320 results about "Wind power system" patented technology

The present disclosure provides a fault measurement impedance calculation method and device for a hybrid grid-following / grid-forming wind power system. The method comprises: acquiring characteristics of a grid-following converter and a grid-forming converter, and corresponding low-voltage ride-through control strategies; establishing an equivalent circuit corresponding to a fault state; performing simplified analysis on a hybrid wind power system to obtain an equivalent network diagram; obtaining a branch circuit diagram under individual action of each power excitation; obtaining short-circuit currents and grid-connected point voltages on two sides of the system corresponding to the individual action of each power excitation; performing superimposition to obtain a total short-circuit current and a total grid-connected point voltage at the two sides of the hybrid wind power system; and obtaining a measurement impedance at a protection installation point on a new energy side. In the method, a measurement impedance value at a protection installation point of a hybrid wind power system after a fault occurs can be accurately calculated, so that the setting calculation of distance protection is ensured, so as to accurately reflect fault characteristic information of a hybrid AC system, thereby providing a basis for the distance protection applicability research of the hybrid wind power system, and thus ensuring the safe and stable operation of new energy systems.

The invention discloses a wind power generation system. The system comprises a ground device; the floating device comprises an adjusting air floating piece and a first annular air floating piece, the adjusting air floating piece is movably connected with the ground device, the first annular air floating piece is connected with the adjusting air floating piece, and a through duct is defined by the inner wall of the first annular air floating piece; the wind power generation device is arranged in the duct; and the position of the gravity center of the adjusting air floating piece in the extending direction of the duct is adjustable. According to the wind power generation system, the influence of airflow disturbance, temperature change and buoyancy lift gas leakage on the floating device can be reduced, the phenomenon that the pitching posture change amplitude is large is reduced, particularly, the included angle between the wind receiving face of the blade of the wind power generation device and the airflow direction is closer to the optimal value, the effective wind energy area flowing through the blade is increased, and the wind power generation efficiency is improved. And the fluctuation of the wind energy yield along with the posture is reduced, so that the wind energy utilization efficiency and the power generation output power are improved.

The invention discloses a wind power plant inertia damping adaptive regulation and control method and system fused with a deep Q network, and belongs to the technical field of power systems. The method comprises the following steps: establishing a doubly-fed wind turbine generator, a converter mathematical model and an interaction model of a wind power system connected to a power grid, and analyzing the grid-connected stability of the wind power system; the dynamic response characteristic of providing inertia support by the VSG system under different conditions is researched, and the primary frequency modulation capability is improved; a depth Q network is adopted to select rotational inertia and a damping coefficient, a damping inertia adaptive control strategy is improved, cooperation of inertia support and frequency response capability improvement of a wind turbine generator and continuous and smooth adjustment of active power is realized, the stability of a power grid is improved, and the operation performance of a wind power plant is optimized. According to the method, dynamic optimal matching of inertia response, primary frequency modulation and the running state of a unit is achieved, auxiliary services are provided, meanwhile, the running safety and service life of a draught fan are guaranteed, and smooth and impact-free adjustment of active power is achieved.

The invention discloses an operation control method for a wind power generation system, and relates to the technical field of operation control, and the method comprises the steps: obtaining the historical operation data of a wind power generation system in a target sea area, taking an offshore environment factor as an interference factor, and coupling the time-space parameters of ocean turbulence intensity, wave load and salt spray corrosion rate; establishing a fan-marine environment digital twinborn body; operation data is acquired in real time, synchronous mapping and dynamic updating of the digital twin are realized, and a state prediction model is established in combination with historical operation characteristics; taking the maximum power generation efficiency and the minimum mechanical load as a multi-objective optimization function, and introducing a model prediction controller to obtain an optimal control sequence of the wind power generation system in a future time domain of each control period; and selecting a first control instruction in the optimal control sequence, issuing the first control instruction to a physical fan torque controller and a variable pitch system in real time, realizing rolling optimization of the wind power generation system, and obtaining a self-adaptive operation control scheme of the wind power generation system. The power generation benefit of the whole life cycle is improved.

The invention relates to an alternating-current trunk line or an alternating-current power distribution network, in particular to a method for improving the stability of a wind power system through combined control of network construction type energy storage and a nine-switch UPQC. The method comprises the following steps: firstly, proposing an active regulation and inertial support control method based on a virtual synchronous machine mechanism for network construction type energy storage; and secondly, by constructing a coordination control framework, dynamic response complementation of the energy storage system and the UPQC under disturbance is realized, so that the overall frequency stability and voltage supporting capability of the system are improved. And finally, building a system model in Matlab / Simulink, setting three typical working conditions of wind power fluctuation, frequency disturbance and serious voltage drop, and carrying out scheme validity verification. Simulation results show that the method can effectively stabilize the wind power output fluctuation, enhance the frequency and voltage support capability, and significantly improve the stability of a wind power system.

The method aims at solving the problems that in a wind power generation system, due to modeling errors of a prediction model in model prediction independent variable pitch control, the load of a blade root of a fan is too large, and output power is unstable. On the basis of model predictive control (MPC) independent variable pitch control, a model predictive independent variable pitch control method integrating deep deterministic policy gradient algorithm (DDPG) reinforcement learning compensation is provided, so that the modeling error of an MPC predictive model is reduced, the load reduction effect is improved, and the stability of output power is enhanced. And a DDPG compensator is designed, so that an intelligent agent continuously learns through a trial-and-error and feedback mechanism, thereby dynamically compensating a modeling error and improving the load reduction performance of MPC independent variable pitch control. According to the invention, the output power of the fan can be more stable, and the fluctuation of blade root load can be effectively reduced, so that the service life of the fan is prolonged, and the operation reliability of the system is improved.

The invention relates to the technical field of offshore wind turbine generators, in particular to a method and system for providing emergency power supply for a wind power generation system through an ocean energy power generation system, electronic equipment, a storage medium and a monitoring system. The invention discloses an emergency power supply method, a wind power generation system is provided with an energy storage backup power supply module and an electric energy access and switching control module, and communication connection is configured between an ocean energy power generation system and a main control system of the wind power generation system. When the high-voltage side of the wind power generation system is powered off or the power grid is interrupted, the main control system judges whether the energy storage backup power supply needs to supplement electric energy; if yes, the ocean energy power generation system is started to charge the system; if not, the energy storage module supplies power to the control system; when the energy storage module fails, the ocean energy system is controlled to directly supply power to the control system; and energy scheduling, state monitoring and remote control are realized through communication connection, so that the power supply reliability and the operation safety of the system under extreme working conditions are improved.

The invention belongs to the technical field of wind power prediction, and provides a double-layer cascade wind power prediction method and system based on TransformerEncoder, and the method comprises the steps: a fusion variable selection module comprises a Pearson correlation coefficient and an XGBoost regression model; the data processing module preprocesses the input original data to obtain normalized data; a fusion variable selection module screens normalized data, a Pearson correlation coefficient quantifies a linear relation of the normalized data, an XGBoost regression model captures a nonlinear relation, and a correlation feature sequence is obtained through fusion; and the model construction and prediction module processes the related feature sequence, predicts and optimizes a power value, and outputs an optimized power prediction value. According to the method, efficient screening of key variables is realized, change rules of meteorological data, fan speed data and power data are effectively identified, redundant variables are effectively reduced, the complexity of the model is reduced, dynamic characteristics of a wind power system can be better understood and learned, and higher precision and stability are shown in an actual prediction task.

The invention discloses a wind power generation system model prediction control method and device based on event triggering. The method comprises the following steps: establishing a wind power generation system model; based on the wind power generation system model, whether an event triggering mechanism is activated or not is judged according to the deviation between the current state and the target state of the system and the maximum sampling interval time; designing an LMPC algorithm based on event triggering: if an event triggering mechanism is activated, solving an optimization problem in a finite time domain to obtain an optimal control sequence of the system, and fusing Lyapunov function constraint to ensure the closed-loop stability of the system; wherein the optimization problem takes a minimum weighted sum of a system output tracking error and a control input variable quantity as a target; and deploying the LMPC algorithm based on event triggering into a control device of the wind power generation system so as to realize optimal control of the wind power generation system. The stability and robustness of the wind power generation control system can be effectively improved.

The invention discloses a high-altitude wind power generation system which comprises a main air bag extending in the front-back direction, and the peripheral face of the main air bag is a rotary face; the ring wing sleeves the radial outer side of the main air bag and is spaced from the main air bag, and a duct space is formed between the inner wall of the ring wing and the outer wall of the main air bag; the first supporting frame and the second supporting frame are sequentially arranged on the radial outer side of the main air bag in a sleeving mode in the axial direction of the main air bag; the wind power assembly is mounted on the first supporting frame; the first supporting frame comprises a plurality of supporting units, an annular supporting frame with an inner ring and an outer ring is defined by the multiple supporting units, the annular supporting frame comprises ducts formed between the adjacent supporting units, and the wind power assembly is installed in the ducts; the second supporting frame is of an annular grid truss structure and comprises a main body frame and truss rod pieces assembled in the main body frame through truss nodes, and the truss rod pieces and the truss nodes are modularly expanded to form the grid truss structure.

The invention provides a subsynchronous oscillation monitoring system and method for a wind power generation system, and the system comprises a signal collection module which is used for obtaining an output current parameter and a power grid interface voltage parameter in a target wind power plant region, and generating a current and voltage monitoring value; the feature extraction module is used for extracting oscillation frequency parameters and oscillation feature parameter values based on the current and voltage monitoring values; the dynamic threshold module is used for acquiring a power grid load parameter and a wind speed parameter and generating a dynamic threshold parameter value through weighted calculation; the state judgment module is used for performing state logic judgment based on the oscillation frequency parameter and the dynamic threshold value to obtain an oscillation state judgment value; and the result output module is used for generating a monitoring alarm signal value based on the oscillation state judgment value. According to the method, dynamic environment response and accurate feature extraction can be combined, the monitoring sensitivity and reliability are enhanced, the misjudgment probability caused by external interference is reduced, the protection action accuracy is optimized, and stable operation of a power grid is guaranteed.

A diversely useful wind power generation system for use with an existing structure such as a building. The system has one or more wind capture funnels located at a first location of the existing structure such as at or adjacent its roof. An air pressure powered rotor mechanically coupled to a generator at a second location of the existing structure, such as inside or at ground level. A conduit fluidly connects the one or more wind capture funnels at the first location to the air pressure powered rotor at the second location of the existing structure.

The invention discloses a multi-frequency subsynchronous oscillation self-adaptive suppression method for a doubly-fed wind power generation system, and belongs to the technical field of power system stability control. The invention aims to solve the problem that an existing method only suppresses single oscillation frequency and cannot guarantee stable operation of a wind turbine generator and a power grid. Comprising the steps that discrete current signals of the double-fed wind power generation system are collected, a sparse Fourier observer is used for sequentially conducting frequency spectrum rearrangement, window function filtering, frequency domain down-sampling and fast Fourier transformation, positioning circulation and valuation circulation on the discrete current signals, and the frequency and amplitude of subsynchronous oscillation components of the double-fed wind power generation system are obtained; a parallel multi-frequency self-adaptive wave trap is connected into a rotor side converter control loop of the doubly-fed wind power generation system, parameters of the wave trap are dynamically adjusted, and a suppression signal opposite to a subsynchronous oscillation component is output to filter out the subsynchronous oscillation component. According to the invention, the subsynchronous oscillation of the power system can be effectively suppressed under the condition of high-proportion new energy access.

The invention discloses a wind power system cooperative power smoothing method based on rotor kinetic energy storage and variable pitch, belongs to the technical field of wind power, and solves the technical problem that in a full-wind-speed operation range, a traditional variable coefficient control method based on the rotating speed is difficult to accurately respond to wind speed changes after variable pitch control is introduced. According to the technical scheme, the method comprises the following steps that S1, according to the rotor kinetic energy principle, an active reference value of a given fan power controller is determined so as to smooth wind power fluctuation, that is, a filter GLF is cascaded after traditional maximum power tracking control reference power; s2, on the basis of power smoothing under the full wind speed, model-free self-adaptive variable pitch control is introduced, and control over the output power and the rotating speed of the draught fan in the full wind speed interval is achieved; and S3, considering the cooperative control of the kinetic energy and the variable pitch of the rotor under the full wind speed, adopting a fuzzy variable filter coefficient strategy based on wind speed estimation, and remarkably improving the power smoothing effect under the full wind speed through real-time control of the filter coefficient.

The invention discloses a cascade water-wind-light multi-power system modeling method based on time-space correlation, and the method comprises the steps: building an autoregression integral moving average-generalized autoregression condition heterovariance model of wind power photovoltaic power and cascade hydropower station runoff, building an R-vine, C-vine and D-vine Copula function spatial correlation model through employing a generalized autoregression condition heterovariance value, and carrying out the modeling of a cascade water-wind-light multi-power system. And selecting an optimal spatial correlation model according to a Bayesian information criterion, an akaike information criterion and a logarithm likelihood value goodness of fit index. Based on the optimal spatial correlation model, constructing a scene generation method of Latin hypercube-Copula function sampling, performing scene generation on the wind power photovoltaic power and the runoff volume of the cascade hydropower station, and constructing a scene reduction method of contour coefficient optimization Kmeans clustering to reduce the generated scene. The invention provides a time-space correlation cascade water-wind-light multi-power system modeling method, and aims to analyze water-wind-light multi-energy complementary operation characteristics and provide reference for a scheduling mode among water-wind-light multi-energy.

A wind power generation system preset time maximum power point tracking control method comprises the following steps: firstly, establishing a wind power generation system dynamic model containing parameter uncertainty and external disturbance, and meanwhile, constructing a preset time convergence integral sliding mode surface; the method has the core advantages that the convergence time can be directly set by controller parameters and is irrelevant to the initial state of the system; secondly, designing a preset time self-adaptive controller based on the rotating speed tracking error and the sliding mode surface, and enabling the rotating speed tracking error to be quickly converged in preset time; the upper bound of lumped uncertainty of the system is estimated online through a self-adaptive mechanism, unknown dynamic and external disturbance are compensated in a unified mode, and dependence on an accurate model and disturbance prior knowledge is not needed; and finally, strictly proving the preset time stability of the closed-loop system through a Lyapunov stability theory. The method has good dynamic response performance and predictable convergence behaviors, and the robustness and the power generation efficiency of the system are improved.

The invention provides a wind power integration system small disturbance modeling and stability analysis method considering control delay, and the method comprises the steps: introducing a sampling delay link, a zero-order holding link and a switch delay link in a small disturbance linearization modeling process, carrying out the linearization processing through employing a first-order inertia link, and building a unified state space model; respectively constructing control delay mathematical models of the direct-driven fan and the double-fed fan, and analyzing and identifying the influence of the control delay on the oscillation mode and stability of the system through characteristic values and impedance; and finally, performing time domain simulation in the simulation platform, and comparing a calculation result with a simulation result to verify the accuracy of the model. The method can accurately reflect the small disturbance characteristics of the wind power grid-connected system in the sub-synchronous frequency band and the super-synchronous frequency band, provides a theoretical basis for optimization of control parameters of a wind turbine generator and evaluation of grid-connected stability, and solves the technical problem that the influence of control delay is generally ignored in modeling of an existing wind power grid-connected system.

The invention discloses an SMES-MMC cooperative frequency supporting method for a new energy sending-out system, discloses a system and a medium with the SMES-MMC cooperative frequency supporting method for the new energy sending-out system, and provides a method for improving the transient stability of a wind power-containing multi-machine system by combining superconducting energy storage. A dynamic power compensation control strategy based on sliding mode control is designed by constructing a mathematical model of a superconducting energy storage and direct-driven wind power generation system, and optimal control of system frequency recovery and voltage stability is realized by combining slope power recovery characteristics of a fan.

The application discloses a capacity planning method and device of a wind-solar-hydrogen storage micro-grid system, and relates to the technical field of renewable energy micro-grid planning. The method comprises the following steps: obtaining a target function and parameter constraint conditions of the wind-solar-hydrogen storage micro-grid system; the target function is determined according to total fixed costs and total operating costs of the wind-solar-hydrogen storage micro-grid system; the parameter constraint conditions comprise photovoltaic and wind power installed capacity output constraints, energy storage boundary and energy change rate constraints, maximum hydrogen consumption rate constraints, system feasibility constraints, continuous operation constraints and timing consistency constraints, and robustness constraints; the target function and the parameter constraint conditions are solved to obtain the installed capacity of a photovoltaic power generation system and a wind power generation system, and the storage capacity of an electrochemical energy storage system and the rated power capacity of a hydrogen fuel cell system. The method improves the accuracy of micro-grid system capacity planning and realizes the balance between economy and reliability.

The application considers the offshore wind power multi-unit space-time characteristic ultra-short-term power prediction model establishment method belongs to the technical field of wind power systems; in order to solve the problems of too long prediction time caused by predicting offshore wind power single unit, poor quality of overall predicted power curve, and facilitate the efficient dispatching of offshore wind power units by the power grid company, a kind of offshore wind power multi-unit space-time characteristic ultra-short-term power prediction model establishment method is provided; the technical scheme adopted includes the following steps: S1) analyzing the mechanism of the Transformer model, S2) establishing an offshore wind power multi-unit ultra-short-term power prediction model based on improved Transformer, S3) example analysis and verification; the method proposed in the application can effectively measure the space-time characteristics between units, and the prediction model has higher prediction accuracy and speed compared with the traditional prediction model.

The invention relates to the field of electric power, in particular to a wind power generation system. Comprising a rotating base and a wind power driving component installed on the rotating base, a middle base is connected to the rotating base in a matched mode, two fixing pieces are symmetrically and rotationally connected to the middle base, motors I are fixedly connected to the two ends of the middle base, rotating shafts are connected to output shafts of the two motors I through couplings, and the two rotating shafts are fixedly connected with the two fixing pieces respectively. The rotating seat is rotationally connected to the middle seat, a gear ring is fixedly connected to the rotating seat, a gear is fixedly connected to the middle seat, a motor III is fixedly connected to an output shaft of the gear, and the motor III is in meshing transmission connection with the gear ring. The wind power generation device has the beneficial effects that windward stress can be carried out at different height positions to realize conversion and utilization of wind energy.

The invention discloses a power prediction method for a wind power generation system based on a stacked sparse auto-encoder network Hammerstein model, and aims to solve the problems that only nonlinear mapping is modeled and dynamic characteristics of the system are neglected and parameter coupling of the Hammerstein model leads to complex identification in an existing method, the Hammerstein model is constructed, an ARMAX model is utilized to describe a dynamic linear module, and the dynamic linear module is used to predict the power of the wind power generation system based on the stacked sparse auto-encoder network Hammerstein model. A static nonlinear module is described by stacking the sparse auto-encoder network; designing a zero-mean Gaussian signal input proxy model, realizing series module decoupling based on covariance function characteristics, and eliminating parameter coupling; a self-adaptive multi-strategy grey wolf optimization algorithm is adopted to determine the number of neurons in a network hidden layer, training is performed in combination with a sparse criterion function, and the feature extraction capability is improved. According to the method, synchronous capture of static nonlinear and dynamic linear characteristics is realized, the calculation complexity is reduced, the model identification precision, prediction precision and robustness are improved, and the method is suitable for accurate prediction of the power of a wind power system.

The application discloses a kind of applied to water platform type data center, including from top to bottom two-layer platform, main platform, water cabin, the water cabin is double-layer board structure, its inside is equipped with data center air conditioning system, the air supply opening of this data center air conditioning system is connected to server cabinet place by data center cold channel, and the server cabinet is also arranged in water cabin;Sea water natural heat exchange system is equipped on the main platform, and the system utilizes sea water to take away the heat generated by data center air conditioning system and transfer to the ocean;The two-layer platform is equipped with wind power generation system around it.This application can realize modular assembly, according to demand, quickly arranged in required area, construction, transportation, installation is convenient, without using large water chiller, cooling tower and a large number of auxiliary pipeline, save early investment, greatly reduce energy consumption.

This invention proposes a method and system for electrothermal coordination overload control of grid-connected wind power systems. The method involves acquiring current measurements of the transmission components and wind farm of the grid-connected wind power system; predicting wind speed based on meteorological data; obtaining the temperature of the transmission components; and predicting the active power of the wind farm within a set time step of the current control cycle. Considering the predicted wind speed, transmission component temperature, and wind farm active power, an optimization problem is established based on the electrothermal coordination model of the grid-connected wind power system. Process-oriented electrothermal coordination control is then implemented to ensure that the temperature of the grid-connected line does not exceed limits during overload control. The optimization problem is solved under constraints to determine the optimal control sequence. The active power of the first wind farm group in the optimal control sequence is applied to the current wind farm's power generation control. This invention uses the maximum allowable temperature of the transmission components as a limit to dynamically coordinate and continuously optimize the wind farm output and the temperature of the external transmission components in the grid-connected system. Compared to traditional overload control methods, this method can further tap the overload potential of the external transmission components, which is beneficial for alleviating the contradiction of wind energy consumption.

The application discloses a kind of non-full-phase operation wind power system sequence network equivalence and voltage calculation method and device, the method includes: when the single-phase fault of wind power system occurs and wind power machine terminal voltage is lower than entering low-voltage ride-through threshold, the positive sequence current, negative sequence current and zero sequence current of wind turbine in fault steady-state stage are determined, to construct wind power side controlled current source model;Positive sequence network, negative sequence network and zero sequence network of wind power system in non-full-phase operation stage are constructed, and system side is equivalent to voltage source in each sequence network, to establish three sequence Thevenin equivalence model at fault break;Three sequence currents and three sequence voltages at fault break are determined based on wind power side controlled current source model and three sequence Thevenin equivalence model, and further determine three sequence voltages and three-phase voltages at wind turbine grid connection point.The application enables voltage analysis in non-full-phase operation stage to reflect wind power side controlled current source characteristics, to provide basis for new energy grid connection point voltage variation analysis.

A kind of permanent magnet direct drive type medium-high voltage high-power wind power converter and control method, belong to power electronics technical field.The wind power converter adopts H bridge midpoint clamping type five-level converter topology, wherein wind generator side is five-level midpoint clamping type H bridge converter, grid side is three three-phase three-level midpoint clamping type grid-connected converter, its DC side is connected to wind generator side converter, grid side is connected to 66kV or higher voltage grid through isolated four-winding power frequency step-up transformer.The topology structure can improve wind generator voltage to 8.5kV, and can be used in 20MW and above power level wind power system.Compared with traditional wind power converter, it has the advantages of high rated voltage, less power device, no need for device or converter parallel, large single machine capacity, simple cable twisting, small cable loss, good harmonic characteristic, high fault tolerance, simple structure, easy to control, etc., and has important application prospect in medium-high voltage high-power offshore system.

The invention belongs to the technical field of transient analysis of a new energy grid-connected system, and particularly relates to a transient overvoltage analysis method of a direct-driven wind power grid-connected system under an asymmetric fault, which comprises the following steps: acquiring three-phase asymmetric voltage and current, and constructing a positive and negative sequence dq control model of positive and negative sequence bisynchronization of a direct-driven wind power plant station; establishing a mapping relation with a symmetric component method, and determining a positive-sequence dynamic reactive current increment and a negative-sequence current suppression coefficient according to a converter control strategy; establishing sequence network boundary conditions under various asymmetric faults; enabling the direct-driven wind power plant to be equivalent to a frequency-related controlled sequence impedance source, and obtaining equivalent sequence impedance of the wind power plant; establishing a sequence network equation considering wind power dynamic support; calculating the current and sequence voltage of the fault point, and obtaining a three-phase voltage through symmetric component inverse transformation; and an overvoltage coefficient is calculated, and a quantitative relational expression between the overvoltage coefficient and the negative-sequence current suppression coefficient is established and applied. The method provides theoretical support for parameter setting and capacity planning of the wind power integration system.

The application discloses a kind of power generation systems based on friction nanogenerator, including photo-thermal power generation system, heat storage system and friction nanogenerator component.This system is a kind of comprehensive power generation system that TENG wind power generation system is combined with photo-thermal power generation system, the application will large-area TENG power generation system be arranged in solar photo-thermal power station reflector back with array distribution, saves the support part investment of TENG power generation system.Meanwhile, the electric energy of TENG power generation is directly converted into heat energy storage and is stored in the molten salt energy storage system matched with photo-thermal, realizes the energy storage function of wind power generation, and does not need to increase energy storage investment, saves the investment of downstream power transmission and transformation equipment, inverter and other equipment equipped with TENG power generation system, finally, due to the energy storage of TENG power generation system contribution, mirror field area of photo-thermal power generation system can be reduced, and the investment of photo-thermal power station itself will be reduced.

The invention discloses a wind power generation system fault diagnosis method and device based on multi-source data fusion and deep learning. The method comprises the following steps: collecting vibration, electrical, environment and operation state data of the wind generating set through a sensor array; performing preprocessing and depth feature extraction on the data, and fusing the data into a global feature vector; the global feature vector is input into a hybrid deep learning model for fault diagnosis, the model integrates CNN and LSTM, and a diagnosis threshold can be dynamically adjusted according to the wind speed; when a sensor fault is diagnosed, a fault reconstruction module based on a T-S fuzzy sliding mode observer is started, and fault information is accurately estimated; and feeding the reconstructed fault-free signal into a model prediction fault-tolerant controller to realize active fault-tolerant control of the system and maintain the stability of the output power. The problems that an existing fault diagnosis method is single in view angle, depends on an accurate model, and is disjointed in diagnosis and control are solved, and comprehensive, accurate and self-adaptive state monitoring and fault processing of the wind power generation system are achieved.

The invention relates to a self-adaptive fractional order sliding mode control method of a doubly-fed wind power system, solves the problem that chaotic oscillation of a doubly-fed induction generator cannot be effectively suppressed, and belongs to the technical field of wind power generation control. The method comprises the following steps: establishing a chaos sensitive parameter identification model of the doubly-fed induction generator, and estimating system state variables and harmonious scheduling in real time; calculating a chaos intensity index through a chaos phase trajectory prediction module based on a system state variable and harmonious scheduling k; the method comprises the following steps: establishing a fractional order adaptive adjustment mechanism, and dynamically adjusting the fractional order of a fractional order sliding mode surface; according to the method, a fractional order sliding mode surface with a dual-mode switching characteristic is designed; constructing a multi-time scale nonlinear disturbance observer to obtain a total disturbance estimated value; based on the sum fractional order sliding mode surface, designing a chaos feedforward compensator to obtain a feedforward compensation control signal; and performing fusion based on the fractional order sliding mode surface, the total disturbance estimation value and the feedforward compensation control signal to obtain a final control signal.