turbulence intensity reaches 0.3, it corresponds to 80% of the rated power. The control module adjusts the generator torque set value or the variable pitch angle in real time according to the limit value, so that the unit output power is always lower than the limit threshold. Through the stepwise attenuation of the power output, the dynamic load of the key components such as the blade root bending moment and the tower vibration can be effectively reduced.

[0054] The embodiment realizes the balance optimization of load control and power generation efficiency by establishing the quantitative correspondence between the turbulence intensity and the power limit. Through the above technical scheme, the power output can be gradually reduced in the process of continuous increase of the turbulence intensity, so as to avoid the impact on the power grid caused by sudden power limitation, and the service life of the blade bearing and the gearbox is effectively prolonged by reducing the stress amplitude of the key components. The control strategy controls the structural fatigue damage accumulation rate within the safe threshold range on the premise of ensuring the grid operation.

[0055] In an embodiment of the present specification, when the preset wind condition type is a composite wind condition, the unit control rule comprises: According to the preset priority rule, the plurality of unit control rules are dynamically integrated; Among them, the composite wind condition is a wind condition in which at least two preset wind condition types exist at the same time; The priority rule is based on the influence degree of the wind condition on the safety and power generation efficiency of the unit, and the control rule with the greatest influence on safety is preferentially executed.

[0056] In the embodiment, the composite wind condition refers to a wind condition environment in which at least two preset wind condition types exist at the same time, which can be realized by multi-dimensional wind condition feature data fusion analysis, for example, jointly modeling parameters such as wind speed mutation, turbulence intensity, wind direction deviation, etc. for identifying the state of superimposed multiple wind conditions. The priority rule refers to the execution order established according to the influence degree of the wind condition on the safety and power generation efficiency of the unit, which can be realized by using a decision tree algorithm based on risk level evaluation, for example, setting the wind condition type that causes mechanical structure overload as the highest priority. Dynamic integration refers to the process of coordinating the execution of multiple control rules according to real-time wind condition changes, which can be realized by using a multi-objective optimization algorithm, for example, weighted fusion of each control instruction under the condition of ensuring safety constraints.

[0057] Specifically, when the composite wind condition is detected, the feature extraction module is first used to identify the existing wind condition type combination, for example, the case of superimposed windstorm and turbulence. Then, the preset priority rule library is called, for example, the power limitation rule corresponding to the windstorm is set as the highest priority, and the dynamic power limitation rule corresponding to the turbulence is set as the secondary priority. The control instruction generation module coordinates the rule outputs according to the priority order, for example, the power upper limit constraint is preferentially executed in the windstorm condition, and the dynamic power limitation instruction corresponding to the turbulence condition is superimposed. In the implementation process, if it is detected that the safety related parameter reaches the critical threshold, the execution of the low priority rule is immediately terminated, for example, when the generator speed exceeds the safety threshold, the control instruction related to the power generation efficiency optimization is suspended.

[0058] The embodiment can realize real-time coordination of the interaction between multiple rules through the establishment of a dynamic integration mechanism. For example, when the wind direction suddenly changes and the emergency crosswind is superimposed, the yaw locking instruction is preferentially executed and then the pitch angle compensation control is superimposed, so as to guarantee the structural safety and maintain the continuity of power generation. Through the above technical solution, the problems of single strategy and execution conflict of the traditional control method under the composite wind condition are solved, and the cooperative control under the multi-wind condition superimposed scene is realized. Through the dynamic integration mechanism of the priority rule, the safety hidden danger is preferentially eliminated under the complex working condition, and the power generation efficiency optimization demand is considered at the same time, so as to effectively improve the operation reliability and control response precision of the unit under the extreme meteorological condition.

[0059] In an embodiment of the present specification, when the preset wind condition type is a composite wind condition, the unit control rule comprises: When it is identified that the current wind condition type is one of the preset wind condition types, but the matching degree is lower than the preset matching threshold, the fuzzy identification mode is entered; In the fuzzy identification mode, a plurality of unit control rules of similar wind condition types are called, and weight distribution is performed on each control rule according to the operation data to generate a fusion control instruction.

[0060] In the embodiment, the fuzzy identification mode refers to a multi-rule cooperative decision mechanism enabled when the matching degree of the wind condition characteristics and the preset type does not reach the deterministic threshold. Specifically, a fuzzy logic algorithm can be used to calculate the membership degree of the wind condition characteristics, so as to solve the problem of rigid control strategy caused by traditional binary judgment. The matching degree refers to a similarity quantitative index between the wind condition characteristic data and the preset wind condition type, which can be calculated by the Euclidean distance or cosine similarity algorithm, and is used to evaluate the matching degree of the current wind condition and the preset type. The weight distribution refers to a decision process of priority sorting of a plurality of control rules according to the real-time operation state of the unit, which can use the analytic hierarchy process combined with the sensor data to dynamically adjust the weight coefficient, so as to realize the accurate adaptation of the control strategy and the operation condition.

[0061] Specifically, when the wind condition recognition module detects that the matching degree of the current wind condition and the preset type is lower than the set threshold, the fuzzy logic operation unit is started. The unit first calculates the membership values of the current wind speed, wind direction, turbulence intensity and other characteristic parameters and various types of preset wind conditions, and selects a candidate control rule set with a membership degree higher than a critical value. Then, based on the real-time operation parameters such as the generator speed, the pitch angle position, the grid dispatching instruction, etc., the applicable weight of each candidate rule is determined through a multi-objective optimization algorithm. Finally, the control parameters such as the power set value and the pitch angle adjustment amount corresponding to each rule are linearly superimposed according to the weight, to generate a composite control instruction considering safety and power generation efficiency.

[0062] The embodiment can effectively deal with the common complex wind conditions in the wind farm by establishing a multi-rule collaborative decision mechanism. The control strategy switching mode based on the fixed threshold in the prior art is prone to control instruction oscillation, and the dynamic weight distribution mechanism adopted in the scheme can smoothly transition different control rules, significantly improving the stability of the unit operation. Through the above technical scheme, the technical problem of poor adaptability of the control strategy under complex wind conditions is effectively solved, and the optimal control rule combination can be automatically selected when the wind condition characteristics are not clear. Through the synergistic effect of fuzzy recognition and dynamic weight distribution, the limitations of single control rule under complex working conditions are avoided, and control conflicts caused by parallel execution of multiple rules are prevented, thereby maximizing power generation efficiency under the premise of ensuring safe operation of the unit.

[0063] In an embodiment of the present specification, a plurality of unit control rules of similar wind condition types are called, and each control rule is weighted and distributed according to the operation data to generate a fusion control instruction, including: Calculate the fuzzy membership degree of the current wind condition characteristic data and the preset wind condition type, and select the wind condition type with fuzzy membership degree greater than or equal to the preset fuzzy threshold as the candidate control rule set; Determine the applicable weight of each candidate control rule based on the unit safety state, power grid dispatching demand and historical success rate in the operation data; wherein the applicable weight reflects the adaptation degree of the control rule to the current operation data, and the higher the weight value, the more priority is given; Weighted fusion of the output control parameters of each control rule to generate the final fusion control instruction.

[0064] In the embodiment, the fuzzy membership degree refers to a quantitative index of the matching degree between the current wind condition characteristic data and the preset wind condition type, which can be realized by using a fuzzy logic algorithm or a similarity calculation model, and is used to select candidate control rules with high correlation with the current wind condition. The candidate control rule set refers to a plurality of potential applicable control rule sets selected by fuzzy membership degree, which can be generated by using a threshold filtering or sorting selection method, and is used to cover the multiple control requirements that may exist in the current wind condition. The applicable weight refers to a priority parameter reflecting each candidate control rule in the current operating environment, which can be determined by a multi-factor weighted evaluation model, and the weight value is dynamically adjusted according to the unit safety state, power grid dispatching demand and historical success rate to ensure the adaptability of the control strategy. Weighted fusion refers to the process of integrating the output parameters of different control rules according to the weight, which can be realized by using a linear weighting or nonlinear interpolation algorithm, and is used to generate a comprehensive control instruction to balance multiple target requirements.

[0065] Specifically, when the system detects that the current wind condition matches the preset type below a set threshold, the fuzzy recognition mode is activated. At this time, by calculating the fuzzy membership of the wind condition feature data and each preset wind condition type, a candidate rule set with a matching degree exceeding the minimum requirement is screened out. Subsequently, based on the real-time monitored unit safety state parameters, power grid dispatching power demand and historical control success rate data, each candidate rule is multi-dimensionally evaluated to determine its applicable weight. Finally, the control parameters (such as pitch angle setting, power limit value, etc.) corresponding to each rule are fused and calculated according to the weight to generate a comprehensive control instruction considering safety and power generation efficiency.

[0066] The embodiment can effectively handle the control decision problem under the boundary wind condition by establishing a fuzzy recognition mechanism, and improve the control precision by using the synergistic effect of multiple rules. The embodiment introduces multi-dimensional evaluation of unit safety state, power grid demand and historical success rate, so that the control strategy has stronger environmental adaptability. Through the above technical solution, intelligent optimization selection of the control strategy can be realized in the case of fuzzy or mixed wind condition. The method effectively solves the poor adaptability problem of the traditional control method under the boundary condition, reduces the misjudgment risk through the multi-rule fusion mechanism, while ensuring the operation stability of the unit under complex working conditions and the power grid dispatching response capability, and is particularly suitable for the atypical wind condition scene frequently occurring in the wind farm, which helps to prolong the service life of the equipment and improve the power generation benefit.

[0067] In an embodiment of the present specification, when it is identified that the current wind condition type is a transition type wind condition, the unit control rule includes: According to the wind condition feature change trend in the preset time window, the wind condition is divided into multiple evolution process stages; According to the dynamic coupling relationship between different evolution process stages and operating feature data, a stage response rule is defined.

[0068] In the embodiment, the transition type wind condition refers to a wind condition in which the wind speed, wind direction or turbulence intensity is in a continuous change state, which can be realized by trend identification of wind condition data through a time series analysis algorithm, and is used to solve the problem that the traditional method cannot effectively handle the dynamic change wind condition. The evolution process stage refers to the decomposition of the continuously changing wind condition into time periods with clear characteristics, which can be used to realize the accurate matching of the control strategy and the wind evolution process by using a sliding window statistical method combined with a clustering algorithm to divide the wind condition change mode. The dynamic coupling relationship refers to the correlation between the unit operating parameters and the wind evolution stage, which can be realized by establishing a correlation model through historical operating data to determine the adjustment priority of the control strategy in different stages.

[0069] Specifically, when the wind condition is detected to be in a transition state, first, the wind speed, wind direction angle and turbulence intensity data sequence within a preset time length are collected, and the evolution direction of the wind condition is judged by calculating the change rate index. For example, within a 10-second time window, if the standard deviation of the wind direction angle continuously increases and the wind speed change rate exceeds the threshold value, it is determined that the wind direction mutation evolution stage is entered. Subsequently, according to the association model of each stage and the state of the generator speed and the pitch angle, the corresponding pitch angle adjustment rate limiting rule is generated. In the initial stage, gradual power regulation is adopted, when entering the middle acceleration stage, it is switched to fast pitch control, and finally the conventional control mode is restored in the stable stage.

[0070] The embodiment dynamically divides the evolution stage and establishes the stage response rule, so that the control parameters can be adaptively adjusted according to the wind condition evolution process, and the control lag phenomenon is eliminated. Through the above technical scheme, a stage control strategy can be provided for the continuous change characteristics of the transition type wind condition, mechanical impact caused by sudden change of the control instruction is avoided, and through dynamic matching of the stage characteristics and the operating parameters, the load fluctuation of the unit in the wind condition evolution process is reduced, and the operation stability is improved.

[0071] In some other embodiments of the present specification, feature extraction is performed on the preprocessed operating data and wind condition data to obtain operating feature data and wind condition feature data, including: The preprocessed operating data and wind condition data are respectively subjected to cluster analysis to determine the center points of each cluster; Operating features and wind condition features are respectively extracted from the center points of each cluster to form operating feature data and wind condition feature data.

[0072] In the embodiment, the operating data includes parameters such as generator speed, pitch angle, power output, etc. Through cluster analysis, these data can be divided into different clusters, and each cluster represents a specific operating state mode. For example, one cluster may represent normal operating state, and another cluster may represent high-load operating state. The wind condition data includes parameters such as wind speed, wind direction, turbulence intensity, etc. Through cluster analysis, these data can be divided into different clusters, and each cluster represents a specific wind condition mode. For example, one cluster may represent smooth wind condition, and another cluster may represent gust wind condition.

[0073] The center point of a cluster is a representative feature point of the data in the cluster, which can usually be determined by calculating the mean value of all data points in the cluster. This center point can reflect the typical features of the data in the cluster. Operating features and wind condition features are respectively extracted from the center points of each cluster to form operating feature data and wind condition feature data.

[0074] The center points of the operation data clusters are extracted to obtain features, such as the mean value of the generator speed, the variance of the pitch angle, the extreme value of the power output, and the like. These features can represent the typical characteristics of the operation state mode. The center points of the wind condition data clusters are extracted to obtain features, such as the mean value of the wind speed, the change rate of the wind direction, the standard deviation of the turbulence intensity, and the like. These features can represent the typical characteristics of the wind condition mode. The extracted features are combined into feature vectors, and the feature vectors of the operation data are referred to as operation feature data, and the feature vectors of the wind condition data are referred to as wind condition feature data.

[0075] The embodiment introduces clustering analysis to pre-process the operation data and the wind condition data, and then extracts feature data, so that the representativeness of feature extraction is improved, the accuracy of wind condition recognition is enhanced, the adaptability of the control strategy is improved, the calculation efficiency is optimized, and the robustness of the system is enhanced.

[0076] Based on the same overall inventive concept, the application also protects a control device for a wind turbine based on wind conditions, such as Figure 2 as shown in Figure 2 is a structural schematic diagram of the control device for the wind turbine based on wind conditions provided by the embodiment of the application. The control device for the wind turbine based on wind conditions provided by the application is described below, and the control device for the wind turbine based on wind conditions described below can be correspondingly referred to the control method for the wind turbine based on wind conditions described above.

[0077] The control device for the wind turbine based on wind conditions comprises a data acquisition module 201, a pre-processing module 202, a feature extraction module 203, a wind condition recognition module 204, a rule generation module 205, and a turbine control module 206.

[0078] The data acquisition module 201 is configured to acquire operation data and wind condition data of the wind turbine. The pre-processing module 202 is configured to pre-process the operation data and the wind condition data. The feature extraction module 203 is configured to extract features from the pre-processed operation data and wind condition data to obtain operation feature data and wind condition feature data. The wind condition recognition module 204 is configured to recognize a wind condition type represented by the wind condition feature data. The rule generation module 205 is configured to, when the wind condition feature data indicates that the current wind condition is a preset wind condition type, select a corresponding turbine control rule in combination with the preset wind condition type and the operation feature data. The turbine control module 206 is configured to control the wind turbine based on the turbine control rule.

[0079] Figure 3 is a structural schematic diagram of an electronic device provided by the embodiment of the application.

[0080] As Figure 3As shown, the electronic device can include a processor 310, a communications interface 320, a memory 330, and a communications bus 340, wherein the processor 310, the communications interface 320, and the memory 330 complete communications with each other through the communications bus 340. The processor 310 can invoke a logical instruction in the memory 330 to execute the wind condition-based wind turbine control method.

[0081] In addition, the logical instruction in the memory 330 described above can be implemented in the form of a software function unit and sold or used as an independent product, and can be stored in a computer-readable storage medium. Based on such understanding, the technical solutions of the present application essentially or parts of the prior art that contribute to the technical solutions or parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0082] On the other hand, the present application also provides a computer program product, which includes a computer program, the computer program can be stored on a non-transitory computer readable storage medium, and the computer program is executed by a processor, so that the computer can execute the wind condition-based wind turbine control method provided by the above-mentioned methods.

[0083] In yet another aspect, the present application also provides a non-transitory computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the wind condition-based wind turbine control method provided by the above-mentioned methods.

[0084] The device embodiments described above are only schematic, wherein the units shown as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, i.e., they can be located in one place, or distributed on multiple network units. Part or all of the modules can be selected according to actual needs to achieve the purpose of the present embodiment. Those skilled in the art can understand and implement without creative labor.

[0085] Those skilled in the art can clearly understand the technical solutions of the various embodiments from the above description of the embodiments, and the various embodiments can be implemented by means of software with the necessary general hardware platforms, and of course, can also be implemented by hardware. Based on such understanding, the above technical solutions, essentially or in other words, the part of the prior art that makes a contribution, can be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, and the like, and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0086] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, rather than limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for some technical features therein; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A control method for a wind turbine generator system based on wind conditions, characterized in that: include: Obtain wind turbine operation data and wind condition data; Preprocessing the operation data and the wind condition data; Performing feature extraction on the pre-processed operation data and wind condition data to obtain operation feature data and wind condition feature data; Identifying the type of wind condition represented by the wind condition characteristic data; When the wind condition characteristic data indicates that the current wind condition is a preset wind condition type, selecting a corresponding unit control rule in combination with the preset wind condition type and the operation characteristic data; Based on the wind turbine generator set control rule, the wind turbine generator set is controlled.

2. The wind turbine control method based on wind conditions according to claim 1, characterized in that: When the preset wind condition type is a storm, the unit control rules include: If it is detected that the current wind speed is greater than the preset cut-out wind speed, the power upper limit of the wind turbine is limited, and the power setting value is dynamically adjusted according to the pre-created wind speed power interpolation table; The wind speed power interpolation table includes a mapping relationship between multiple sets of wind speed values ​​and corresponding power limits, and the power limit decreases as the wind speed increases, so that the unit maintains a power generation operation state.

3. The wind turbine control method based on wind conditions according to claim 1, characterized in that: When the preset wind condition type is gust, the unit control rules include: Monitor the generator speed acceleration; If the acceleration continues to rise and exceeds a preset threshold, the pitch angle is limited to a preset minimum angle limit; The minimum angle limit is determined by load iterative optimization to speed up the response speed of the pitch system.

4. The wind turbine control method based on wind conditions according to claim 1, characterized in that: When the preset wind condition type is a sudden change in wind direction, the unit control rules include: Detect current yaw deviation; If the yaw deviation exceeds a preset limit, the pitch angle is raised to a corresponding value according to a pre-created interpolation table of minimum pitch angles for wind deviation; The interpolation table includes a mapping relationship between multiple sets of yaw deviation values ​​and minimum pitch angles, and the pitch angle increases as the deviation increases, so as to reduce the unbalanced load of the unit.

5. The wind turbine control method based on wind conditions according to claim 1, characterized in that: When the preset wind condition type is emergency crosswind, the unit control rules include: If it is detected that the generator speed of the wind turbine generator exceeds the safety threshold and the pitch control system feeds back a fault signal, the yaw drive of the wind turbine generator is controlled to perform a 90° sidewind action and lock the yaw state until it is manually reset.

6. The wind turbine control method based on wind conditions according to claim 1, characterized in that: When the preset wind condition type is turbulence, the unit control rules include: Calculate turbulence intensity based on wind speed sequences of preset duration; Dynamically adjusting the power upper limit of the wind turbine generator set according to the turbulence intensity and a pre-created turbulence power limit interpolation table; The turbulence limit power interpolation table includes a mapping relationship between multiple sets of turbulence intensity values ​​and power limits, and the power limit decreases as the turbulence intensity increases, so as to reduce the fatigue load of the unit.

7. The wind turbine control method based on wind conditions according to claim 1, characterized in that: When the preset wind condition type is a composite wind condition, the unit control rules include: Dynamically integrate multiple unit control rules according to preset priority rules; Wherein, the composite wind condition is a wind condition in which at least two preset wind condition types exist simultaneously; The priority rules are sorted based on the degree of impact of wind conditions on the safety and power generation efficiency of the unit, and the control rules with the greatest impact on safety are executed first.

8. The wind turbine control method based on wind conditions according to claim 1, characterized in that: When the preset wind condition type is a composite wind condition, the unit control rules include: When the current wind condition type is identified as one of the preset wind condition types, but its matching degree is lower than the preset matching threshold, the system enters the fuzzy recognition mode; In the fuzzy recognition mode, multiple unit control rules with similar wind conditions are called, and weights are assigned to each control rule based on the operating data to generate fusion control instructions.

9. The wind turbine control method based on wind conditions according to claim 8, characterized in that: Call multiple unit control rules with similar wind conditions, assign weights to each control rule based on operating data, and generate fusion control instructions, including: Calculate the fuzzy membership between the current wind condition characteristic data and the preset wind condition type, and select the wind condition type whose fuzzy membership is greater than or equal to the preset fuzzy threshold as the candidate control rule set; Determine the applicable weight of each candidate control rule based on the unit safety status, grid dispatch requirements, and historical success rate in the operating data; wherein the applicable weight reflects the adaptability of the control rule to the current operating data, and the higher the weight value, the higher the priority; The output control parameters of each control rule are weighted and fused to generate the final fusion control instruction.

10. The wind turbine control method based on wind conditions according to claim 1, characterized in that: When the current wind condition type is identified as a transitional wind condition, the unit control rules include: According to the changing trend of wind condition characteristics within the preset time window, the wind condition is divided into multiple evolution process stages; According to the dynamic coupling relationship between different evolution process stages and operation characteristic data, the phased response rules are defined.

Images