706 results about "Controller design" patented technology

The invention discloses a robust model prediction control method for mechanical arm trajectory tracking control, and relates to the field of multi-degree-of-freedom mechanical arm trajectory tracking control. According to the method, disturbance and parameter perturbation of a mechanical arm system are converted into lumped disturbance, a mechanical arm system error model is established, and feedback linearization is conducted on an error system based on an inverse dynamics method; based on a mechanical arm system error model, a nominal system model prediction controller is designed, a terminal area, a terminal control law and corresponding terminal cost are designed, and the feasibility of rolling interval optimization in each time step is guaranteed. According to the method, the uncertainty and disturbance of the mechanical arm system can be processed, it is guaranteed that system constraints are met, and high-precision trajectory tracking control and input torque optimization are achieved.

The invention discloses a wind power grid-connected oscillation suppression method and system based on a self-adaptive damping controller, and relates to the technical field of oscillation suppression of a power system. According to the method, a self-adaptive damping controller structure is designed, and parameter setting is completed; then building a wind power grid-connected system simulation model; after voltage signals are collected, an FFT processing method is used for identifying oscillation frequency, and whether an unstable oscillation mode exists in the system or not is judged; if unstable oscillation exists, a self-adaptive damping controller is connected between the wind power plant side and the power grid side; the self-adaptive damping controller filters out signal components causing system oscillation and performs phase modulation; a signal component generated by the self-adaptive damping controller is injected into the power grid and counteracts with an original signal, and oscillation suppression is achieved. According to the self-adaptive damping controller designed by the invention, the oscillation frequency identification module and the phase shift parameter calculation module are introduced, so that measured data can be fully utilized, control link parameters are adjusted according to vibration frequency changes, and oscillation is effectively suppressed.

The invention discloses a data-based predefined time heterogeneous multi-agent formation collision avoidance method. The method comprises the following steps: establishing a nonlinear heterogeneous multi-agent system; designing a bimodal artificial potential field function to perform dynamic obstacle avoidance and prevent regional escape; establishing a self-adaptive robust controller used for generating an obstacle avoidance safety motion trail of the root leader; designing a self-adaptive formation zooming mechanism of the leader, and constructing a predefined time affine observer of the follower based on the self-adaptive formation zooming mechanism; designing a unified obstacle function; constructing a virtual control law for processing tracking errors based on the unified obstacle function; designing a neural network estimator; designing controllers of the leader and the follower according to the virtual control law; and forming a collision avoidance decision of the heterogeneous multi-agent formation based on a self-adaptive robust controller, a predefined time affine observer, a neural network estimator and controllers of the leader and the follower. According to the method, safe, efficient and robust cooperative control of the formation in a complex environment is realized, and the safety and task execution efficiency of the heterogeneous multi-agent formation in a limited and unknown environment are remarkably improved.

The invention discloses a fixed-wing unmanned aerial vehicle trajectory tracking control system and method based on a disturbance observer. The system acquires various state data of the unmanned aerial vehicle through the data acquisition module, the interference observer module estimates external interference in real time based on a dynamic model, the trajectory planning module generates an optimized trajectory according to tasks and environments, and the controller module realizes accurate control by adopting a model prediction control and sliding mode control composite strategy. And the execution mechanism driving module executes the control instruction. The method comprises the steps of data acquisition, interference estimation, trajectory planning, controller design and calculation, actuating mechanism driving and the like. The method can effectively improve the trajectory tracking accuracy and stability of the fixed-wing unmanned aerial vehicle in a complex environment, and has a wide application prospect.

The invention belongs to the technical field of position tracking control of rigid multi-joint mechanical arms, and discloses a fuzzy self-adaptive visual servo control method and system for a multi-joint mechanical arm system for placing bobbins in a textile workshop, and the method comprises the steps: constructing an image error model according to the positions of feature points on an image plane; the fuzzy logic system is used for processing uncertain items in the system, the instruction filtering and fuzzy self-adaption technology is used for achieving tracking control over the expected trajectory of the system, the problem of calculation complexity is solved, and adverse effects caused by filtering errors are eliminated. In the process of changing the bobbins, the bobbins are placed on a creel through a multi-degree-of-freedom robotic arm, a clamping jaw at the tail end of the robotic arm is required to accurately grab the bobbins for feeding and discharging, and the requirement for accurate and rapid control of the robotic arm is met, so that research on visual servo control of the robotic arm is of great significance. The method has a good control effect, the problem of calculation complexity in the design process of the controller is solved, the trajectory tracking error is smaller, and the system robustness is higher.

The invention relates to the technical field of power supply, and particularly discloses a peak and frequency regulation heat supply method for a multi-element energy storage coupling coal power unit, which is used for solving the problems that only active frequency is optimized, electric heating coordination and charge state constraint are lacked and time delay compensation is insufficient in the prior art. The method provided by the invention comprises the steps of system modeling, controller design, coupling constraint, adaptive parameter adjustment, delay compensation and distributed consensus. According to the method, a dual-domain electric power-thermal interconnection model is constructed, a cooperative controller based on delay compensation distributed model prediction control is designed, electric-thermal cooperative penalty and charge state constraint are introduced into a target function, a prediction window and weight parameters are adaptively adjusted, and network delay is identified and compensated online. And a consensus algorithm is adopted to realize multi-region power-heat collaborative optimization.

The invention belongs to the field of urban sewage treatment, and provides an inverse fuzzy dynamic optimal self-adaptive aeration control method based on sewage treatment. Comprising the steps of dissolved oxygen concentration kinetic model construction, inverse fuzzy dynamic multi-objective optimization algorithm design, evaluation network and long-term utility function setting, execution network design, actual controller design, execution error function determination, execution network and actual controller parameter optimization and aeration pump control. According to the method, the optimal set value of the dissolved oxygen concentration is obtained through calculation of the inverse fuzzy dynamic multi-objective optimization algorithm; an execution network is designed by utilizing a judgment network and a long-term utility function, and unknown dynamic information of the dissolved oxygen concentration kinetic model is identified; optimization of an execution network and an actual controller is realized through the evaluation network and the execution error function; through the actual controller with the optimal parameters, self-adaptive control over the aeration pump is achieved, the control precision of the aeration degree is improved, and operation energy consumption is effectively reduced.

The invention provides a distributed formation control method driven by a recursive balance network under a communication attack, and relates to the technical field of cooperative control of a multi-agent system, and the method comprises the steps: constructing a distributed multi-agent system model, and constructing an RBN controller heterogeneous communication network architecture and a DoS attack model; the RBN controller design is optimized, the distributed RBN controller architecture is realized, the stability of the RBN controller is analyzed based on the shrinkage mapping theory, and the exponential convergence of the system state difference is proved by constructing a Lyapunov function; training the optimized RBN controller by adopting a difficulty priority confrontation training strategy, designing a multi-objective loss function, and dynamically adjusting the training weight of each difficulty level; and simulating the distributed multi-agent system optimized by the above steps, testing the robustness of the distributed multi-agent system under incremental DoS attack intensity, and performing comparative analysis of heterogeneous and isomorphic communication network configuration and comprehensive performance comparison of an RBN controller and a traditional MPC method.

The invention provides a mechanical arm predefined time trajectory tracking control method and system based on time delay estimation, and relates to the technical field of multi-degree-of-freedom mechanical arm trajectory tracking control. Constructing a predefined time error conversion function to define a system error and conversion error system, designing a barrier function and a feedback control rate based on the conversion error system, and designing a Lyapunov function to prove the stability of the system so as to track an expected trajectory; according to the method, time delay information is deeply fused, dependence on a complex model approximate structure is not needed, stable convergence of the mechanical arm system state within predefined time can be achieved when a mathematical model is not accurate, the system control performance and robustness are effectively improved, and the requirement of modern industry for mechanical arm high-performance control is met.

The invention belongs to the technical field of hypersonic flight vehicle control, and relates to a rigid-elastic coupling-oriented active and passive integrated control method for a hypersonic flight vehicle. The invention aims to realize stable tracking control of the elastic hypersonic flight vehicle. The method comprises the following steps: constructing a longitudinal dynamic model of the elastic hypersonic aircraft; self-adaptive identification of the elastic vibration frequency is realized through a cascaded self-adaptive filter; an elastic modal filtering estimation method is designed, and high-precision and low-cost elastic modal state quantity is provided for subsequent active feedback controller design; and then rigid-elastic coupling model decomposition is carried out, the control performance is ensured by using active disturbance rejection passive control for a rigid body subsystem, an RBF neural network is introduced for an elastic subsystem, an elastic mode is actively inhibited by using sliding mode control, and stable tracking of a reference instruction is realized. The method is an active and passive integrated control method for the hypersonic flight vehicle oriented to rigid-elastic coupling, and the application prospect is wide.

The invention belongs to the technical field of force / position hybrid control of mechanical arm systems, and particularly discloses a finite-time self-adaptive impedance control method and system for a flexible joint mechanical arm system. In order to solve the problems that the control effect of a mechanical arm system is affected by nonlinear and unknown system model parameters at present and derivation is complex in backstepping design, the fuzzy self-adaptive finite time impedance controller is designed based on the impedance control technology so as to achieve hybrid control over the track and force of the tail end of the mechanical arm. In the design process of the controller, a real control law is constructed to realize finite time stability of the system; and meanwhile, command filtering and fuzzy self-adaptive technologies are introduced to solve the problems of calculation explosion in backstepping design and unmodeled dynamics of a mechanical arm system. By means of the control method, the influence caused by system uncertainty can be effectively overcome, the position tracking error of the mechanical arm system is reduced, and meanwhile it can be guaranteed that all signals in a closed-loop system are bounded within finite time.

The invention discloses a hypersonic variable wingspan aircraft attitude control method based on reinforcement learning, aiming at the characteristics of complex flight environment, strong nonlinearity of control input and aerodynamic characteristics, strong coupling and the like of a hypersonic variable configuration aircraft. The method comprises the following steps: acquiring discrete relationships between variables such as wingspan length, rudder deflection angle, flight attitude and flight speed and aerodynamic parameters through a computational fluid mechanics method, and then fitting the discrete relationships by utilizing a neural network method to realize aerodynamic parameter identification under different flight working conditions and appearance conditions; secondly, establishing a dynamic model of the hypersonic variable-wingspan aircraft by using an aerodynamic parameter identification network; and finally, realizing attitude control of the hypersonic variable-wingspan aircraft based on a DQN reinforcement learning method. The method can effectively solve the problems that a traditional control method is complex in controller design and strict in model precision requirement, and simulation experiment results prove that the method can effectively achieve attitude angle tracking.

The invention relates to the technical field of under-actuated crane system motion control, in particular to an enhanced coupling positioning anti-swing control method and system for a crane with distributed mass loads. Based on a Lagrange kinetic equation, establishing a six-degree-of-freedom bridge crane nonlinear model with distributed loads, and analyzing the kinetic characteristics of the six-degree-of-freedom bridge crane nonlinear model; establishing an energy function of the model based on the bridge crane nonlinear model, constructing a new coupling signal based on a displacement signal of the model to enhance dynamic coupling among a trolley, a lifting hook and a load, and constructing a new state vector based on the constructed coupling signal to enhance dynamic coupling among the trolley, the lifting hook and the load. Substituting the constructed new state vector into an energy function of the model so as to obtain a new class energy function; establishing a nonlinear coupling controller with swing angle information according to the proposed new energy-like function; according to the method, linear processing does not need to be carried out on a kinetic equation of a crane system in controller design, and finally efficient trajectory tracking and positioning and load swing suppression are achieved.

The invention discloses a hydroelectric generating set speed regulation control method considering excitation coordination. The method comprises the steps that 1, system state information is collected and preprocessed; step 2, on-line identification of excitation speed regulation coupling characteristics; 3, decomposing a multi-time-scale control target; step 4, designing a self-adaptive multivariable controller; 5, working condition self-adaptive parameter optimization; step 6, intelligently inhibiting the water attack effect; 7, multi-machine cooperative reactive power optimization control is carried out; 8, optimizing and executing a control strategy in real time; the technical problems that excitation speed regulation dynamic coupling, multi-time scale response mismatch, multi-machine cooperative control and the like in a hydroelectric generating set control system cannot be comprehensively solved in the prior art are solved, and the regulation response speed and the system operation safety are improved while the frequency and voltage stability is ensured.

The invention belongs to the technical field of unmanned aerial vehicle trajectory tracking control, and particularly discloses an unmanned aerial vehicle preset performance control method and system considering time-varying position constraints. According to the method, under the condition that the unmanned aerial vehicle has time-varying position constraint, model uncertainty, actuator fault and wind disturbance, a nonlinear mapping method is firstly adopted to convert a system with position constraint into an unconstrained system, then a preset performance control method and a self-adaptive backstepping technology are adopted to carry out controller design on the converted system, and therefore the control precision of the unmanned aerial vehicle is improved. The system error is kept in a preset boundary function range; the invention also designs a fuzzy logic system (FLS) and a nonlinear disturbance observer to estimate the uncertainty and wind disturbance of the model, thereby providing a trajectory tracking control scheme combining model mapping and preset performance. Under the control of the method, the quad-rotor unmanned aerial vehicle has good robustness, and even if an actuator breaks down, the tracking error can still be kept within a preset interval.

The invention provides a fault-tolerant control method for preset performance of a morphing aircraft based on sliding-mode control. The fault-tolerant control method comprises the following steps: establishing a longitudinal nonlinear dynamic model of the morphing aircraft; based on the longitudinal nonlinear dynamic model of the morphing aircraft, establishing a longitudinal nonlinear dynamic model of the morphing aircraft under the fault condition of the execution mechanism; the method comprises the following steps: extracting a speed subsystem and an attitude subsystem aiming at a longitudinal nonlinear dynamic model of a morphing aircraft under an execution mechanism fault condition; carrying out sliding-mode control-based preset performance fault-tolerant controller design on the attitude subsystem; aiming at a speed subsystem, combining an attitude subsystem controller, and carrying out sliding mode control-based preset performance fault-tolerant controller design; the two designed controllers are utilized to realize the fault-tolerant control of the variant aircraft under the condition of executing mechanism fault. The sliding mode control and the preset performance control are combined, so that the conservative property is improved by quick response, the fault-tolerant capability is enhanced by switching the control law, and the stability is improved.

The invention discloses a fuel cell rapid cold start method considering initial water content optimization, and belongs to the technical field of fuel cell automobile optimization control. According to the fuel cell rapid cold start method considering initial water content optimization, a closed-loop model prediction controller is firstly designed to accurately control the current of a galvanic pile, and then the initial film water content is optimized by using a particle swarm optimization algorithm, so that the rapidity of a cold start system is improved. The method can be structurally divided into the following parts: establishment of a cold start model, design of a parameter self-tuning model prediction controller and optimization of the optimal initial membrane water content. In the cold start process, the current output of the electric pile is adjusted in real time according to different environment temperatures and membrane water contents, controller parameters are adjusted in a self-adaptive mode, the freezing rate and the heating rate of water produced by the electric pile can be effectively balanced, and the performance of a cold start system is improved.

The invention provides a finite time cooperative tracking control method based on an adaptive RBF neural network, and belongs to the technical field of networked multi-agent control strategies. Constructing a dynamic mathematical model of a high-order all-drive uncertain nonlinear multi-agent system comprising a virtual leader and a follower; according to a cooperative tracking control target and uncertain items in the system, constructing an error dynamic system comprising an adaptive RBF neural network estimation compensation item; designing a finite time integral sliding mode surface based on a high-order all-drive system theory; designing linearization parameters of a finite time integral sliding mode surface based on a pole assignment method according to system dynamic performance and finite time convergence requirements, and obtaining a finite time integral sliding mode controller; and designing a self-adaptive updating law of an upper bound of an RBF neural network weight and an approximate error, and substituting the network weight and the approximate error into a finite time integral sliding mode controller to realize cooperative tracking control of finite time.

The invention relates to a dynamic modeling method for an attitude control system under a dynamic fault. The method comprises the following steps: determining a modeling hypothesis of a nonlinear dynamic model; establishing a coordinate system used for modeling; rocket configuration parameters and engine related parameters are obtained; building displacement and acceleration descriptions of the three types of structures on the rocket; establishing a rigid body translation equation, a rigid body rotation equation, a rocket body elastic vibration equation, a propellant shaking equation and a sensitive element measurement equation; summarizing the five established equations to form a nonlinear dynamic equation set; and performing small-disturbance linearization expansion on the nonlinear dynamic equation set on the basis of the nominal reconstructed trajectory to obtain a linearized small-deviation equation set suitable for controller design and stability analysis. According to the method, the influence of the thrust drop fault is comprehensively considered, and the model can be used for carrying out relatively accurate dynamic response analysis and reconstruction scheme design under the fault.

The invention provides an active-disturbance-rejection control method for an electromagnetic bearing two-level digital switching power amplifier embedded with model information. The method comprises the steps that an electromagnetic bearing two-level digital switching power amplifier mathematical model suitable for controller design is established based on the Fourier series theory and coil current characteristics; a direct current component in the mathematical model is defined as a modeling disturbance term, and feedforward compensation is directly carried out in the control law; parameter perturbation and an unmodeled part in the mathematical model are defined as unknown perturbation items, and real-time estimation is carried out through an extended state observer; a current item and a control input item in the mathematical model are used as known model information to be embedded into the design of the extended state observer; designing a feedback control law to carry out real-time compensation on the current item, the modeling disturbance item and the unknown disturbance item; a zero-order retainer and a current observer are adopted to carry out discretization processing on the controller, and the discretization processing is realized on a digital control platform based on a DSP (Digital Signal Processor). The method is high in current response speed and high in control precision.

The invention is suitable for the technical field of automatic driving vehicle control, and provides an automatic driving track rapid tracking control method based on online neural network learning, which comprises the following steps: firstly, designing an adaptive model prediction controller, then making a data set and training a fuzzy radial basis function neural network; then, online learning of the fuzzy radial basis function neural network is carried out; and finally, accelerated optimization of the training process of the fuzzy radial basis function neural network is carried out. The automatic driving track rapid tracking controller based on online neural network learning provided by the invention has the remarkable advantages that the neural network model is trained by using control data of MPC (model predictive control), and a nonlinear relation is fitted to approximate the MPC, so that the calculation efficiency is effectively improved, and the rapidity of the controller is improved; the controller can collect real-time data, update a data set and learn new neural network weight parameters online in the process of tracking a reference trajectory, and shows better adaptability and precision compared with a traditional model prediction controller.

The invention relates to a method and device for designing a controller of a direct-current converter and a medium, and the method comprises the following steps: determining a control condition of the direct-current converter according to a controller design scene, and inputting the control condition into a large language model; establishing a mathematical model of the direct-current converter according to control conditions by using a large language model, and calculating converter control parameters; designing and verifying a circuit simulation model according to the converter control parameters; outputting a controller parameter control code by using a large language model according to the circuit simulation model; and running a controller parameter control code, an inspection program and a controller performance index, and iteratively eliminating error information to obtain a coding result. Compared with the prior art, the method has the advantages of short waiting time and high accuracy.

The invention discloses an intelligent adaptive fault-tolerant control method for an aircraft. According to the method, the extended state observer with fixed time convergence is designed to obtain the lumped disturbance including the fault influence, the design of the super-spiral sliding mode controller is completed under the preset performance control framework, and the compensation of the total disturbance is generated by means of the good robustness of the sliding mode controller and in combination with the observer. The influence of aircraft faults on a control system is effectively reduced, the preset performance super-spiral sliding mode controller can realize rapid and accurate tracking of a control instruction in a short time, overshoot and oscillation in the control process are reduced, and the influence of buffeting of a traditional sliding mode algorithm on the aircraft control system is reduced; meanwhile, a reinforcement learning agent is designed to carry out online self-adaptive adjustment on parameters of the super-spiral sliding mode controller with the preset performance, so that performance reduction of the controller caused by various sudden faults which occur randomly and have random fault types is dealt with, and the influence of the faults on aircraft tasks is reduced.

The invention relates to an all-drive unmanned vehicle tracking control and torque control method based on a residual error model. The method comprises the following steps: establishing a nonlinear vehicle dynamics model and a Gaussian process-based residual error model; combining the two models to obtain a vehicle dynamics model based on the residual error model; establishing a Gaussian-model predictive control GP-MPC controller for path tracking by taking transverse compensation and course angle minimization as optimization targets and taking a vehicle dynamics model based on a residual model as a prediction model; a multi-target torque control algorithm is designed, the optimal control quantity output by the GP-MPC controller is distributed, and the expected longitudinal force of each tire is obtained; and designing a tire longitudinal force observer and an anti-interference current control law. According to the invention, the defects of poor tracking precision and poor stability of an all-drive unmanned vehicle are effectively overcome.

The invention belongs to the field of vehicle stability control, and particularly relates to a control method suitable for integration of four-wheel independent drive and active rear wheel steering. Comprising the steps of establishing a whole vehicle dynamics model suitable for controller design, performing stable region division by combining front and rear wheel side slip angle phase planes, setting an ideal yaw velocity and an ideal side slip angle, designing a feedforward and PID feedback integrated controller, performing torque distribution and the like. According to steering wheel rotation angle input, corresponding parameters of the vehicle are combined, the vehicle stability coefficient, the ideal yaw velocity and the side slip angle are calculated, the feedforward and PID feedback integrated controller inputs the calculated rear wheel rotation angle into the controlled vehicle, the calculated additional yaw moment obtains the basic driving moment based on pedal information, and the vehicle stability coefficient, the ideal yaw velocity and the side slip angle are calculated. Torques corresponding to four wheels are input to a controlled vehicle through torque distribution, so that the purpose of integrated control is achieved, and the vehicle handling stability is improved.

The invention discloses a mechanical arm iterative learning control method based on a radial basis function network. The method solves the limitation that a traditional mechanical arm control method deals with nonlinear characteristics and external disturbance problems in a complex dynamic environment. The method provided by the invention comprises the following steps: firstly, constructing a mechanical arm system dynamic model, and dynamically correcting and optimizing a reference track by adopting a dynamic correction strategy; then designing a radial basis function neural network to construct a nonlinear compensation item, and designing a dynamic weight parameter and a dynamic learning gain for optimizing the performance of the controller; and finally, designing an iterative learning controller, and verifying the stability and error convergence of a control algorithm. Through the radial basis function network, the dynamic adjustment strategy and the iterative learning strategy, the control precision, the adaptive capacity and the error convergence speed of the mechanical arm system are improved.

The invention discloses a two-degree-of-freedom helicopter optimal tracking controller design method based on disturbance observation, and relates to the technical field of two-degree-of-freedom helicopter control, and the method comprises the steps: considering the internal uncertainty and external disturbance of a system, and constructing a two-degree-of-freedom helicopter system equation; a pre-defined time nonlinear disturbance observer is introduced to estimate disturbance, coordinate transformation is constructed based on a dynamic surface control technology, a pre-defined time filter is introduced, a two-degree-of-freedom helicopter system model is decomposed into two stages of subsystems, and an optimal performance function is constructed for each subsystem. And designing an optimal virtual controller and a predefined time trajectory tracking controller. The controller designed by the invention can ensure that all signals of the whole two-degree-of-freedom helicopter are bounded within the preset time, can effectively improve the transient performance and the steady-state performance of the two-degree-of-freedom helicopter, and can ensure that the two-degree-of-freedom helicopter can still quickly and accurately track a reference trajectory within the preset time after being disturbed.

The invention relates to a hybrid energy storage control method for an urban rail transit energy router. The method comprises the following steps: S1, carrying out topological structure design and system compatibility configuration on the energy router; s2, impedance modeling and frequency division power distribution of the hybrid energy storage system are carried out; s3, fuzzy controller design and super capacitor SOC dynamic management are carried out; s4, carrying out membership function optimization and fuzzy control parameter setting; s5, multi-mode cooperative control and system operation optimization are carried out; according to the structure of the energy router and the power utilization characteristics of the rail transit system, working modes are divided, the working state of the system is optimized, and the system is kept in a reasonable working state. The method can effectively improve the utilization rate of energy and prolong the service life of the system.

The present invention discloses a fixed-time control method for a multi-motor servo system based on multi-surface sliding mode, including the modeling of a multi-motor servo system affected by friction and unknown time-varying time delay, the design of a fixed-time tracking controller, the design of a fixed-time synchronization controller, and the design of a fixed-time convergence controller. The present invention discloses a synchronization and tracking control method for a multi-motor servo system based on multi-surface sliding mode. Its technology includes the modeling of a multi-motor servo system, the design of a fixed-time tracking controller, the design of a fixed-time synchronization controller, and the design of a fixed-time convergence controller. In view of the load tracking control problem in a multi-motor servo system, the present invention designs a fixed-time tracking controller based on multi-surface sliding mode; in order to achieve speed synchronization control among multiple motors, a fixed-time synchronization controller based on multi-surface sliding mode is designed. The present invention can effectively solve the synchronization and tracking control problems of a multi-motor servo system affected by friction and unknown time-varying time delay.

The invention discloses a PINN-based magnetic levitation vehicle nonlinear predictive control method and device and a medium, and relates to the field of rail transit, and the predictive control method comprises the following steps: S1, constructing a dynamic model; s2, learning and approaching unknown dynamic and time-varying parameters in the dynamic model by adopting a physical information neural network; s3, designing an optimization cost function meeting system input and output constraints based on the unknown dynamic state of the dynamic model predicted by the physical information neural network; and S4, constructing a step-by-step variable terminal constraint set to process input time lag. In a controller design and theoretical analysis process, a non-linear dynamic form of a system is completely reserved, and a stepping variable terminal constraint set suitable for input time delay is constructed, so that the controller can still maintain stability and dynamic performance under the condition that a system state obviously deviates from a balance point. According to the method, the operation safety and the control precision of the maglev vehicle under complex working conditions such as parameter drift and time lag disturbance are effectively improved.