86 results about "Wind disturbance" patented technology

The invention relates to an unmanned aerial vehicle self-adaptive wind-resistant flight control method and system based on multi-mode environment perception. The method comprises the steps that a miniature wind speed and direction sensor array obtains real-time wind speed and wind direction information of the surrounding environment of an unmanned aerial vehicle; the inertial measurement unit obtains real-time attitude angle, angular velocity and acceleration information of the unmanned aerial vehicle; the visual flow sensor obtains real-time image data of the surrounding environment of the unmanned aerial vehicle; the data fusion and wind field estimation module receives multi-source data collected by the miniature wind speed and direction sensor array, the inertial measurement unit and the visual flow sensor, carries out fusion processing on the multi-source data based on an extended Kalman filtering algorithm, and predicts to obtain predicted wind field information in a future short time window; the flight control core module adopts an adaptive sliding mode control algorithm to calculate a compensation control quantity for counteracting wind disturbance, and performs real-time control on the unmanned aerial vehicle based on the compensation control quantity; and the wind resistance and the operation reliability of the unmanned aerial vehicle in a complex dynamic environment are improved.

The invention provides a four-rotor unmanned aerial vehicle anti-wind-disturbance robust flight control method and system, and belongs to the technical field of unmanned aerial vehicle control, and the method comprises the steps: collecting the real-time state data of an unmanned aerial vehicle, the real-time state information comprises the position, speed, height, three-axis attitude angle and three-axis angular speed; acquiring an expected inspection track instruction, generating an expected attitude angle instruction and a total lift instruction in combination with the real-time state data, performing wind disturbance estimation by adopting a neural network, and compensating the expected attitude angle instruction and the total lift instruction; calculating a control torque increment by adopting an increment backstepping method based on the expected attitude angle instruction and the real-time state data, and obtaining a control torque instruction by combining the control torque at the previous moment; and the control torque instruction and the total lift instruction are distributed to the rotating speeds of four motors of the four-rotor unmanned aerial vehicle, and the motors execute the rotating speed instructions to drive the unmanned aerial vehicle to complete a wind disturbance resisting flight task. The method can actively adapt to wind field changes, and it is guaranteed that the unmanned aerial vehicle can still fly accurately, stably and safely under disturbance.

The invention discloses a double-machine cooperative hoisting operation guiding system and method based on Beidou positioning, and the system comprises a coordinate data implantation unit which is used for pre-storing a standardized coordinate template with environment compensation parameters; the sensor network is used for acquiring crane position, load and environment data in real time; the crane positioning and guiding unit is used for generating a multi-dimensional environment correction factor, dynamically comparing coordinates, weighting and calculating deviation, and planning a synchronous walking path through a multi-objective optimization algorithm; and the hoisting control unit is used for constructing a synchronous control model containing moment balance and kinematics constraint and adjusting hoisting parameters by adopting a closed-loop algorithm. According to the method, millimeter-level positioning guiding and double-machine load self-adaptive balancing can be achieved, segment inclination and wind disturbance influences are effectively restrained, hoisting synchronization precision and operation safety are remarkably improved, high-steady-state anti-inclination control can be completed without newly adding hardware, and the method has high engineering practicability and popularization value.

The invention provides a non-linear flight control method and system for an anti-wind disturbance unmanned aerial vehicle. The method comprises the following steps: acquiring wind field disturbance characteristics in real time by using a preset meteorological radar; inputting the wind field disturbance characteristics into a preset aerodynamic disturbance prediction model to generate an aerodynamic torque fluctuation prediction value; preset dynamic filtering processing is applied to the amplitude characteristic of the aerodynamic torque fluctuation predicted value so as to generate a control instruction correction signal; and the control instruction correction signal is coupled with a preset nonlinear control law of an unmanned aerial vehicle flight control system, so that unmanned aerial vehicle attitude offset caused by wind disturbance is inhibited in real time, and unmanned aerial vehicle nonlinear flight control is carried out. According to the method, the composite defect of hysteresis and filtering mismatch of traditional linear control in a strong wind sudden change scene is overcome, stable attitude control of the unmanned aerial vehicle in low-altitude wind shear and gust sudden attack is realized, the anti-interference response speed of the unmanned aerial vehicle is remarkably improved, and the out-of-control risk of the unmanned aerial vehicle is greatly reduced.

The invention discloses an unmanned aerial vehicle anti-wind disturbance controller and a control method, and belongs to the technical field of unmanned aerial vehicle flight control. The method runs on an independent processing module which is connected in series between a main flight controller and an electronic speed regulator of the unmanned aerial vehicle, a dynamic reference is constructed by collecting motor current in real time, deviation is calculated, and wind disturbance equivalent disturbance torque is estimated in a prospective mode through a third-order linear extended state observer (LESO) with bandwidth parameterization design; in combination with a'user operation state + flight mode 'two-dimensional intelligent decision compensation strategy, a'look-ahead wind resistance + attitude backup' dual-redundancy channel is matched, so that the wind disturbance is compensated in advance, and the flight stability in a complex scene is ensured. A corresponding controller adopts a standardized independent hardware design, the adaptability is high, the integration cost is low, and the method can be widely applied to high-precision operation scenes of various multi-rotor unmanned aerial vehicles.

The invention relates to the technical field of artificial intelligence, and discloses an unmanned aerial vehicle flight control-oriented intelligent obstacle recognition method, which comprises the following steps of constructing an adaptive wind disturbance fuzzy kernel based on unmanned aerial vehicle attitude data, and synthesizing a degraded image for training; a specific obstacle recognition model integrating a frequency domain and space domain joint feature decomposition module, a turbulence invariant feature enhancement module guided by physical prior information and a double-branch anti-fuzzy feature extraction network is adopted, and a fuzzy robustness contrast loss function is combined to carry out progressive training so as to learn feature representation insensitive to fuzziness; after the trained model is deployed, the wind disturbance fuzzy intensity of a real-time input image is estimated on line, the internal workflow of the model is dynamically adjusted according to the wind disturbance fuzzy intensity, the attention weight is adaptively adjusted, and the output of a trunk or an anti-fuzzy branch is selected. According to the invention, through coupling of the physical model and deep learning, the recognition robustness, accuracy and stability of the model in a dynamic wind disturbance environment are improved.

The invention relates to an unmanned aerial vehicle attitude control method based on motor state disturbance compensation, belongs to the technical field of unmanned aerial vehicle control, and solves the problems of hysteresis and limited control effect of an existing unmanned aerial vehicle attitude control method. The position controller calculates to obtain expected tension, a roll angle and a pitch angle; the attitude feedback controller calculates a feedback torque according to the expected attitude, the actual Euler angle and the body angular velocity; the load identification module calculates an estimated disturbance torque based on the target rotating speed, the actual rotating speed and the current of each motor; the feedforward neural network module adopts a trained RBF neural network to calculate torque residual error estimation, and torque synthesis is carried out to obtain a torque feedforward compensation amount; adding the feedback torque and the feed-forward compensation amount to obtain a total control torque; and the mixing controller calculates the target rotating speed of each motor according to the expected tension and the total control torque, and finally the control distributor drives the motors to execute. The attitude stability and the control response speed of the unmanned aerial vehicle in the wind disturbance environment are remarkably improved.

The present application relates to the field of unmanned aerial vehicle flight control, more particularly, the present application relates to unmanned aerial vehicle flight control method and system based on unmanned aerial vehicle search and rescue platform, the method comprises: based on the preset time window calculates the current attitude stability and wind resistance consumption of unmanned aerial vehicle, and then the excess proportion is obtained and the comprehensive wind resistance index is calculated, according to which the weak machine is judged; Then calculate the next moment of weak machine traction (current traction minus release amount) and strong machine next moment of traction (original traction plus weak machine release amount total sum of increments), complete the reassignment of unmanned aerial vehicle cluster traction. The present application can intelligently evaluate the wind resistance of unmanned aerial vehicle and dynamically adjust the traction distribution, combined with accurate prediction and environmental adaptation, significantly improve the task execution stability and reliability of unmanned aerial vehicle cluster in wind disturbance environment, ensure that the task allocation is more scientific and reasonable.

The invention relates to the technical field of unmanned aerial vehicle control, and discloses an unmanned aerial vehicle multi-load synchronous control system, and the system comprises a linkage control unit which is used for detecting an image shot by an unmanned aerial vehicle, obtaining a camera imaging plane deviation according to a detection result, and combining with a kinematic model to solve an expected instruction of the unmanned aerial vehicle and a holder; the multi-load configuration unit is used for determining control logic according to the load type and the expected instruction and issuing an operation instruction to the load according to the control logic so as to realize linkage control of the load and the unmanned aerial vehicle controller; the control instruction adjusting unit is used for acquiring the flight state of the unmanned aerial vehicle when the expected instruction is executed, and calculating a disturbance value of the unmanned aerial vehicle to determine a final control instruction of the unmanned aerial vehicle by taking the flight state as input; the equipment is an airborne computing power unit. The active-disturbance-rejection pose correction technology is introduced, real-time compensation of disturbance such as wind disturbance, load sudden change and hanging point deviation is achieved, and the working efficiency and the complex scene adaptability are improved.

The application discloses a quad-rotor unmanned aerial vehicle attitude fault-tolerant control method considering unknown wind disturbance, and relates to the field of unmanned aerial vehicle attitude control design; the method can effectively cope with unknown wind disturbance, actuator partial failure and deviation faults. In the application, unknown wind disturbance and deviation faults are regarded as total disturbance, an improved disturbance compensator is designed by using an adaptive mechanism for the total disturbance, and the size of switching gain is adjusted online according to the control accuracy requirement, so that the waste of controller output energy caused by excessively large switching gain is avoided. For actuator partial failure, a failure factor compensator designed based on an adaptive method enables the unmanned aerial vehicle to timely process faults and recover normal trajectory. An attitude controller is designed by using a non-singular fast terminal sliding mode control technology, so that the robustness and fast response characteristics are ensured, the unmanned aerial vehicle can timely process faults, the fault tolerance of the unmanned aerial vehicle is enhanced, and the flight safety of the unmanned aerial vehicle is improved.

The invention discloses a mooring unmanned aerial vehicle take-up and pay-off anti-interference control method based on image recognition, and relates to the technical field of unmanned aerial vehicle cable anti-interference control systems. Comprising the following steps: acquiring a wind speed, a wind direction, a cable direction, an actually measured tension, a winch speed and a cable image with aligned timestamps, and projecting the wind speed along the cable direction to obtain a wind disturbance component along the cable; inputting the actually measured tension, the winch speed and the wind disturbance component into a tension prediction model to output predicted tension at the next moment; comparing the predicted tension with a safety interval to adjust the take-up and pay-off speed of the winch; and in combination with the image, identifying the cable form, performing visual correction on the winding and unwinding speed of the winch through loosening eliminating logic and vibration suppression logic, and issuing the corrected winding and unwinding speed of the winch to execute and synchronize to the unmanned aerial vehicle so as to adaptively cooperate with the winding and unwinding action of the winch. Through tension prediction and multi-link evaluation adjustment, the problem that the unmanned aerial vehicle shakes and drifts in the air due to the fact that the tension is abnormal and the take-up and pay-off speed is not matched is effectively solved.

The invention relates to the field of remote control, and discloses an intelligent bucket throwing operation method and system for remotely controlling a grab ship unloader, which are used for realizing intelligent bucket throwing operation for remotely controlling the grab ship unloader. The intelligent bucket throwing operation method for remotely controlling the grab ship unloader comprises the steps of generating a full-state expected trajectory containing position, speed and acceleration information, ensuring that the trajectory is smooth and accurate, constructing a nonlinear model prediction controller, integrating a nonlinear disturbance observer, effectively estimating and compensating wind disturbance and unmodeled dynamics, and enhancing the anti-jamming capability of the system. A discrete element method is utilized to simulate interaction of material particles, and in combination with bilge topographic data, spatial distribution after material throwing is accurately predicted, system stability is monitored in real time, and a control instruction is dynamically adjusted. The precision, the stability and the efficiency of bucket throwing operation of the grab ship unloader are remarkably improved, the operation difficulty and the labor cost are reduced, and the grab ship unloader can well adapt to complex working conditions.

The invention discloses an unmanned aerial vehicle flight control method and system based on a Mangbar and a dual-channel attention mechanism under wind field disturbance, and particularly relates to the technical field of unmanned aerial vehicle autonomous navigation and intelligent control. The method comprises the following steps: constructing a wind field disturbance model based on computational fluid mechanics, and simulating an unsteady wind field environment among urban building groups; designing a deep reinforcement learning network fusing a Mama framework and a double-channel attention mechanism, wherein the deep reinforcement learning network is used for realizing dynamic modeling of long-sequence wind field features and attention weighting of key spatial-temporal features; a dynamic road sign point guiding mechanism and a multi-stage attenuation greedy strategy are put forward, the sparse reward problem is relieved, and the local path optimization capability is improved; and a multi-target composite reward function including energy constraint, safety distance and path efficiency is constructed, and global path planning of energy consumption perception is realized. The method can improve the flight stability, path smoothness and energy efficiency of the unmanned aerial vehicle in a strong wind disturbance environment, and is suitable for unmanned aerial vehicle autonomous navigation tasks in an urban complex environment.

The invention relates to the technical field of wind power plant construction, and discloses a wind-solar narrow field fan hoisting construction method which comprises the following steps: arranging a real-time dynamic positioning module and an inertial measurement unit; presetting a virtual stable anchor point, and resolving a deviation vector between the real-time spatial position of the hoisting component and the virtual stable anchor point by the control system; according to the invention, the conversion from passive swing suppression to active disturbance cancellation is realized, the traditional open-loop operation is converted into a closed-loop control process, and under the conditions of high wind speed and narrow space, the control efficiency is improved. Therefore, the collision risk between the component and the photovoltaic facility is avoided, and the installation precision is ensured.

The invention belongs to the technical field of vehicle four-wheel steering control, and discloses a four-wheel steering control method and system based on Transform and deep reinforcement learning. The method comprises the following steps: S1, obtaining an output state quantity based on a vehicle steering model comprising crosswind disturbance; and S2, according to the output state quantity and an improved PPO-Transformer algorithm, solving a feasible optimal solution of front and rear wheel turning angles in the four-wheel steering system, and determining a control quantity acting on the vehicle steering model based on the feasible optimal solution. Specifically, on one hand, the stability factor and disturbance factor of vehicle steering are fully considered, and external disturbances such as crosswind are introduced into a vehicle steering model, so that the robustness of a reinforcement learning training result is effectively improved; and on the other hand, the improved PPO-Transform algorithm is obtained by embedding a Transform architecture with a simplified structure into an Actor network, and the recognition capability of the algorithm on abnormal data is improved by utilizing a self-attention mechanism of a Transform core while the real-time control and generalization advantages of the PPO algorithm are not influenced.

The invention discloses a servo turntable low-temperature friction adaptive compensation method, which belongs to the field of antenna servo control, and comprises the following steps: acquiring environment temperature, air pressure, wind speed and current parameters, and generating feature vectors; generating a working condition diagnosis label through pattern recognition; dynamically constructing an instantaneous friction response model from the physical effect library; executing an asymmetric high-frequency current pulse sequence in an extremely low temperature starting stage to break through static friction; based on model output and encoder micro-motion spectrum characteristics, a compensation mode is decided and activated through multi-mode collaborative logic; and calculating a composite compensation amount and superposing the composite compensation amount to a position loop for output. A multi-source environment perception and physical effect library dynamic combination mechanism is adopted, precise compensation can be achieved for severe working conditions such as plateau low pressure and strong wind disturbance, and the pointing precision and operation stability of the servo rotary table in the extremely cold complex environment are improved.

The invention discloses a flight control and low-complexity swing suppression method for an unmanned aerial vehicle hanging load system, belongs to the technical field of unmanned aerial vehicle flight control, and provides a linear active-disturbance-rejection control strategy (LADRC) based on a special orthogonal group SO (3) aiming at the influence of external environment disturbance, and while singularity is avoided and rotation motion is optimized, the unmanned aerial vehicle hanging load system can be controlled in a low-complexity mode. Accurate tracking of a reference trajectory under the conditions of external wind disturbance and load swing is realized; in view of task requirements of cooperative processing trajectory tracking precision and load swing suppression, a virtual position on a tether between the quad-rotor unmanned aerial vehicle and a load is selected as a control target, so that the differential order requirement of a reference trajectory is reduced to two orders, and the whole control framework and quad-rotor unmanned aerial vehicle monomer control are extremely similar; according to the invention, load swing suppression is realized while the unmanned aerial vehicle accurately tracks the expected trajectory.

The invention provides an eVTOL wind disturbance resistance robust design optimization method based on a depth evidence theory, and the method comprises the following steps: firstly, training an EDL model based on existing training sample data, and outputting four key parameters which are used for representing a prediction value, data noise and model uncertainty; secondly, performing performance evaluation on the trained EDL model by using a model evaluation index, visualizing a prediction result, and drawing a prediction scatter diagram and an uncertainty visualization diagram; thirdly, according to the four parameters output by the EDL, calculating a prediction mean value and a variance of the target function; and finally, constructing a robust design optimization problem containing uncertainty information, setting an objective function and constraint conditions, and solving to obtain an optimal solution meeting design robustness requirements. The method does not need to depend on complete design variable probability distribution information, is suitable for uncertainty modeling and optimization problems in a multidisciplinary coupling system, and has high adaptability, accuracy and calculation efficiency.

This invention discloses a dynamically adjustable forest gap simulation device, belonging to the technical field of ecological experimental equipment. The device includes a supporting column, a supporting frame, a driving component, a shading component, and an intelligent control unit. The supporting column is a multi-stage telescopic structure equipped with a field anchoring mechanism. The supporting frame consists of a central connecting part and multiple radially telescopic and foldable radial arm-shaped components. The shading component is laid on the arm-shaped components to form a variable shading area. The driving component drives the arm-shaped components to extend and retract. The intelligent control unit uses off-grid photovoltaic power and can adaptively control the movement of the arm-shaped components according to preset strategies, light intensity, and wind speed parameters, realizing dynamic forest gap simulation and dynamic restoration of wind-disturbed light spots. This invention features high modularity, accurate simulation, stable structure, and suitability for long-term unattended field experiments, effectively solving the technical problems of traditional forest gap simulation devices, such as static fixation, poor dynamic effects, low intelligence level, and insufficient field adaptability.

The invention provides a self-adaptive wind feedforward unmanned ship course control system based on active disturbance rejection, and belongs to the technical field of unmanned ship course control. The system comprises an ultrasonic anemometer for collecting relative wind speed and relative wind direction; the gradient descent module outputs compensation gain based on the difference value between the actual course angle and the expected course angle; the wind feedforward module receives the relative wind speed, the relative wind direction and the compensation gain and outputs wind disturbance compensation; the expansion state observer outputs an actual course angle pre-estimated value, an actual course angle differential pre-estimated value and other unknown disturbance pre-estimated values; the non-linear state error feedback unit performs non-linear combination by using the state error to obtain an expected control quantity; the disturbance compensation unit determines the control quantity of the unmanned ship based on the expected control quantity, the wind disturbance compensation and other unknown disturbance estimation values. Rapid compensation of wind disturbance is achieved through self-adaptive wind feedforward control, and the response speed and stability of sailing direction control of the unmanned ship in a complex wind field are stably improved.

The application belongs to the field of automatic control technology of aircraft, and proposes a quadrotor double pendulum finite time swing elimination method based on full drive mapping and active anti-disturbance, which is applied to a quadrotor unmanned aerial vehicle double pendulum hoisting system. The method adopts a hierarchical control structure composed of an outer ring position and swing elimination control module and an inner ring bottom layer flight control module. The method comprises the following steps: establishing a quadrotor double pendulum horizontal plane block matrix dynamics model; full drive state mapping and dynamic reconstruction facing the controller; Y-axis full drive space isomorphic expansion; UDE-based finite time control law design; closed loop system stability and finite time convergence analysis based on Lyapunov theorem. The application can improve the waypoint tracking accuracy, swing angle suppression effect and robust flight capability of the quadrotor double pendulum hoisting system under the working condition that discrete waypoints are switched and external wind disturbance exists simultaneously.

The application discloses a kind of servo turntable low temperature friction self-adapting compensation method, belong to antenna servo control field, it includes: obtaining environmental temperature, air pressure, wind speed and current parameter and generates feature vector;Through mode recognition, generate working condition diagnosis label;From physical effect library, dynamically construct transient friction response model;In extremely low temperature start-up stage, execute asymmetric high-frequency current pulse sequence to break through static friction;Based on model output and encoder micro-motion frequency spectrum characteristics, through multimodal collaborative logic decision and activate compensation mode;Calculate composite compensation and superimpose to position loop output.The application adopts multi-source environmental perception and physical effect library dynamic combination mechanism, can realize accurate compensation to highland low air pressure, strong wind disturbance and other severe working conditions, improve the pointing accuracy and running stability of servo turntable in extremely cold complex environment.

The invention discloses a carrier rocket load shedding control algorithm verification method and device, equipment, a medium and a product, and relates to the technical field of spacecraft control, and the method comprises the steps: building a carrier rocket entity model located in a wind field simulation system, and simulating an actual wind disturbance environment of a rising section; constructing a dynamic model based on the entity model; obtaining an initial position coordinate, and starting a wind field simulation system according to a preset wind speed parameter; using a load shedding control algorithm to control the position and attitude of the model so as to obtain motion response data; wind speed parameters are changed and iterated until a threshold value is met, and multiple groups of data are obtained; and finally, calculating verification results such as a wind speed reduction rate and a positioning error value through a statistical method. Through a ground low-cost test scheme, an evaluable test environment is established, the problem that the real environment of a load shedding algorithm is difficult to verify is solved, the algorithm performance can be comprehensively and accurately verified, and the flight safety and reliability of a carrier rocket are improved.

This invention discloses an AIS-based UAV search and rescue deployment method and apparatus, relating to the field of data processing technology. The method includes: decoding the AIS signal to obtain decoded information; performing ship information filtering and analysis on the decoded information using a particle filter algorithm to obtain target ship information; obtaining ballistic trajectory calculation information based on the target ship information through ballistic trajectory analysis and ballistic calculation; preprocessing real-time wind field data; constructing a layered wind disturbance model based on the preprocessed real-time wind field data; correcting and optimizing the ballistic trajectory information based on the ballistic calculation information and the layered wind disturbance model to obtain optimized ballistic trajectory information; and generating an execution trajectory command set based on B-spline curve smoothing using the optimized ballistic trajectory information to perform UAV search and rescue deployment in conjunction with real-time control feedback. This invention achieves ballistic trajectory correction control under wind field disturbances, thereby achieving precise UAV deployment of distressed targets under complex sea conditions.

The invention provides a wind disturbance control method based on adaptive parameters and a related device. The wind disturbance control method comprises the steps of collecting original data; inputting the acquired position, speed and attitude data observation values into an improved EKF model for wind disturbance estimation, and estimating a wind disturbance speed component and wind disturbance intensity under a navigation coordinate system in real time; self-adaptive correction is carried out on PID parameters of the attitude loop and the position loop; according to the corrected PID parameters of the attitude ring and the position ring, calculating to obtain a three-axis torque generation and an expected total thrust; according to a four-rotor motor thrust distribution model, the expected three-axis torque and thrust are converted into the expected speed of a motor, and the expected speed is output to the motor through a PWM driving module; and a motor rotating speed feedback value and unmanned aerial vehicle state data are collected in real time, the steps are repeated, and closed-loop control of collection-estimation-adjustment-control is formed. By applying the technical scheme of the invention, the technical problems of fixed wind disturbance resistance control parameters, inaccurate wind disturbance estimation and single adaptive logic of the quad-rotor unmanned aerial vehicle in the prior art are solved.

The invention relates to the technical field of reinforcement learning, and discloses a subway station environment control wind-water linkage system control method based on deep reinforcement learning, and the method comprises the steps: introducing phase information formed by a train operation cycle, combining piston wind disturbance and tunnel cold storage behaviors, and constructing a unified region state expression capable of reflecting a dynamic thermal process in a station; according to the method, a learnable environment model is formed by using temperature, humidity, internal load, external weather and cold source parameters of a subway station hall and a platform, and efficient modeling of time-varying periodic disturbance is realized through an action value function with a finite harmonic structure. At the moment, the reinforcement learning algorithm adjusts the air supply temperature and the chilled water supply temperature at the same time, cooperative control over the air side and the water side is achieved, the system can adapt to fluctuation under different running diagrams and passenger flow conditions, cooling capacity mismatching is reduced, and the energy efficiency and environment stability are improved.

The application belongs to the technical field of unmanned aerial vehicle control, and provides a four-rotor unmanned aerial vehicle model predictive control method based on Kolmogorov-Arnold network residual compensation, which comprises data acquisition, KAN residual compensation, post-processing, residual compression and MPC optimization; the residual compensator pre-training process comprises nominal model and residual label setting, simulation sample generation, training set construction and network training; the application learns the nominal model error through the KAN network and performs feedforward compensation inside the MPC, realizes real-time feedforward compensation of the model error, and can still maintain high trajectory tracking accuracy under wind disturbance and parameter perturbation conditions; the residual learning conforming to the Newton-Euler coupling mechanism is realized by introducing a physical prior mask constraint in the structure, and the model overfitting risk is reduced; the normalization and compression of the residual dimension are realized through the intermediate conversion layer.

The application discloses a kind of dual unmanned aerial vehicle anti-interference cooperative hoisting control method, system, equipment and medium, comprising: obtaining the actual state information of dual unmanned aerial vehicle and the desired state information of virtual leader;According to desired state information, the desired position information of dual unmanned aerial vehicle is calculated according to pre-set dual-machine cooperative decoupling control rule;With desired position information as input, based on the extended state observer and nonlinear anti-interference controller constructed in advance, the control input information of each unmanned aerial vehicle is output, so that the power system controls dual unmanned aerial vehicle anti-interference cooperative hoisting load according to control input information.The application introduces virtual leader, solves the problem of sling tension imbalance caused by independent trajectory planning;Based on dual-machine cooperative decoupling control rule, the problem of unmeasurable load pose caused by flexible sling is solved, and the extended state observer and nonlinear anti-interference controller are used to realize real-time estimation and active compensation for compound disturbance such as wind disturbance and sudden load.