Wind power variable pitch and rotating speed cooperative control method, system and equipment and medium

Abstract

The invention relates to the field of wind power research, and discloses a wind power variable pitch and rotating speed cooperative control method, system and device and a medium, and the method comprises the steps: extracting operation space-time working condition characteristics in a target time window according to obtained operation state data and incoming flow environment data, and obtaining working condition space-time comprehensive characteristic indexes; calculating a unit working condition average power value corresponding to the target time window, forming a working condition level power feature set, and obtaining a working condition power difference index according to the dispersion degree of the data; performing feature matching on the obtained indexes, and calculating a cooperative control fusion weight on the basis of the basic weight of the variable pitch channel and the basic weight of the rotating speed or torque channel; and according to the power grid dispatching information and the unit control constraint condition, a cooperative control instruction is generated, and the wind generating set executes the cooperative control instruction to complete cooperative control of the variable pitch and the rotating speed. According to the method, under the condition that grid connection and safety constraints are met, power fluctuation and loads are reduced, variable pitch abrasion is reduced, and robustness is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of wind power research, and in particular to a wind power variable pitch and rotational speed cooperative control method, system, device and medium. BACKGROUND

[0002] The wind turbine generator set usually adopts a zoning control strategy: in the low wind speed zone, the constant optimal tip speed ratio or power law torque control is used to improve energy capture, and in the rated zone, the variable pitch is mainly used to maintain the rated power and limit the rotational speed. In existing engineering, the "pitch ring" and the "rotational speed / torque ring" are designed relatively independently: the pitch angle is used to adjust the aerodynamic thrust and the aerodynamic power, and the electromagnetic torque or speed of the generator is used to fine-tune the power and balance the inertia.

[0003] However, under the conditions of strong turbulence, rapid swing of wind direction and yaw mismatch, wake interference, and grid side limited power / peak shaving, there will be target conflicts and coupling competitions between the two loops. On the one hand, frequent action of variable pitch leads to thermal wear / abrasion and structural load fluctuation of the actuator; on the other hand, pure dependence on rotational speed / torque will introduce power oscillation and degradation of grid connection quality. At the same time, there are difficulties in measurement and modeling: ① the measured power at the grid connection point contains basic losses such as the converter and the variable pitch; ② the application of the "reference power curve" has a drift in caliber due to individual differences caused by air density, temperature and station topology; ③ the incoming flow sensor (cabin wind speed / direction, airborne laser radar) may not be available during salt spray, icing or maintenance, resulting in failure of working condition evaluation and feedforward control. Therefore, there is a lack of a cooperative control mechanism in the prior art that can quantitatively trade off between time and space working conditions and power consistency / load, and can remain robust in the presence of sensor abnormalities and grid constraints. SUMMARY

[0004] In view of the above existing problems, the present application is proposed.

[0005] Therefore, the present application provides a wind power variable pitch and rotational speed cooperative control method, system, device and medium, which solves the problem that the existing independent variable pitch and rotational speed control of wind power cannot simultaneously consider power stability and load suppression under complex working conditions, and lacks robust processing of loss stripping and sensor failure.

[0006] To solve the above technical problems, the present application provides the following technical solutions: In a first aspect, the present application provides a wind power variable pitch and rotational speed cooperative control method, comprising: extracting the running time and space working condition characteristics of the wind turbine generator set in a target time window according to the obtained running state data and incoming flow environment data of the wind turbine generator set, to obtain a working condition time and space comprehensive characteristic index; Based on the operating state data, inflow environment data and reference power curve, an average power value of a unit operating condition corresponding to the target time window is calculated, an operating condition level power feature set is formed, and an operating condition power difference degree index is obtained according to the discrete degree of data in the set; The operating condition space-time comprehensive feature index and the operating condition power difference degree index are subjected to feature matching, and a cooperative control fusion weight is calculated on the basis of a variable pitch passage basic weight and a rotation speed or torque passage basic weight; According to the cooperative control fusion weight, power grid scheduling information and unit control constraint conditions, a cooperative control instruction is generated, and the wind turbine generator unit executes the cooperative control instruction to complete the cooperative control of variable pitch and rotation speed.

[0007] As a preferred scheme of the wind power variable pitch and rotation speed cooperative control method, the operating state data of the wind turbine generator unit includes rotor rotation speed, pitch angle, generator active power, electromagnetic torque, nacelle yaw angle, converter load rate and variable pitch system working duty cycle; the inflow environment data includes wind speed, wind direction and turbulence intensity; Different converter load rates and variable pitch system working duty cycles correspond to different basic loss power models, and the basic loss power model is used to separate the basic loss from the measured electric power to obtain the net output power.

[0008] As a preferred scheme of the wind power variable pitch and rotation speed cooperative control method, the calculation of the operating condition space-time comprehensive feature index includes: ; Wherein, represents the operating condition space-time comprehensive feature index, represents the end time of the target time window, represents the start time of the target time window, represents the cumulative change amount of wind direction in the target time window, represents the average wind speed in the target time window, represents the average absolute yaw mismatch angle in the target time window, represents the average turbulence intensity in the target time window, , , , , All represent space-time feature weight coefficients.

[0009] As a preferred scheme of the wind power variable pitch and rotation speed cooperative control method, the operating condition power difference degree index includes: Determine a current basic loss power according to the converter load rate and the variable pitch system working duty cycle, and deduct the current basic loss power from the measured electric power to obtain a net output power; Integrate the net output power in the target time window and divide by the window length to obtain a unit condition average power value; Construct a power feature set according to a two-dimensional binning of wind speed and wind direction, and collect the unit condition average power values in the same bin based on a reference power curve corrected by density, and count the number of samples of the unit condition average power values in each bin; If the number of samples exceeds a preset threshold, calculate the standard deviation of all unit condition average power values in the bin, and use the standard deviation as a condition power difference degree indicator of the current bin to represent the dispersion degree of power output under the condition; if the number of samples is less than the preset threshold, the condition power difference degree indicator is not calculated.

[0010] As a preferred scheme of the wind power variable pitch and rotating speed cooperative control method, the unit control constraint conditions include rotating speed upper and lower limit constraints, pitch angle and variable pitch rate upper limit constraints, generator torque / current limit constraints, nacelle / blade root / tower bottom load limit constraints and grid connection specifications; the cooperative control instructions include a cooperative control priority table, a pitch angle reference, a rotating speed reference, a generator torque reference, a variable pitch rate threshold and control switching-in and switching-out timing; the fusion weight is used to update the priority or control gain of the variable pitch and rotating speed or torque channel in real time.

[0011] As a preferred scheme of the wind power variable pitch and rotating speed cooperative control method, the modification of the cooperative control instructions based on grid side power constraints includes: When there is a grid power limit instruction or a energy storage peak shaving instruction, the priority is re-distributed according to the channel weight after gating processing, so that the weighted comprehensive value of the condition power difference degree indicator and the structural load indicator is reduced to the minimum while meeting the power limit constraint; the structural load indicator includes at least one of the blade root bending moment, the tower bottom bending moment and the drive chain torque.

[0012] As a preferred scheme of the wind power variable pitch and rotating speed cooperative control method, the method further includes: When the wind speed and wind direction sensors or wind measurement laser radars of the unit are unavailable, the incoming flow data of adjacent units and wind measurement towers within the internal communication range of the wind farm are acquired, and are jointly weighted according to the attenuation relationship with the distance of the unit and the consistency of the relative wind direction, to estimate the wind speed, wind direction and turbulence intensity of the unit as the replacement incoming flow data for calculating the condition space-time comprehensive feature indicator; When the native group sensor recovers available, the deviation compensation amount is established according to the difference between the recovered native inflow data and the alternative inflow data, and the wind speed, the wind direction, and the unit operating condition average power value and the operating condition power difference degree index are re-estimated according to the deviation compensation amount, so as to realize smooth switching and precision correction.

[0013] In a second aspect, the present application provides a wind power variable pitch and rotating speed cooperative control system, comprising: A perception module is configured to acquire operating state data and inflow environment data of the wind turbine generator set. An operating condition feature calculation module is configured to extract operating space-time condition features of the wind turbine generator set in a target time window according to the operating state data and the inflow environment data, and obtain an operating condition space-time comprehensive feature index. A power feature analysis module is configured to calculate a unit operating condition average power value corresponding to the target time window based on the operating state data, the inflow environment data and a reference power curve, form an operating condition level power feature set, and obtain an operating condition power difference degree index according to the dispersion degree of data in the set. A weight fusion module is configured to perform feature matching on the operating condition space-time comprehensive feature index and the operating condition power difference degree index, and calculate a cooperative control fusion weight based on a preset variable pitch channel basic weight and a rotating speed or torque channel basic weight. A control instruction generation and execution module is configured to generate a cooperative control instruction according to the cooperative control fusion weight, power grid scheduling information and unit control constraint conditions, and the wind turbine generator set executes the cooperative control instruction to complete the cooperative control of the variable pitch and the rotating speed.

[0014] In a third aspect, the present application provides an electronic device comprising a memory and a processor; the memory is configured to store computer executable instructions, and the processor is configured to execute the computer executable instructions to realize the steps of a wind power variable pitch and rotating speed cooperative control method.

[0015] In a fourth aspect, the present application provides a computer readable storage medium storing computer executable instructions, which are executed by a processor to realize the steps of a wind power variable pitch and rotating speed cooperative control method.

[0016] Compared with the prior art, the present application has the beneficial effects that: the present application provides a wind power variable pitch and rotating speed cooperative control method, system, device and medium, by constructing a cooperative control mechanism integrating time and space working condition characteristics and power difference degree, dynamic weight distribution and priority adjustment of the variable pitch and rotating speed loop are realized, power fluctuation and structural load under complex inflow conditions are effectively reduced, and frequent action and wear of the variable pitch actuator are reduced. The present application establishes a basic loss power model taking the converter load rate, variable pitch duty cycle and environmental temperature as independent variables, decomposes the measured active power into net output power, significantly reduces the power aperture deviation caused by different working conditions / model / temperatures, and provides a consistent benchmark for subsequent statistics and optimization. In addition, when the sensor fails, the method of the present application can intelligently fuse the data of adjacent machines and wind measurement towers and perform deviation compensation, significantly enhancing the adaptability and robustness of the unit under abnormal working conditions, and better meeting the coordinated control demand under the constraints of power grid peak regulation and limited power. BRIEF DESCRIPTION OF DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0018] Figure 1 The overall flow logic diagram of the wind power variable pitch and rotating speed cooperative control method provided by an embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0019] In order to make the above-mentioned purposes, features and advantages of the present application more apparent and easy to understand, the specific embodiments of the present application will be described in detail below with reference to the drawings of the specification. Obviously, the described embodiments are only a part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should be within the scope of protection of the present application.

[0020] Embodiment 1, refer to Figure 1 For an embodiment of the present application, a wind power variable pitch and rotating speed cooperative control method is provided, as shown in Figure 1 specifically comprising the following steps: S100: According to the obtained operating state data and inflow environment data of the wind turbine generator, the running time and space working condition characteristics of the wind turbine generator in the target time window are extracted, and the working condition time and space comprehensive characteristic index is obtained; S200: based on the operating state data, the inflow environment data and the reference power curve, calculating a unit working condition average power value corresponding to a target time window to form a working condition level power feature set, and obtaining a working condition power difference degree index according to the discrete degree of data in the set; S300: performing feature matching on the working condition space-time comprehensive feature index and the working condition power difference degree index, and calculating a cooperative control fusion weight on the basis of a preset variable pitch passage basic weight and a rotating speed or torque passage basic weight; S400: generating a cooperative control instruction according to the cooperative control fusion weight, power grid scheduling information and unit control constraint conditions, and executing the cooperative control instruction by the wind turbine generator to complete the cooperative control of variable pitch and rotating speed.

[0021] It should be noted that in the existing wind power control technology, the variable pitch control and the rotating speed / torque control are usually independent of each other. In complex working conditions such as turbulence, rapid change of wind direction, wake interference or power grid power limitation, the variable pitch actuator is prone to frequent action, the structural load fluctuation is increased, the power output is oscillated and the grid quality is decreased due to target conflict. Meanwhile, the loss of the converter and the variable pitch system contained in the measured power is difficult to accurately separate, resulting in power control reference drift. In addition, when the inflow sensor fails, there is no reliable alternative data source, which causes insufficient robustness of the unit in abnormal working conditions.

[0022] It should be noted that the above steps S100-S400 realize dynamic weight distribution and priority adjustment of the variable pitch and rotating speed loop by constructing a cooperative control mechanism that fuses space-time working condition features and power difference degree, effectively reducing power fluctuation and structural load under complex inflow conditions, and reducing frequent action and wear of the variable pitch actuator. The present application establishes a basic loss power model with the converter load rate, the variable pitch duty cycle and the environmental temperature as independent variables, decomposes the measured active power into net output power, significantly reduces the power aperture deviation caused by different working conditions / model / temperature, and provides a consistent reference for subsequent statistics and optimization. In addition, when the sensor fails, the method of the present application can intelligently fuse the data of adjacent machines and wind measurement towers and perform deviation compensation, significantly enhancing the adaptability and robustness of the unit in abnormal working conditions, and better meeting the coordinated control demand under the power grid peak regulation and power limitation constraints.

[0023] In the embodiment of the present application, the above step S100 extracts the running space-time working condition features of the wind turbine generator in the target time window according to the obtained operating state data and inflow environment data of the wind turbine generator, and obtains the working condition space-time comprehensive feature index including the following sub-steps A1 and A2: In A1: obtaining the operating state data and inflow environment data of the wind turbine generator; Specifically, the operating state data of the wind turbine generator set includes rotor speed, pitch angle, generator active power, electromagnetic torque, nacelle yaw angle, converter load rate and variable pitch system working duty cycle; the incoming flow environment data includes wind speed, wind direction and turbulence intensity; Specifically, the data sampling frequency is not less than 10Hz, and the time stamp is unified to the same basis and aligned by interpolation. In the embodiment of the application, different converter load rates correspond to different basic loss power models of the variable pitch system working duty cycle, wherein the converter load rate is the ratio of the current output active power to the rated active power, the variable pitch system working duty cycle is the ratio of the actuator drive occupation time length to the window time length in the window, and the basic loss power model is used to separate the basic loss from the measured electric power to obtain the net output power.

[0024] Specifically, the basic loss power model is obtained by a regression model, and the regression model takes at least the converter load rate, the variable pitch duty cycle and the nacelle environmental temperature as input; the update period of the basic loss power model is not more than 24h, and a sliding window is used for retraining to suppress drift.

[0025] In A2: extract the operating space-time working condition characteristics of the wind turbine generator set in the target time window to obtain the working condition space-time comprehensive feature index; Specifically, the extraction of the operating space-time working condition characteristics of the wind turbine generator set in the target time window includes the end time, the start time, the cumulative change amount of wind direction, the average wind speed, the average absolute yaw mismatch angle and the average turbulence intensity of the target time window. Specifically, the calculation of the working condition space-time comprehensive feature index includes: ; Wherein, represents the working condition space-time comprehensive feature index, represents the end time of the target time window, represents the start time of the target time window, represents the cumulative change amount of wind direction in the target time window, represents the average wind speed in the target time window, represents the average absolute yaw mismatch angle in the target time window, represents the average turbulence intensity in the target time window, 、 、 、 、 all represent space-time feature weight coefficients.

[0026] It should be noted that the step S100 extracts the spatio-temporal working condition characteristic index capable of comprehensively reflecting the wind direction change, turbulence intensity, yaw mismatch and time span based on the inflow environment data within the target time window, so as to quantitatively evaluate the non-stationarity and complexity of the current working condition.

[0027] In the embodiment of the present application, the step S200 calculates the unit working condition average power value corresponding to the target time window based on the running state data, the inflow environment data and the reference power curve, forms the working condition level power feature set, and obtains the working condition power difference index according to the dispersion degree of the data in the set, including the following sub-steps B1-B4: In B1: the current basic loss power is determined according to the converter load rate, the cabin environment temperature and the pitch system working duty cycle, and the current basic loss power is deducted from the measured electric power to obtain the net output power; In B2: the net output power is integrated in the target time window and divided by the window length to obtain the unit working condition average power value , which is expressed by the formula: ; wherein, represents the length of the target window, represents the net output power.

[0028] In B3: the power feature set is constructed according to the wind speed-wind direction two-dimensional binning, and the unit working condition average power values in the same bin are collected based on the corrected reference power curve, and the sample number of the unit working condition average power value is counted in each bin; wherein the wind speed bin width is 1 m / s and the wind direction bin width is 10°; Specifically, the reference power curve is corrected according to the air density and temperature, including: calculating the current air density according to the real-time measurement values of the cabin temperature and the air pressure sensor, and correcting the reference power curve under the standard air density according to the scaling relationship, so as to obtain the power reference curve suitable for the current actual atmospheric conditions and having the same caliber, thereby providing an accurate basis for the subsequent collection and comparison of the unit working condition average power.

[0029] In B4: if the sample number exceeds the preset threshold, the standard deviation of all unit working condition average power values in the bin is calculated, and the standard deviation is taken as the working condition power difference index of the current bin to represent the dispersion degree of the power output under the working condition; if the sample number is less than the preset threshold, the working condition power difference index is not calculated temporarily; In the embodiment of the present application, the preset threshold is 20, which is the minimum requirement to ensure that the power data in the bin has enough samples to calculate a reliable standard deviation, so as to avoid the distortion or excessive fluctuation of the difference index caused by too few samples, and to take into account the data accumulation speed of the common operating conditions in the actual operation of the wind farm, so as to ensure that the control system can update the power difference index in time and stably.

[0030] In the embodiment of the present application, the standard deviation of the average power value of all unit operating conditions in the bin is calculated, which is expressed by the formula: ; Among them, represents the operating condition power difference index of the current bin, n represents the number of samples under the same bin, represents the mean value of the current bin.

[0031] It should be noted that the step S200 calculates the unit operating condition average power and constructs the power feature set, and further obtains the power difference index by combining the net power output analysis, which effectively reveals the dispersion degree of the unit power output under the same inflow condition, and provides a quantifiable basis for identifying performance degradation, wake effect or control mismatch.

[0032] In the embodiment of the present application, the step S300 performs feature matching on the operating condition space-time comprehensive feature index and the operating condition power difference index, and calculates the cooperative control fusion weight based on the preset variable pitch passage basic weight and the rotation speed or torque passage basic weight, which includes: Specifically, the step of performing feature matching on the operating condition space-time comprehensive feature index and the operating condition power difference index includes: Standardize the two types of indexes according to the historical statistical range respectively, and divide them into three grades: low, medium and high (corresponding to stable, general and strong operating conditions; small, medium and large power difference); Establish a matching matrix: when the operating condition is strong and the power difference is large, increase the priority of the variable pitch passage to quickly stabilize the angle and suppress the load; when the operating condition is stable and the power difference is small, increase the priority of the rotation speed / torque passage to reduce the variable pitch action and wear; the rest of the combinations gradually transition from variable pitch to rotation speed / torque in order; To avoid frequent jitter, set up and down hysteresis loop for gear switching; only when any index continuously crosses the threshold for several sampling periods is the switching allowed; If the structural load is close to the limit value or there is a drop-out power instruction on the grid side, additional penalties or additions are added based on the matching matrix results, so that the priority is tilted to the passage that is more conducive to load limiting and stable power; Get the passage priority and control gain ratio at the current time; the bottom control loop allocates the adjustment range of pitch, rotation speed / torque accordingly.

[0033] Specifically, the normalized working condition space-time comprehensive feature index and the working condition power difference degree index are fused in multiple dimensions, are input to an activation function for nonlinear mapping through weighted linear combination, and a collaborative control fusion weight between 0 and 1 is generated on the basis of the preset variable pitch channel basic weight and the rotational speed or torque channel basic weight. The collaborative control fusion weight can dynamically reflect the comprehensive influence of the space-time unsteady characteristics and the power output dispersion degree on the control channel under the current working condition, so as to realize adaptive matching according to real-time working condition characteristics.

[0034] Specifically, the collaborative control fusion weight W is calculated as: ; wherein, represents an activation function mapping operation, represents the normalized variable pitch channel basic weight, represents the normalized rotational speed or torque channel basic weight, represents the normalized working condition power difference degree index, represents the normalized working condition space-time comprehensive feature index, , , , all represent adjustment coefficients. The preset variable pitch channel basic weight and the rotational speed or torque channel basic weight are both between 0 and 1, and the sum of the two is 1. Specifically, the collaborative control fusion weight is used to generate or update the priority or control gain of the variable pitch and rotational speed or torque channels in real time. The update of the priority or control gain adopts an up-down hysteresis loop to avoid frequent switching.

[0035] It should be noted that the above step S300 matches and fuses the space-time working condition characteristics and the power difference degree index, and dynamically generates a collaborative control fusion weight on the basis of the preset variable pitch and rotational speed channel basic weights, so as to adaptively adjust the priority and gain distribution of the variable pitch and rotational speed control loops according to different working condition characteristics, thereby enhancing the coordination ability of the system under complex conditions.

[0036] In the embodiment of the application, the above step S400 generates a collaborative control instruction according to the collaborative control fusion weight, the power grid scheduling information and the unit control constraint condition, and the wind turbine generator set executes the collaborative control instruction to complete the collaborative control of the variable pitch and the rotational speed, including the following sub-steps D1~D4: In D1: a collaborative control instruction is generated according to the collaborative control fusion weight, the power grid scheduling information and the unit control constraint condition; Specifically, the unit control constraints include rotational speed upper and lower limit constraints, pitch angle and pitch rate upper limit constraints, generator torque / current limit constraints, nacelle / blade root / tower bottom load limit constraints, and grid connection specifications; the generated cooperative control instructions include a cooperative control priority table, a pitch angle reference, a rotational speed reference, a generator torque reference, a pitch rate threshold, and control switching-in and switching-out timing; Specifically, when control targets conflict, the priority table and the gating gain are executed, and saturation protection and anti-integration wind up strategies are adopted; when any hard constraint is triggered, the grid connection specifications are prioritized, and the remaining degrees of freedom are then distributed according to the updated cooperative control fusion weights.

[0037] In D2: modifying the cooperative control instructions based on grid-side power constraints includes: when there are grid power limit instructions or energy storage peak shaving instructions, re-distributing priorities according to the channel weights after gating processing, while meeting the power limit constraints, prioritizing the weighted comprehensive value of the operating condition power difference index and the structural load index to be minimized; the structural load index includes at least one of the blade root bending moment, the tower bottom bending moment, and the drive chain torque; Specifically, the calculation of the weighted comprehensive value of the operating condition power difference index and the structural load index J is as follows: ; wherein, denotes the weighted value of the normalized structural load index of the blade root bending moment, the tower bottom bending moment, and the drive chain torque, , both denote the weighting coefficients, and ; the weighted comprehensive value J of the operating condition power difference index and the structural load index is solved approximately by heuristic or quadratic programming at a time scale of every 1-5 s to update the priority and the reference value.

[0038] In D3: when the wind speed, wind direction sensor or wind measurement laser radar of the local unit is unavailable, the incoming flow data of the adjacent unit and the wind measurement tower within the internal communication range of the wind farm is obtained, and the wind speed, wind direction and turbulence intensity of the local unit are estimated as the replacement incoming flow data for calculating the operating condition space-time comprehensive feature index according to the attenuation relationship with the distance of the local unit and the consistency of the relative wind direction; In D4: when the local unit sensor recovers to be available, the deviation compensation quantity is established according to the difference between the recovered local incoming flow data and the replacement incoming flow data, and the wind speed, wind direction, unit operating condition average power value and operating condition power difference index are re-estimated according to the deviation compensation quantity to realize smooth switching and accuracy correction; Specifically, when the local sensor recovers to be available, the system first calculates the difference between the recovered local inflow data and the substitute inflow data, and then recursively filters the difference sequence by using an exponential weighted moving average algorithm to generate a smooth and gradual deviation compensation; the compensation is applied to continuously correct the current estimated wind speed, wind direction, unit operating condition average power value and power difference index in real time, so as to realize smooth transition from substitute data to local measured data at the initial stage of sensor data recovery, effectively suppress the estimation value jump at the switching moment, and finally achieve the purpose of precision correction and smooth transition of system state.

[0039] It should be noted that the cooperative control instruction is generated by the supervision layer in a cycle and is issued to the bottom layer controller for execution, and the complete process is as follows: a, gather inflow, unit state, grid dispatching and load monitoring data, and judge whether there is a limit power, peak regulation or safety constraint trigger; b, form a channel priority table based on the matching result of S300, and superimpose the following constraints in the following order: grid connection specification / current limit→structural load limit→speed safety margin→pitch rate limit; c, reference value generation: In the allowed pitch interval, the adjustment direction and amplitude are determined according to the priority table; when the unsteady enhancement or load rises, the opening pitch is appropriately increased to stabilize the angle and limit the load; when the working condition is stable, unnecessary pitch change is reduced; In the rated region, power stability is given priority, and speed deviation is limited; in the low wind region, the target speed of energy capture is preferentially maintained; if there is a limit power instruction, the target is converged to the target through torque reference, and small amplitude pitch adjustment is used to suppress oscillation; According to the actuator temperature rise and action frequency, the upper limit of the rate is set, and the minimum holding time is set for rapid repeated action; when the rate or frequency exceeds the threshold, the pitch weight is automatically reduced; When the inflow and power state are continuously stable for several cycles, the strategy is slowly transitioned to the speed / torque-based strategy; when rapid wind direction swing, turbulence enhancement or load close to the limit value are detected, the pitch-based strategy is quickly switched in; d, if a limit power / peak regulation instruction is received, the priority is rearranged without breaking the hard constraint, so that the comprehensive index of power fluctuation and key load is minimized; if necessary, the speed target is reduced and the pitch back sweep speed is limited to prevent re-vibration; e, when the wind speed / wind direction / laser radar is unavailable, the substitute data of the adjacent machine and the wind measurement tower are enabled and weighted according to the distance and wind direction consistency; after the sensor recovers, the reference value is smoothly switched back in a gradual deviation compensation manner to avoid sudden change; f. The generated pitch angle, rotational speed, and torque reference values are subjected to amplitude limiting and ramping, and packaged into cooperative control instructions for issuance; the bottom loop is executed at a fixed frequency, and the actual execution and deviation are returned for correction by the upper layer in the next cycle.

[0040] It should be noted that the above step S400 dynamically generates cooperative control instructions according to the fusion weight calculated in real time, the power grid dispatching requirements, and the unit safety constraints, and comprehensively adjusts the pitch angle, rotational speed, and torque reference values, so that the wind turbine generator set realizes the cooperative control target of stable power output and structural load optimization under the premise of meeting the grid connection specification and load limitation.

[0041] Embodiment 2, based on the previous embodiment, provides an application example of a wind power variable pitch and rotational speed cooperative control method, which verifies and illustrates the technical effects adopted in the method.

[0042] This embodiment takes a 3MW land-based wind turbine generator set as the object, which can adopt direct drive or semi-direct drive configuration, and its rated wind speed is 12m / s. The sensors configured by the system include nacelle anemometer and wind vane (cup + wind vane), tower top temperature and pressure sensor, blade root and tower bottom strain gauge, main shaft torque meter, generator current and voltage sampling unit, and variable pitch servo current sensor. Data acquisition is performed at a frequency of 50Hz, and time synchronization is achieved through precise time protocol or network time protocol, and finally a unified time base data frame is sent to the supervisory control layer every 1 second.

[0043] This embodiment takes 60 seconds as the sliding window length, and the window overlaps for 30 seconds, that is, the control instruction update period is 30 seconds. The original data needs to be preprocessed before feature extraction: the median ± median absolute deviation (MAD) method is used to remove outliers for each variable, linear interpolation is performed for data segments with continuous missing data of no more than 3 seconds, and data exceeding this range is marked as invalid. In order to eliminate the influence of atmospheric condition changes, the measured temperature and pressure are used to calculate the air density, and the standard reference power curve is scaled and corrected to establish a power benchmark suitable for the current environment.

[0044] Further, the basic loss power model is estimated by a quadratic polynomial regression model characterized by converter load rate, variable pitch duty cycle, and nacelle temperature. The model is based on 7-day historical data and is trained by ridge regression regularization, and is retrained every 6 hours. At least two months of data are required in the initialization stage.

[0045] Further, to evaluate the power output characteristics, the system performs two-dimensional binning statistics on the unit operating condition average power with a bin width of 1 m / s wind speed and 10° wind direction. At least 20 samples are required in each bin to calculate the operating condition power difference index δop, which is defined as the standard deviation of all unit operating condition average powers in the bin. The extreme values are removed again using the median ± 3MAD method before calculation.

[0046] Further, the operating condition space-time characteristics are composed of window length ΔT, wind direction cumulative change amount Δφ, average wind speed vavg, average absolute yaw mismatch angle γ, and average turbulence intensity T Iavg Five parameters. After normalization of each parameter in the historical 5%–95% quantile range, the operating condition space-time comprehensive characteristic index is obtained by linear weighted summation with weight coefficients α=[0.25, 0.20, 0.20, 0.20, 0.15]. The cooperative control fusion weight W is obtained by linear weighted summation of the normalized prior channel weights (W =0.6, =0.4), δop and F wind , where the adjustment coefficient β takes values [1.2, 0.8, 1.6, 1.0]. To suppress frequent fluctuations in the weight, a hysteresis interval of [0.45, 0.55] is set. The final channel weight distribution is: the pitch channel w'θ=W· , the speed / torque channel w'ω=(1-W)· .

[0047] The control command is updated every 1 to 2 seconds by the supervisory layer. The pitch angle reference increment and the generator torque reference increment are calculated by the amplitude limiting linear or piecewise linear mapping function according to the active power set value deviation, yaw mismatch angle, turbulence intensity, and speed safety margin, etc., and then multiplied by the corresponding channel weight and gain coefficient. The bottom layer pitch, torque, and speed control loops operate at a frequency of 100 Hz and use saturation limiting and anti-integral saturation measures. The system follows strict constraint priorities: grid connection specifications and current limits are the highest, followed by structural loads, speed, and finally pitch rate limits. Typical operating constraints include: speed range 0.7–1.2pu, pitch rate absolute value not greater than 8° / s, generator torque not exceeding 1.05pu.

[0048] Further, in the case of rapid changes in wind direction (Δφ>30° / 5min) and enhanced turbulence, the system increases the fusion weight W (approaching 1) to improve the priority of the variable pitch channel, to quickly stabilize the tip angle and suppress load fluctuations; in the stable downwind condition, W decreases to 0.3-0.4, and the system relies more on the speed / torque channel for fine tuning, which helps to reduce power generation noise and wear of the variable pitch system. The hysteresis gating mechanism effectively avoids frequent switching of the weight near the critical value, and the power difference index δop provides stable performance evaluation feedback after sufficient sample size.

[0049] From the above analysis, the present application realizes dynamic weight distribution and priority adjustment of the variable pitch and speed loop by constructing a cooperative control mechanism that fuses the time and space working condition characteristics and the power difference, effectively reducing power fluctuations and structural loads under complex inflow conditions, and reducing the frequent action and wear of the variable pitch actuator. The present application establishes a basic loss power model with converter load rate, variable pitch duty cycle and environmental temperature as independent variables, decomposes the measured active power into net output power, significantly reduces the power aperture deviation caused by different working conditions / models / temperatures, and provides a consistent benchmark for subsequent statistics and optimization. In addition, in the case of sensor failure, the method of the present application can intelligently fuse the data of adjacent machines and wind towers and perform deviation compensation, significantly enhancing the adaptability and robustness of the unit under abnormal working conditions, while better meeting the coordinated control requirements under the constraints of power grid peak regulation and limited power.

[0050] In embodiment 3, a wind power variable pitch and speed cooperative control system is provided, comprising: A perception module for obtaining operating state data and inflow environment data of a wind turbine generator set; A working condition characteristic calculation module for extracting the running time and space working condition characteristics of the wind turbine generator set in a target time window based on the operating state data and the inflow environment data, to obtain a working condition time and space comprehensive characteristic index; A power characteristic analysis module for calculating the unit working condition average power value corresponding to the target time window based on the operating state data, the inflow environment data and the reference power curve, forming a working condition level power characteristic set, and obtaining a working condition power difference index according to the dispersion degree of the data in the set; A weight fusion module for feature matching of the working condition time and space comprehensive characteristic index and the working condition power difference index, and calculating a cooperative control fusion weight based on the preset variable pitch channel basic weight and the speed or torque channel basic weight; A control instruction generation and execution module for generating a cooperative control instruction according to the cooperative control fusion weight, the grid dispatching information and the unit control constraint conditions, and the wind turbine generator set executing the cooperative control instruction to complete the cooperative control of variable pitch and speed.

[0051] It should be noted that the technical scheme of the wind power variable pitch and rotating speed cooperative control system and the technical scheme of the wind power variable pitch and rotating speed cooperative control method described above belong to the same concept, and the technical details of the wind power variable pitch and rotating speed cooperative control system in the embodiment are not described in detail, which can be seen from the description of the technical scheme of the wind power variable pitch and rotating speed cooperative control method described above.

[0052] The above-mentioned unit modules can be embedded in or independent of the processor in the electronic device in hardware form, or can be stored in the memory in the electronic device in software form, so as to call and execute the operations corresponding to the above-mentioned modules by the processor.

[0053] The embodiment also provides an electronic device, which comprises a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. The processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device comprises a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium. The communication interface of the electronic device is used to communicate with external terminals in a wired or wireless manner. The wireless manner can be realized through WIFI, operator network, NFC (near field communication) or other technologies. The computer program is executed by the processor to realize a wind power variable pitch and rotating speed cooperative control method. The display screen of the electronic device can be a liquid crystal display screen or an electronic ink display screen. The input device of the electronic device can be a touch layer overlaid on the display screen, or a key, trackball or touchpad arranged on the shell of the electronic device, or an external keyboard, touchpad or mouse, etc.

[0054] The embodiment also provides a computer readable storage medium, which stores a computer program. The program is executed by the processor to realize the method proposed in the above-mentioned embodiment.

[0055] The storage medium proposed in the embodiment and the method proposed in the above-mentioned embodiment belong to the same inventive concept, and the technical details not described in detail in the embodiment can be seen from the above-mentioned embodiment, and the embodiment has the same beneficial effects as the above-mentioned embodiment.

[0056] Those skilled in the art can clearly understand the present application by the description of the above embodiments, and the present application can be realized by software and necessary general hardware, and of course can also be realized by hardware, but in many cases the former is a better embodiment. Based on such understanding, the technical solutions of the present application or the part that contributes to the prior art can be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as a floppy disk, a ROM, a RAM, a flash memory, a hard disk or an optical disk, and includes a number of instructions to make an electronic device (which can be a personal computer, a server, or a network device, etc.) execute the method of the embodiments of the present application.

[0057] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present application but not limit the present application, and although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or replaced equivalently without departing from the spirit and scope of the technical solutions of the present application, and all of them should be covered in the scope of the claims of the present application.

Claims

1. A method for wind power variable-pitch and rotational speed cooperative control, characterized in that, The method comprises: According to the acquired operating state data and inflow environment data of the wind turbine generator set, the running space-time working condition characteristics of the wind turbine generator set in a target time window are extracted, and a space-time comprehensive characteristic index of the working condition is obtained; Based on the operating state data, the inflow environment data and the reference power curve, the unit working condition average power value corresponding to the target time window is calculated, a working condition level power feature set is formed, and a working condition power difference index is obtained according to the dispersion degree of the data in the set; The space-time comprehensive characteristic index of the working condition and the working condition power difference index are matched, and the cooperative control fusion weight is calculated on the basis of the variable pitch channel basic weight and the rotating speed or torque channel basic weight; According to the cooperative control fusion weight, the grid dispatching information and the unit control constraint condition, a cooperative control instruction is generated, and the wind turbine generator set executes the cooperative control instruction to complete the cooperative control of variable pitch and rotating speed.

2. The method of wind power variable pitch and rotational speed cooperative control according to claim 1, characterized in that, The operating state data of the wind turbine generator set includes rotor rotating speed, pitch angle, generator active power, electromagnetic torque, nacelle yaw angle, converter load rate and variable pitch system working duty cycle; the inflow environment data includes wind speed, wind direction and turbulence intensity; Different converter load rates and variable pitch system working duty cycles correspond to different basic loss power models, and the basic loss power model is used to separate the basic loss from the measured electric power to obtain the net output power.

3. The method of wind power variable pitch and rotational speed cooperative control according to claim 2, characterized in that, The calculation of the space-time comprehensive characteristic index of the working condition comprises: wherein, represents the comprehensive characteristic index of the working condition-time-space, represents the end time of the target time window, represents the start time of the target time window, represents the cumulative change amount of wind direction within the target time window, represents the average wind speed within the target time window, represents the average absolute yaw mismatch angle within the target time window, represents the average turbulence intensity within the target time window, , , , , all represent the space-time characteristic weight coefficients.

4. The method of wind power variable pitch and rotational speed cooperative control according to claim 3, characterized in that, The working condition power difference index is obtained by: According to the converter load rate and the variable pitch system working duty cycle, the current basic loss power is determined, and the current basic loss power is deducted from the measured electric power to obtain the net output power; The net output power is integrated in the target time window and divided by the window time length to obtain the unit working condition average power value; The power feature set is constructed according to the wind speed-wind direction two-dimensional binning, and the unit working condition average power values in the same bin are collected based on the density corrected reference power curve. The sample number of the unit working condition average power value is counted in each bin; If the sample number exceeds the preset threshold, the standard deviation of all unit working condition average power values in the bin is calculated, and the standard deviation is taken as the working condition power difference index of the current bin to represent the dispersion degree of the power output under the working condition. If the sample number is less than the preset threshold, the working condition power difference index is not calculated.

5. The method of wind power variable pitch and rotational speed cooperative control according to claim 1, characterized in that, The unit control constraint condition includes rotating speed upper and lower limit constraint, pitch angle and variable pitch rate upper limit constraint, generator torque / current limit constraint, nacelle / blade root / tower bottom load limit constraint and grid connection specification; the cooperative control instruction includes cooperative control priority table, pitch angle reference, rotating speed reference, generator torque reference, variable pitch rate threshold and control cut-in and cut-out timing; The fusion weight is used to update the priority or control gain of the variable pitch and rotating speed or torque channel in real time.

6. The method of wind power variable pitch and rotational speed cooperative control according to claim 1, wherein, The modification of the cooperative control instruction based on the grid side power constraint comprises: When there is a power grid power limiting instruction or energy storage peak shaving instruction, the channel weight after gating processing is used to re-distribute priorities, so that the weighted comprehensive value of the operating condition power difference index and the structural load index is reduced to the lowest while meeting the power limiting constraint; the structural load index includes at least one of the blade root bending moment, tower bottom bending moment and drive chain torque.

7. The method of wind power variable pitch and rotational speed cooperative control according to claim 1, wherein, Also includes: When the wind speed and direction sensor or wind measurement laser radar of the local unit is unavailable, the incoming flow data of the adjacent unit and the wind measurement tower within the communication range of the wind farm is obtained, and the wind speed, wind direction and turbulence intensity of the local unit are estimated by joint weighting according to the attenuation relationship with the distance of the local unit and the consistency of the relative wind direction, which are used as the replacement incoming flow data for calculating the operating condition space-time comprehensive feature index; When the sensor of the local unit is restored to be available, the deviation compensation amount is established according to the difference between the restored local incoming flow data and the replacement incoming flow data, and the wind speed, wind direction, unit operating condition average power value and operating condition power difference index are re-estimated according to the deviation compensation amount, so as to realize smooth switching and accuracy correction.

8. A system for wind power variable pitch and rotational speed cooperative control, applying the method for wind power variable pitch and rotational speed cooperative control according to any one of claims 1-7, characterized in that, Includes: a perception module, configured to obtain operating state data and incoming flow environment data of a wind turbine generator unit; an operating condition feature calculation module, configured to extract operating condition space-time features of the wind turbine generator unit in a target time window according to the operating state data and the incoming flow environment data, and obtain an operating condition space-time comprehensive feature index; a power feature analysis module, configured to calculate a unit operating condition average power value corresponding to the target time window based on the operating state data, the incoming flow environment data and a reference power curve, form an operating condition level power feature set, and obtain an operating condition power difference index according to the dispersion degree of the data in the set; a weight fusion module, configured to perform feature matching on the operating condition space-time comprehensive feature index and the operating condition power difference index, and calculate a cooperative control fusion weight based on a pre-set variable pitch channel basic weight and a rotational speed or torque channel basic weight; a control instruction generation and execution module, configured to generate a cooperative control instruction according to the cooperative control fusion weight, grid dispatching information and unit control constraint conditions, and the wind turbine generator unit executes the cooperative control instruction to complete the cooperative control of variable pitch and rotational speed. 9.An electronic device comprising a memory and a processor, the electronic device characterized by: The memory is used to store computer executable instructions, and the processor executes the computer executable instructions to realize the steps of the method of claim 1-7.

10. A computer-readable storage medium having computer-executable instructions stored thereon, characterized in that: The computer executable instructions are executed by the processor to realize the steps of the method of claim 1-7.

Images