CN-121976909-A - Wind power blade flexible variable pitch system based on self-adaptive fuzzy control

CN121976909ACN 121976909 ACN121976909 ACN 121976909ACN-121976909-A

Abstract

The invention relates to the technical field of new energy power generation, in particular to a wind power blade flexible variable pitch system based on self-adaptive fuzzy control, which comprises an acquisition module, a mirror image algorithm module and a convex hull algorithm module, wherein the acquisition module is used for acquiring real-time strain data of a blade waving direction and a shimmy direction through a fiber bragg grating sensor arranged at the root of a wind power blade, the mirror image algorithm module is used for applying mirror image algorithm processing to the real-time strain data to generate a symmetrical compensation data set for eliminating single-side deviation, and the convex hull algorithm module is used for extracting strain envelope characteristic points representing a load distribution mode through a convex hull algorithm based on the symmetrical compensation data set. According to the invention, through sensing-analysis-decision-execution-anti-interference full-link optimization, the response speed of the wind power blade pitch system is improved, and the blade load impact is effectively reduced.

Inventors

NING JINYE
QIN SHIGANG
LIAN HONGHAI
YU YI
FENG YANYI
CHEN CHAO

Assignees

湖南电气职业技术学院

Dates

Publication Date: 20260505
Application Date: 20251216

Claims (10)

1. Wind-powered electricity generation blade flexibility variable pitch system based on self-adaptation fuzzy control, characterized by comprising: The acquisition module is used for acquiring real-time strain data of the blade waving direction and the shimmy direction through a fiber bragg grating sensor arranged at the root of the wind power blade; the mirror image algorithm module is used for applying mirror image algorithm processing to the real-time strain data to generate a symmetrical compensation data set for eliminating single-side deviation; the convex hull algorithm module is used for extracting strain envelope feature points representing a load distribution mode through a convex hull algorithm based on the symmetrical compensation data set; The fuzzy control module is used for inputting the strain envelope characteristic points into the self-adaptive fuzzy controller, dynamically reconstructing membership characteristics and generating a pitch angle adjustment instruction, and simultaneously expanding a fuzzy rule base in real time according to a load distribution mode abnormal signal triggered when the pitch angle adjustment instruction is generated and combining a blade surface state monitoring result; The matching module is used for inputting the pitch angle adjusting instruction into a cooperative mechanism of the magnetorheological damper and the servo motor to obtain a buffer torque value matched with the load distribution mode; The temperature feedback module is used for starting phase change material heating and dynamically adjusting current parameters based on the buffer torque value and real-time temperature feedback of the magnetorheological damper so as to maintain torque output efficiency; The electromagnetic shielding module is used for deploying a multistage electromagnetic shielding layer to inhibit electromagnetic interference in a closed loop signal transmission path formed by strain data acquisition, mirror image algorithm processing, convex hull feature extraction, fuzzy control decision and rule base expansion, buffering torque value and temperature feedback adjustment.
2. The adaptive fuzzy control-based wind power blade flexible pitch system of claim 1, wherein the real-time strain data of the blade flapping direction and the edgewise direction is collected by a fiber bragg grating sensor installed at the root of the wind power blade, comprising: activating a fiber bragg grating sensor array according to a preset spatial distribution matrix, synchronously collecting original light intensity attenuation values, and calculating initial strain components of each sensor node in the waving direction and the shimmy direction; Performing time domain alignment calculation on the initial strain component, compensating signal transmission delays of different sensor nodes through a sliding time window, and generating a time-synchronous strain data sequence; performing amplitude correction calculation on the time-synchronous strain data sequence based on the calibration curve, and eliminating nonlinear errors caused by ambient temperature drift by adopting a cubic spline interpolation method to obtain preprocessed strain data; and carrying out load effectiveness verification calculation on the preprocessed strain data, triggering a sensor self-checking protocol and replacing the sensor self-checking protocol with historical mean value data when the strain ratio of the waving direction to the shimmy direction exceeds a preset safety threshold value, and finally generating real-time strain data.
3. The adaptive fuzzy control-based wind power blade flexible pitch system of claim 2, wherein applying a mirror image algorithm process to the real-time strain data generates a symmetric compensation dataset that eliminates single-sided offset, comprising: Based on real-time strain data, carrying out sliding time window interception according to the rotation phase angle of the blade, and calculating strain data slices of the swing direction and the shimmy direction in the same period; performing central line fitting calculation on the strain data slice, and fitting a neutral layer strain distribution curve of the blade by adopting a least square method to generate a reference symmetry axis; performing mirror symmetry compensation calculation based on the reference symmetry axis, performing equidistant mapping on strain values of the windward side and the leeward side of the blade relative to the reference axis, solving a compensation quantity difference value, and superposing the compensation quantity difference value to original data to obtain compensated strain data; And performing dynamic weight fusion calculation on the compensated strain data, and distributing weight coefficients according to the section positions of the blades to generate a symmetrical compensation data set for eliminating single-side deviation.
4. A wind power blade flexible pitch system based on adaptive fuzzy control of claim 3, wherein extracting strain envelope feature points characterizing a load distribution pattern by a convex hull algorithm based on the symmetric compensation dataset comprises: Performing strain gradient preprocessing calculation on the symmetrical compensation data set, dividing the data sections according to the position of the blade, and calculating the strain dispersion and mean ratio of each section as gradient sensitivity coefficients; Carrying out dynamic convex hull construction calculation based on the gradient sensitivity coefficient, screening a section with the sensitivity coefficient exceeding a preset threshold value as a key region, and connecting strain extreme points in the region to form an initial convex hull; Based on the initial convex hull, redundant vertexes are removed through a geometric curvature analysis algorithm, and inflection points with large curvature change are reserved as candidate feature points; And inputting the candidate feature points into load mode matching calculation, comparing the envelope templates of the history working condition feature library, and screening feature points with matching degree reaching a preset standard as strain envelope feature points.
5. The adaptive fuzzy control-based wind power blade flexible pitch system of claim 4, wherein the strain envelope feature points are input into an adaptive fuzzy controller to dynamically reconstruct membership features and generate pitch angle adjustment instructions, and wherein the method comprises the steps of: Based on the strain envelope feature points, acquiring geometric figure key size parameters formed by the feature points in a space parameterization measurement mode, and generating feature vectors representing a load distribution mode; When the degree of the feature vector deviating from the reference template exceeds a preset threshold, dynamically adjusting the central position parameter and the distribution width parameter of the fuzzy set according to the deviation degree to obtain a reconstructed membership feature; inputting the membership characteristics into fuzzy reasoning calculation, activating a fuzzy rule base to generate a pitch angle adjustment instruction, and synchronously generating confidence coefficient parameters for representing the reliability of a control decision; triggering a load distribution mode abnormal signal when the confidence coefficient parameter is lower than a preset credible threshold value, and calculating a parameter representing the icing severity by combining icing coverage data monitored by the surface state of the blade; And executing fuzzy rule expansion calculation based on the parameter representing the icing severity, adding a variable pitch angle adjustment amplitude enhancement rule matched with the icing severity, and updating a real-time rule base.
6. The adaptive fuzzy control-based wind power blade flexible pitch system of claim 5, wherein inputting the pitch angle adjustment command into a synergy mechanism of a magnetorheological damper and a servo motor to obtain a buffered torque value matched with a load distribution pattern comprises: Carrying out dynamic instruction analysis and calculation on the variable pitch angle adjustment instruction, and decomposing the dynamic instruction into a variable pitch angle increment value and a variable pitch angle change rate instruction; dynamically adjusting a damping force threshold value through a load distribution pattern matching degree index based on the variable pitch angle increment value, and generating a target output damping force of the magnetorheological damper; based on the variable pitch angle change rate instruction, eliminating a motion hysteresis error of a pitch mechanism through a proportional-integral algorithm, and generating a torque compensation value of a servo motor; based on the target output damping force and the torque compensation value, adopting a weighted moving average algorithm to fuse the target output damping force and the torque compensation value, and generating an initial buffer torque value of the cooperative mechanism; And executing load matching degree verification calculation on the initial buffer torque value, and correcting the torque value according to the fluctuation amplitude proportion when the actual measurement torque fluctuation rate exceeds a preset tolerance range to obtain a buffer torque value matched with a load distribution mode.
7. The adaptive fuzzy control based wind power blade flexible pitch system of claim 6, wherein starting phase change material heating and dynamically adjusting current parameters to maintain torque output efficiency based on the buffered torque values and real-time temperature feedback of the magnetorheological damper comprises: calculating a theoretical optimal efficiency value under the current working condition through a torque-rotating speed characteristic curve pre-stored by a magneto-rheological damper based on the buffer torque value; based on the theoretical optimal efficiency value and the actual measurement efficiency value monitored by the magnetorheological damper in real time, triggering a phase change material heating instruction when the absolute value of the efficiency deviation exceeds a preset threshold value and the real-time temperature is lower than the critical activation temperature of the phase change material; Real-time temperature feedback is carried out on the magnetorheological damper, a temperature-current compensation mapping table is established, and current reference parameters for maintaining target torque output are generated; Dynamically distributing the weight proportion of the heating power of the phase change material and the current compensation intensity based on the heating instruction and the current reference parameter to obtain a current parameter adjustment instruction; and monitoring the torque output efficiency after the current parameter adjustment instruction is executed, and reversely correcting the current parameter according to the efficiency deviation gradient value when the efficiency fluctuation rate exceeds the allowable range, so as to maintain the torque output efficiency in a preset working interval.
8. The adaptive fuzzy control based wind power blade flexible pitch system of claim 7, wherein deploying the multi-stage electromagnetic shielding layer to suppress electromagnetic interference in a closed loop signal transmission path formed by strain data acquisition, mirror image algorithm processing, convex hull feature extraction, fuzzy control decision and rule base expansion, buffering torque values and temperature feedback adjustment comprises: performing electromagnetic interference spectrum analysis on the closed-loop signal transmission path, detecting characteristic interference frequency data of the strain data acquisition section and the temperature feedback adjustment section, and generating an interference spectrum characteristic data set containing frequency values and amplitude values; distributing shielding material types and layer thickness parameters for interference sources in different frequency sections based on the interference frequency spectrum characteristic data set to obtain shielding parameters; determining the deployment position coordinates of the multi-stage shielding layer through the space topological structure data of the signal transmission path based on the shielding parameters; based on the deployment position coordinates, verifying shielding effectiveness through electromagnetic field simulation and generating a signal-to-noise ratio improvement standard instruction; And dynamically adjusting the grounding impedance parameter of the electromagnetic shielding layer according to the signal-to-noise ratio improving standard instruction so as to maintain the integrity of all-link signal transmission.
9. A control method of a wind power blade flexible pitch system based on adaptive fuzzy control, wherein the method is applied to the system as claimed in any one of claims 1 to 8, and comprises the following steps: collecting real-time strain data of a blade waving direction and a shimmy direction through a fiber bragg grating sensor arranged at the root of a wind power blade; mirror image algorithm processing is applied to the real-time strain data, and a symmetrical compensation data set for eliminating single-side deviation is generated; extracting strain envelope characteristic points representing a load distribution mode through a convex hull algorithm based on the symmetrical compensation data set; Inputting the strain envelope characteristic points into a self-adaptive fuzzy controller, dynamically reconstructing membership characteristics and generating a pitch angle adjustment instruction, and simultaneously expanding a fuzzy rule base in real time according to a load distribution mode abnormal signal triggered when the pitch angle adjustment instruction is generated and a blade surface state monitoring result; Inputting the variable pitch angle adjustment instruction into a cooperative mechanism of the magnetorheological damper and the servo motor to obtain a buffer torque value matched with a load distribution mode; Starting phase change material heating and dynamically adjusting current parameters based on the buffer torque value and real-time temperature feedback of the magnetorheological damper so as to maintain torque output efficiency; In a closed loop signal transmission path formed by strain data acquisition, mirror image algorithm processing, convex hull feature extraction, fuzzy control decision and rule base expansion, buffer torque value and temperature feedback adjustment, a multistage electromagnetic shielding layer is deployed to inhibit electromagnetic interference.
10. A computing device, comprising: One or more processors; Storage means for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to implement the method of any of claims 1-8.

Description

Wind power blade flexible variable pitch system based on self-adaptive fuzzy control Technical Field The invention relates to the technical field of new energy power generation, in particular to a wind power blade flexible variable pitch system based on self-adaptive fuzzy control. Background Wind power generation is crucial in energy transformation, and the variable pitch control performance of wind power blades directly influences the stability, efficiency and service life of the unit. However, the current main rheological propeller system adopts a rigid mechanism and combines PID or simple fuzzy control, so that the requirement can be met in a land wind power plant with stable wind speed, but as wind power is developed to a large capacity (more than 6 MW) and deep sea and open sea, the limitation is prominent, and the nonlinear load under extreme working conditions such as offshore typhoons, strong gusts, low-temperature icing and the like can be difficult to cope, so that the running risk is increased and the efficiency is reduced. A case of a 7MW offshore wind power cluster shows that the traditional system has the remarkable problems in typhoon strong wind gust (the wind speed is 15m/s to 28m/s within 10 minutes), namely resistance strain gauge response lag (20 ms) can not be captured sometimes, PID controller parameters are fixed, pitch adjustment lag is achieved, the blade is frozen, the adjustment error can reach +/-3.5 degrees due to no adaptation rule, the signal distortion is caused by strong electromagnetic interference, the final blade waving amplitude can exceed standard (+ -2.8 meters), shutdown is caused for 8 hours, and microcracks can occur. This reflects the limitations that the traditional system may have insufficient dynamic response (delay 15-20 ms), poor control rule generalization (error exceeding + -2.5 DEG during icing), efficiency attenuation of the actuator (30% low temperature response, 40% -60% high load impact) and weak electromagnetic interference resistance (signal to noise ratio less than or equal to 20 dB). Disclosure of Invention The invention aims to overcome the defects of the prior art and provide a wind power blade flexible variable pitch system based on self-adaptive fuzzy control, which improves the response speed of the wind power blade variable pitch system and effectively reduces the blade load impact through sensing-analysis-decision-execution-anti-interference full-link optimization. In order to solve the technical problems, the invention adopts the basic conception of the technical scheme that: A wind power blade flexible pitch system based on adaptive fuzzy control, comprising: The acquisition module is used for acquiring real-time strain data of the blade waving direction and the shimmy direction through a fiber bragg grating sensor arranged at the root of the wind power blade; the mirror image algorithm module is used for applying mirror image algorithm processing to the real-time strain data to generate a symmetrical compensation data set for eliminating single-side deviation; the convex hull algorithm module is used for extracting strain envelope feature points representing a load distribution mode through a convex hull algorithm based on the symmetrical compensation data set; The fuzzy control module is used for inputting the strain envelope characteristic points into the self-adaptive fuzzy controller, dynamically reconstructing membership characteristics and generating a pitch angle adjustment instruction, and simultaneously expanding a fuzzy rule base in real time according to a load distribution mode abnormal signal triggered when the pitch angle adjustment instruction is generated and combining a blade surface state monitoring result; The matching module is used for inputting the pitch angle adjusting instruction into a cooperative mechanism of the magnetorheological damper and the servo motor to obtain a buffer torque value matched with the load distribution mode; The temperature feedback module is used for starting phase change material heating and dynamically adjusting current parameters based on the buffer torque value and real-time temperature feedback of the magnetorheological damper so as to maintain torque output efficiency; The electromagnetic shielding module is used for deploying a multistage electromagnetic shielding layer to inhibit electromagnetic interference in a closed loop signal transmission path formed by strain data acquisition, mirror image algorithm processing, convex hull feature extraction, fuzzy control decision and rule base expansion, buffering torque value and temperature feedback adjustment. In a second aspect, a control method of a wind power blade flexible pitch system based on adaptive fuzzy control includes the following steps: collecting real-time strain data of a blade waving direction and a shimmy direction through a fiber bragg grating sensor arranged at the root of a wind power blade; mirror image algorithm pr