The magnetic suspension system of a low-speed maglev train is presented in this paper. The design and realization of the magnetic suspension controller are discussed, and a nonlinear mathematical model of the magnetic suspension system is built. Then, the proportion integration differentiation controller is investigated, which indicates that it is sensitive to disturbances. To reject the disturbance and parameter perturbations, an adaptive neural-fuzzy sliding mode controller is presented, which employs a sliding mode control, adaptive-fuzzy approximator, and the neural-fuzzy switching law. The sufficient simulation and experimental results are included to demonstrate that the presented robust controller significantly reduces the impact of the disturbance and parameter perturbations with a smooth control current.

Adaptive Neural-Fuzzy Robust Position Control Scheme for Maglev Train Systems With Experimental Verification

Adaptive sliding mode control of maglev system based on RBF neural network minimum parameter learning method

The maglev rail transit has entered a rapid development stage. In order to prevent potential safety hazards in the operation of maglev train, the related monitoring technology needs to be studied urgently. In this article, in view of the wide application of the Internet of Things (IoT) in intelligent transportation, a new method for realizing suspension control for medium-low-speed maglev trains using the IoT and an adaptive fuzzy controller is proposed. First, a mathematical model of the suspension system of medium-low-speed maglev trains is established. Then, the basic composition of the IoT and the circuit design of the key components of maglev trains are introduced. On this basis, an improved Apriori algorithm is used to extract the stored historical database and establish a trusted database. Then, according to the data of the trusted database, the suspension airgap control law is extracted, and the adaptive fuzzy rules of the maglev train suspension system are determined. An improved adaptive suspension controller is designed. Finally, the effectiveness of the method is verified by experiments utilizing a full-scale maglev train.

Internet of Things-Based Online Condition Monitor and Improved Adaptive Fuzzy Control for a Medium-Low-Speed Maglev Train System

The vertical security problem of maglev train is challenging for nonlinearity, external disturbances, unmeasurable airgap velocity and constrained output. To solve this problem, a semi-supervised controller based on deep belief network (DBN) algorithm is proposed in the presence of unknown external disturbances. Firstly, the extended state observer (ESO) is designed to ensure fast convergence of observation errors with high enough estimation precision. An output-constrained controller is designed by backstepping method, and the estimated value of ESO is introduced to ensure that the output airgap is constrained within a bounded range. Then, the stability of this method is proved based on the symmetric Barrier Lyapunov function. Subsequently, a semi-supervised controller is presented based on DBN algorithm and the output-constrained controller. The numerical simulation results show that this method can effectively deal with unmeasurable airgap velocity and generalized external disturbances, and guarantee the vertical security with output airgap within a bounded range. Finally, experiments are implemented on a full-scale maglev vehicle and the experimental results demonstrate that the developed deep learning controller can ensure the vertical security.

Deep Learning Based Semi-Supervised Control for Vertical Security of Maglev Vehicle With Guaranteed Bounded Airgap

In order to asymptotically track the desired trajectory of nonlinear systems with unidirectional control input under various uncertainties, a modified saturated learning-based control law with adaptive notch filter (ANF) is presented in this paper. The proposed control law ensures the asymptotic convergence of the tracking error by utilizing a saturated function and a repetitive learning-based estimator, which allows the learning of the periodic dynamic behavior of the nonlinear system online to make compensations. Simultaneously, an ANF is integrated with the proposed control law to estimate the frequency of the periodic dynamics online. Differing from the existing methodologies in the literatures, the control law proposed in this paper only requires the unknown dynamics be bounded (the parameters, structure, and period of the unknown dynamics is not required to be known). Finally, applying the proposed control law to the electromagnetic suspension system, simulation, and experimental results are included to demonstrate the effectiveness of the proposed method.

Modified repetitive learning control with unidirectional control input for uncertain nonlinear systems

Fuzzy H ∞ robust control for magnetic levitation system of maglev vehicles based on T-S fuzzy model: Design and experiments

The electromagnet levitation system (ELS) of low-speed maglev train is taken as the research object. The nonlinear dynamics and control law of ELS are discussed. Specifically, by employing the Euler-Lagrange’s method, a nonlinear dynamic model is constructed for the single-ELS. Then, the linear control law is studied, which has a disadvantage of weak robustness. To improve the performance of the controller, a fuzzy sliding-mode control law is proposed. According to the dynamic nonlinear model, a novel sliding surface which can make the system reach the stable point within the finite time is presented. Moreover, the fuzzy inference method is utilized to slow down the speed of the states crossing the sliding surface. The simulation results demonstrate that the global robustness of external disturbance and parameter perturbation can be achieved through the proposed control law. And the chattering phenomenon can be reduced significantly. Finally, the experiments are also implemented to examine its practical dynamic performance of the proposed control law.

/pdf/nonlinear-dynamic-modeling-and-fuzzy-sliding-mode-4aabskw4s6.pdf

Nonlinear dynamic modeling and fuzzy sliding-mode controlling of electromagnetic levitation system of low-speed maglev train

The maglev vehicle is becoming a new type of urban transport because of its short turning radius, comfortable and environmental characteristics. In this paper, the multi-point suspension system of maglev train is studied, and the correlative cooperative control law is proposed to solve the problem that the multi-coils cannot be effectively decoupled. Firstly, a current feedback model of single coil maglev system is established. On this basis, the relative errors between multi-coils are determined, and the cross-coupling control strategy is adopted to coordinate the coil output effectively. Finally, the validity of the control law is verified based on the platform of MATLAB/Simulink. It provides an effective way to solve the output asynchronism of multi-point suspension system without complete decoupling.

Chen Chen

Papers

Adaptive sliding mode control of maglev system based on RBF neural network minimum parameter learning method

Fuzzy H ∞ robust control for magnetic levitation system of maglev vehicles based on T-S fuzzy model: Design and experiments

Nonlinear dynamic modeling and fuzzy sliding-mode controlling of electromagnetic levitation system of low-speed maglev train

Multi Point Suspension Cooperative Modeling and Control of Low Speed Maglev Vehicle