64 results about "Maglev" patented technology

A recursive RISE control method and system for maglev train levitation systems is disclosed. The control method includes: constructing the dynamic equations and voltage balance equations of the electromagnets based on a single-point levitation system, and then constructing a dynamic model of the single-point levitation system accordingly; designing a virtual control law, and then designing a recursive RISE controller based on the backstepping method by combining the dynamic model of the single-point levitation system and the virtual control law; performing stability analysis on the RISE controller to obtain its stability conditions; and, based on satisfying the stability conditions, using the RISE controller to perform real-time control of the levitation gap of the maglev train levitation system. This invention has excellent anti-interference capabilities, reducing the impact of external interference or model uncertainty on levitation accuracy. Furthermore, by handling the nonlinear relationship between voltage and current through the backstepping method, this invention avoids the model mismatch problem caused by linearization.

The application discloses an assembled superconducting maglev track structure and a construction method thereof, and belongs to the technical field of superconducting maglev tracks. The assembled superconducting maglev track structure comprises two inverted T-shaped tracks and a connecting frame, a plurality of interval arranged adjusting holes are arranged on each inverted T-shaped track, each adjusting hole is communicated with a first wire groove or a second wire groove, a first anchoring bolt is inserted in each adjusting hole, and a suspension guide coil or a traction coil is fixed at one end of the corresponding first anchoring bolt. Two interval arranged wheel running surfaces are formed at the top of the connecting frame, the connecting frame is located between the two inverted T-shaped tracks, and the two ends of the connecting frame are connected with the corresponding inverted T-shaped tracks through post-poured belts. The assembled superconducting maglev track structure provided in the application can not only reduce concrete pouring at a construction site, but also quickly and accurately fix the suspension guide coil or the traction coil, so that the construction efficiency is improved.

The application provides a UAV-InSAR-based magnetic suspension system multi-point collaborative reinforcement learning compensation control method, system, device and medium, the method comprises the following steps: using a UAV to carry a lightweight X-band interferometric synthetic aperture radar system to carry out high-precision surveying and mapping on a magnetic suspension line, and constructing an orbit irregularity power spectrum model; a hierarchical control system is constructed, the amplitude saturation controller in the lower layer generates a basic electromagnetic force control law according to the state quantity of the current suspension point; the upper layer compensation controller based on reinforcement learning is an agent, interacts with the environment composed of the suspension frame, the track and the amplitude saturation controller, trains by using the standardized irregularity function obtained from the track irregularity power spectrum model, and outputs the compensation control quantity for each suspension point; the basic electromagnetic force control law and the compensation control quantity are superimposed to generate the total electromagnetic force control law of each suspension point, and the suspension system is actively compensated and globally stably suspended. The application significantly improves the comprehensive control performance of the suspension system.

The application provides a turnout beam, which comprises a plurality of beam body units connected in sequence, the beam body unit comprises a box beam, an inner lateral transverse rib plate and a side edge assembly, a plurality of inner lateral transverse rib plates and a plurality of side edge assemblies are arranged on both sides of the box beam along the length direction at intervals, and the inner lateral transverse rib plates and the side edge assemblies on both sides of the box beam are symmetrically arranged; the length direction of the side edge assembly is parallel to the length direction of the box beam, a single side edge assembly is connected with a plurality of inner lateral transverse rib plates corresponding to the single side edge assembly, and the upper top surface of the side edge assembly is flush with the upper top surface of the box beam. The structural form of the turnout beam of the application can effectively reduce the driving force required when the line type is switched, compared with the existing turnout beam. The application further provides a high-speed magnetic levitation turnout and a switching control method thereof, the switching time is less than or equal to 24s, the lateral line type precision error is within 2mm per full line length, the line type fitting precision is not less than the existing eight-car arrangement scheme, and the driving force is much smaller than the three-car arrangement scheme.

This application discloses a multi-field coupled dynamics calculation method and related products for superconducting maglev trains. The method includes: determining the operating conditions of the superconducting maglev train simulation model based on its operating state information; predicting the aerodynamic forces of the superconducting maglev train simulation model by calling a response surface fitting model corresponding to the operating conditions, and predicting the electromagnetic forces of the superconducting maglev train simulation model by calling an electromagnetic force model corresponding to the operating conditions; superimposing the corresponding components of the aerodynamic forces and electromagnetic forces to obtain the target load, which includes the target magnetic drag, target levitation force, target guiding force, target magnetic drag torque, target levitation torque, and target guiding torque; and inputting the target load as an external load into the multibody dynamics model to obtain the dynamic response results. Thus, the dynamic response results can effectively reflect the actual motion of the superconducting maglev train under complex operating conditions.

The present application relates to the technical field of intelligent operation and maintenance of maglev track, and particularly discloses a maglev maintenance base steel beam connecting bolt health monitoring system, which specifically comprises a data acquisition module, a data processing module, a failure diagnosis module and a cloud service platform. The present application sets strain gauges on bolt heads for monitoring, does not need to disassemble or damage the bolts, can monitor the stress of the bolts in service state without affecting the structural integrity, reduces the risk and cost in the monitoring process, in addition, monitors the vibration characteristics of the steel beam, indirectly obtains information about whether the bolt connection is normal, finally, adopts image recognition technology to monitor the bolt loosening in real time, the fusion of the above three technologies of direct stress, indirect representation and image monitoring, superimposed with maglev vehicle operation condition data, can provide comprehensive structural health monitoring information, which is helpful for comprehensively evaluating the overall performance and safety of the connecting bolts and real-time early warning.

This application provides an anti-deformation design method and apparatus for welded structures, relating to the field of superconducting magnet technology. The method includes: constructing a three-dimensional structural model of the weld seam; performing thermo-mechanical coupling analysis and stiffness analysis on the three-dimensional weld seam model to determine the inherent deformation caused by the welding process and the impact load deformation caused by service impact loads; determining anti-deformation parameters to compensate for the total deformation of the welded structure based on the inherent deformation and impact load deformation; and determining the geometric parameters of the welded structure based on the anti-deformation parameters. Therefore, this method suppresses deformation failure of the welded structure caused by the superposition of dynamic loads, extends the service life of the welded structure, and thus improves the operational reliability of the superconducting magnet cryogenic thermostat and even the entire high-speed maglev train.

The application provides a kind of electromagnetic field fast prediction method and system of maglev train suspension electromagnet, for the coil strong source of suspension electromagnet under typical working condition, nonlinear constitutive of iron core and local high gradient multiscale coupling problem, based on electromagnetic field sample data extraction coil area and construct distance field, according to the structure characteristics of suspension electromagnet and the distance field, the solving area of electromagnet is divided into coil conductor subdomain and multiple iron core subdomains of different distance levels, and subnetwork is respectively constructed.In the training process, the residual error of Maxwell quasi-static equation and the consistency constraint of material constitutive are introduced in the subdomain, the magnetic vector potential continuity and the normal continuity constraint of magnetic induction intensity are applied on the interface of subdomain;Further introduce the time-varying mixed scheduling mechanism of the right end source term of iron core subdomain, to improve the prediction stability and precision of strong source area and high gradient area.In the reasoning stage, the electromagnetic field distribution can be quickly output, and support is provided for fast calculation of electromagnetic force, eddy current loss, etc.

This invention discloses a maglev train rescue wheel device and a maglev train, including a mounting base, wheel carriers, and hydraulic cylinders. The mounting base includes a horizontal mounting base and a vertical mounting base. The wheel carriers are located on both sides of the vertical mounting base and are rotatably mounted on the vertical mounting base via eccentric shafts. Each wheel carrier has a wheel mounted on its outer side via a wheel axle. The hydraulic cylinder is arranged obliquely, with one end hinged to the horizontal mounting base and the other end hinged to the drive arm of the wheel carrier to drive the wheel into a retracted or lowered state. Limiting blocks are provided on both sides of the vertical mounting base, and each wheel carrier has a support part for positioning. In the lowered state, the support part of the wheel carrier abuts upward against the limiting blocks. This device can solve the problem of difficult rescue of high-speed maglev vehicles and improve rescue efficiency.

This invention relates to a simulation verification method and system for a flexible direct-drive maglev line. The main components include constructing a virtual model of the flexible direct-drive maglev line; an FRT controller simulation module loading the virtual model and running a high-fidelity motor mathematical model and motion control algorithm; the FRT controller simulation module receiving control commands from an external process controller; real-time calculation based on the virtual model to generate dynamic response data of the virtual mover; and real-time feedback of the dynamic response data to the external process controller. This method completely eliminates the need for physical motors and the maglev line, allowing for comprehensive algorithm performance testing and process logic integration during the control program development phase, significantly shortening the development cycle.

The application discloses a superconducting electric maglev railway low-speed turnout, and belongs to the technical field of maglev rail transit, and comprises a turnout area base plate and a movable guide mechanism. The top end surface of the turnout area base plate is flush with the top end surface of a running plate of a main line track. Straight stock guide rails and side stock guide rails are arranged on the turnout area base plate. The movable guide mechanism comprises a movable frog, a guide assembly and a frog driving assembly. The movable frog is connected with a post-turnout guide rail. The guide assembly comprises a frog stand and a frog sliding groove, and the frog sliding groove is arranged on the turnout area base plate. The frog stand is slidably arranged in the frog sliding groove. The frog stand is connected with one frog driving assembly on each side. The superconducting electric maglev railway low-speed turnout can not only realize stable low-speed line changing of a superconducting maglev vehicle, but also can simplify a turnout structure and reduce the land occupation area of the turnout, so that the construction cost of the turnout structure is reduced, and the convenience of operation and maintenance of the turnout structure is improved.

The application discloses a high-temperature environment magnetic suspension motor heat protection method, obtains the armature winding loss, excitation winding loss and core loss of the magnetic suspension motor under the rated working condition; based on the component loss and the corresponding volume, calculates the heat generation rate of each component, and establishes a temperature field mathematical model containing the heat conduction coefficient and the convective heat transfer coefficient; according to the temperature field mathematical model, the node temperature set of the whole magnetic suspension motor is determined, and the node temperature set is divided into temperature intervals; when the highest temperature is higher than the preset safety threshold, the arrangement parameters of the cooling channel are adjusted, and the simulation and adjustment are repeatedly executed until the highest temperature is below the preset safety threshold, and the heat protection is completed. The application verifies the highest temperature through the temperature field simulation, if the highest temperature exceeds the preset safety threshold, the arrangement parameters of the cooling channel are dynamically adjusted and iteratively optimized until the temperature control requirement is met, so that the key components of the motor are effectively prevented from over-temperature under the high-temperature environment.

The application provides a multi-mode laser ranging and speed measuring device and method for a super-high-speed maglev system, which comprises a laser range finder, a laser reflection plate, a vehicle-mounted grating light source, a plurality of ground laser receiving modules and a data signal processor; the laser range finder is arranged on the ground and is used for emitting laser to the laser reflection plate and acquiring the absolute position of a vehicle according to the reflected laser; the laser reflection plate is arranged on the vehicle and is used for receiving laser and reflecting the laser back to the laser range finder; the vehicle-mounted grating light source is arranged on the motor rotor of the vehicle and is used for emitting laser to form a grating, and the grating is irradiated into the corresponding ground laser receiving module; the plurality of ground laser receiving modules are arranged on one side of the ground track along the direction of the vehicle movement at equal intervals and are used for receiving the grating and generating the relative position information of the vehicle according to the grating; and the data signal processor is used for obtaining the actual position and speed of the vehicle according to the absolute position and the relative position information of the vehicle.

This invention discloses a magnetic levitation control method based on regularized data-driven strategy optimization. First, force analysis is performed on the smallest levitation unit of the maglev train to establish nonlinear dynamic equations. Then, input and output data of this unit are collected at time intervals {0,1,…,k}, and a sample covariance matrix is ​​constructed based on the data. The dynamic equations of the levitation system are rewritten through covariance parameterization. Subsequently, a regularization term is introduced into the LQR cost function to construct a direct data-driven LQR optimization problem with regularization constraints. Finally, the strategy parameter matrix is ​​updated using the projected gradient descent algorithm, and the covariance matrix and its inverse matrix are recursively updated using the rank-one update rule to achieve online control gain update and complete the levitation control of the maglev train. This invention eliminates the need for precise dynamic modeling, solving the problems of cumbersome modeling and inaccurate parameters in traditional model-based control. The regularization term significantly improves the system's robustness to complex disturbances and noise, effectively avoiding system instability under conditions of minimal air gap constraints.

The application belongs to the technical field of artificial intelligence and magnetic suspension transportation, and discloses a magnetic suspension transportation control intelligent system based on multi-modalities, which comprises a user subsystem, a user interface, an artificial intelligence subsystem, a ubiquitous perception subsystem, a magnetic suspension transportation physical subsystem and a communication subsystem; the user subsystem is used for submitting transportation demand, user demand and transportation objects; the artificial intelligence subsystem is used for completing system-level safety demanding tasks, vehicle-level safety demanding tasks and vehicle-level non-safety demanding tasks; the ubiquitous perception subsystem provides multi-modal perception information of the user subsystem and the artificial intelligence subsystem; the magnetic suspension transportation physical subsystem provides physical reality for completing the transportation demand; and the communication subsystem provides ubiquitous interconnection basis for other subsystems. The application effectively promotes the potential implementation of multi-modal artificial intelligence in the safety demanding field, accelerates the intelligent transformation of the magnetic suspension transportation system, and promotes the deep integration of computation, information and physics.

This invention discloses a soft magnetic steel plate for high-speed maglev train guide rails and its production method, belonging to the field of structural steel manufacturing technology for railway tracks. The soft magnetic steel plate comprises the following components by mass percentage: C: 0.040-0.070%, Si: 1.20-1.70%, Mn: 0.35-0.70%, P≤0.015%, S≤0.002%, Ni: 0.40-1.00%, Cu: 0.20-0.50%, N≤60ppm, H≤2ppm, with the remainder being Fe and unavoidable impurities. The sum of the percentages of the above components is 100%. The production method includes low-temperature heating, high-temperature controlled rolling, controlled cooling, and normalizing processes. This production method is simple, low-cost, and easy to scale up, and the produced soft magnetic steel plate can simultaneously possess excellent low-temperature toughness and good magnetic properties.

The application discloses a kind of magnetic power propelling magnetic suspension generator device and its application method, belong to generator technical field, the device of the present application includes base, control mechanism, energy storage mechanism, data monitoring mechanism, starting motor, transmission mechanism, suspension generator and adjustable magnetic power mechanism;Adjustable magnetic power mechanism is set on transmission mechanism, the two sides of the transmission mechanism are respectively connected with starting motor and suspension generator, the suspension generator is electrically connected with energy storage mechanism, the data monitoring mechanism, starting motor and the adjustable magnetic power mechanism are electrically connected with the control mechanism.The magnetic power propelling magnetic suspension generator device and its application method described above, greatly reduce the driving power of starting motor, save energy.

The present application provides a vibration test bench for a permanent maglev train, which comprises: a base, a vertical excitation system, a permanent magnet track simulation system, a gantry-type supporting frame, a suspension platform, a lateral excitation system and a longitudinal excitation system. In the present application, the positional relationship among the levitation frame of the permanent maglev train, the suspension platform and the permanent magnet track simulation system is adjusted by means of the vertical excitation system, the lateral excitation system and the vertical excitation system respectively, the permanent maglev train is maintained in the levitated state by means of the permanent magnet track simulation system, and a variety of the working conditions, such as unsmooth passing on the track, etc., are simulated by means of the vertical excitation system and the lateral excitation system respectively. The vibration test bench for a permanent maglev train in the present disclosure can be used to test the dynamic performance of a permanent maglev train in a freely levitated state, and further can test the dynamic performance of train-track coupling, and has a wide application range.

A magnetic levitation railway system is disclosed herein. The system comprises a vehicle, a guidance track arranged for supporting the vehicle above the guidance track by magnetic levitation, and at least one linear motor comprising a mover and an elongate stator. The vehicle is provided with the mover and the guidance track is provided along its length with the stator. The linear motor is arranged to generate a propulsion force acting on the vehicle along the longitudinal direction of the guidance track for propelling the vehicle along the guidance track. The at least one linear motor is arranged to further generate a respective normal force acting on the vehicle in a direction that is perpendicular to the direction of the propulsion force and has a horizontal component. Further disclosed is a method of controlling such a system.

The present application belongs to the technical field of medium and low speed maglev track structure design, and discloses a medium and low speed maglev large-span bridge end adaptive track row expansion and contraction device and method. The device is arranged at the beam joint position of the bearing track beam corresponding to the large-span bridge structure joint, spans and overlaps between the beam ends of two adjacent bearing track beams, and is composed of a bearing structure, a modular track unit, an adjusting cushion layer structure, a connecting limiting structure and a linkage structure. The device can effectively adapt to the longitudinal expansion and contraction deformation and beam end corner of the bridge, and ensure the continuity and running smoothness of the track structure at the beam joint. Meanwhile, the device has a certain height adjusting capacity in the vertical direction to adapt to the construction error and structural deformation in the operation stage. The method covers multi-process collaborative control of bearing structure reverse positioning, adjusting cushion layer hierarchical layout, connecting limiting structure adaptive installation and modular track unit structure pre-adjustment positioning, so as to realize the balanced release of the structure assembly precision and dynamic expansion and contraction performance of the track row expansion and contraction device.

This utility model discloses an electromagnetic support system for medium- and low-speed maglev vehicles and a maglev vehicle. The electromagnetic support system includes an M-shaped rail, a levitation electromagnet, and a traction motor stator. The M-shaped rail includes a main body and a secondary induction plate of the traction motor fixed to the middle of the lower surface of the main body. The upper surface of the main body is fixedly connected to the lower surface of the T-shaped track beam. The levitation electromagnet is located below the M-shaped rail and installed on the lower part of the suspension frame support arm of the vehicle body. The levitation electromagnet includes a U-shaped iron core and an electromagnet winding wound around the middle of the U-shaped iron core. The two ends of the U-shaped iron core point upwards toward the main body of the M-shaped rail. The traction motor stator is fixed above the electromagnet winding and corresponds to the position of the secondary induction plate of the traction motor. This utility model is beneficial for reducing the levitation energy consumption of medium- and low-speed maglev vehicles with a vehicle-rail-hugging design and for extending the service life of the levitation electromagnet.

This invention discloses a dedicated measuring stand and method for high-speed maglev tracks, belonging to the field of high-speed maglev track engineering measurement technology. This invention solves the problems of existing equipment being costly and complex to operate, lacking dedicated static measuring tools suitable for rapid on-site testing and with strong environmental adaptability, thus failing to meet the real-time data requirements for daily track inspections and fine adjustments. The invention achieves rapid assembly and disassembly of the track measuring stand through a magnetic base. Its composite structure of high-strength alloy hard aluminum profile and tool steel balances high rigidity and lightweight, avoiding deformation that affects accuracy and facilitating handling. Before measurement, a standard sample is used for calibration to unify the benchmark, ensuring consistent, repeatable, and traceable results. The stand is equipped with four 0.01mm precision electronic dial gauges that simultaneously collect data, and combined with dedicated formulas, quickly calculates indicators, resulting in high measurement efficiency, sub-millimeter level measurement capabilities, and independence from environmental conditions such as line of sight and lighting, adapting to the complex testing needs of tracks.

The application discloses a maglev track irregularity random evolution modeling method, medium and equipment, and belongs to the field of track engineering and random dynamics modeling. The method comprises the following steps: acquiring maglev track irregularity data collected along the line direction, and acquiring track structure parameters and vehicle load statistical characteristics corresponding to the line; calculating the track irregularity state increment between adjacent sampling points, and constructing a state variable set based on the track irregularity quantity, the track structure parameters and the vehicle load statistical characteristics; dividing the state interval according to the value range of the state variable set, and statistically counting the conditional statistics of the state increment in each interval; and identifying the drift term and the diffusion term function in the random differential equation by using the conditional statistical information, through statistical inversion, machine learning or a fusion mode thereof, and constructing a track irregularity random evolution model. The application can reflect the non-stationary and state-dependent characteristics of the track irregularity under the action of the track structure and the vehicle load, and can be used for track state evaluation, dynamics simulation and maintenance decision.

This disclosure relates to the field of center of gravity measurement devices, and in particular to a center of gravity measurement device for a magnetic levitation train. The device includes a base, a force-measuring component, and a rotating component. The base is equipped with a state-switching device. The force-measuring component includes a force sensor, a ball socket, and a ball head. The force sensor is mounted above the state-switching device, the ball socket is mounted above the force sensor, and the ball head is mounted on the rotating component. The rotating component is used to connect with the sample to be measured. The state-switching device cooperates with the rotating component to switch the sample between a horizontal and an inclined state. In both the horizontal and inclined states, the ball head can be located within the ball socket, allowing the force sensor to detect the weight of the sample. Because the ball head is placed within the ball socket, and the ball head and ball socket have a spherical fit, the force contact position is a spherical contact, ensuring that the measuring sensor is less affected by lateral forces during force measurement, thereby improving measurement accuracy.

This application provides a method and apparatus for designing the alignment of a flexible, bendable, normally-conducting maglev turnout. The method first determines the length relationships of straight segments, transition curve segments, and circular arc segments, and then defines the constraints on the turnout beam. Subsequently, using several sets of determined straight segment lengths and several sets of determined circular transition ratios, the lengths of several sets of transition curve segments and circular arc segments are determined through these length relationships. Next, the determined lengths of the transition curve segments and circular arc segments are initially screened using the constraints. Based on the screened length parameters, coordinate parameters are further calculated. Based on the calculated length and coordinate parameters, simulation is performed using a simulation model to further screen the length and coordinate parameters, resulting in a set of target parameters. Finally, the parameter combination with the shortest total length is selected as the design parameter. This method can calculate the optimal turnout alignment.

The application provides a high-speed maglev traction control system and a redundancy switching method thereof. The system comprises a traction control unit, at least one sensing unit, at least one high-frequency execution control unit, at least one medium-low-frequency execution control unit, at least one high-frequency actuator and at least one medium-low-frequency actuator. The traction control unit is used for sending high-frequency control instructions to the high-frequency execution control unit and sending medium-low-frequency control instructions to the medium-low-frequency execution control unit, and is also used for sending sensor data, high-frequency control instructions, medium-low-frequency control instructions, a pulse heartbeat signal of the traction control unit itself, high-frequency state information and medium-low-frequency state information to a traction controller without control sovereignty. The sensing unit is used for sending sensor data to the traction control unit. The high-frequency execution control unit is used for generating high-frequency execution instructions. The medium-low-frequency execution control unit is used for generating medium-low-frequency execution instructions. The high-frequency actuator is used for executing corresponding actions. The medium-low-frequency actuator is used for executing corresponding actions.

The application provides a low-vacuum pipeline magnetic suspension system superconducting linear motor stator module heat dissipation method, which comprises the following steps: monitoring the temperature rise of the stator winding, lifting the vacuum degree in the vacuum pipeline to a certain extent when the temperature rise of the winding exceeds the early warning temperature, closing the re-pressurizing valve when the air pressure reaches the preset value, spraying the cooling water of the preset temperature on the surface of the stator module and the bottom series cable by the pipeline spraying system, restoring the air pressure in the vacuum pipeline to the normal low-vacuum state after the spraying is completed, ensuring that the cooling water can completely boil and phase change to absorb heat, monitoring the temperature drop amplitude of the stator module in single heat dissipation, and repeating the above cycle if the stator winding in the whole heat dissipation interval is not completely reduced to the preset temperature after single heat dissipation. The technical scheme of the application solves the technical problems of high cost, many joints, low reliability, large eddy current, high magnetic resistance and inability to directly dissipate heat for the cable caused by the continuous laying of the water-cooled plate in the prior art.

A lateral stabilization device and its control method for a maglev train include at least two lateral stabilization units. Each lateral stabilization unit includes a first hydraulic cylinder located at the end of the suspension frame and a second hydraulic cylinder located in the middle of the suspension frame. The first and second hydraulic cylinders have identical structures, including a cylinder body, two movable ends, and two oil inlets. The cylinder body is fixedly connected to the vehicle body, and the two movable ends are rotatably connected to a pair of parallel sliding platforms in two suspension frame assemblies. All oil inlets of the two hydraulic cylinders are connected in series to form a circuit, and a solenoid valve is connected between the oil inlets of the two hydraulic cylinders. The ratio of the cross-sectional area of ​​the oil chamber of the first hydraulic cylinder to that of the second hydraulic cylinder is equal to the ratio of the displacement of the second sliding platform to that of the first sliding platform. Compared with the prior art, this invention enables the pose of each suspension frame unit to fit along the curve when the vehicle passes through a small curve, thereby greatly improving the vehicle's curve-passing capability.

This invention discloses a levitation control method, equipment, and medium for conventional maglev trains, belonging to the field of maglev transportation control technology. The method constructs a control framework based on a dynamic model of the levitation system and introduces an online residual estimation and compensation mechanism to compensate for track irregularities, aerodynamic disturbances, and unmodeled dynamics under complex operating conditions. A lightweight data-driven model obtained through cloud-based large-scale model knowledge distillation is deployed in the onboard edge computing unit to model the temporal characteristics of system state, track features, and external environmental information, estimating disturbance residuals in real time and generating compensating control quantities that are superimposed on the control input. Simultaneously, the cloud continuously optimizes model parameters based on historical operating data and issues updates, achieving iterative optimization of the control strategy. This invention can significantly improve the stability, dynamic response performance, and operational safety of the maglev train levitation system under high-speed operating conditions.