The running environment of a magnetic levitation (maglev) vehicle is complex, with problems such as track irregularity, external disturbance, varying system parameters, and time delays, which bring great challenges to the design of a high-performance levitation controller. In this article, an adaptive neural network controller with input delay compensation and a control parameter optimization scheme is proposed for the electromagnetic levitation system of a maglev vehicle, which can solve the key engineering problems of external disturbance, input time delay, and time-varying mass. Aiming at the problem of input time delay, a sliding-mode surface with time-delay compensation is constructed, and a double-layer neural network and adaptive law are utilized to approximate the uncertain dynamics; thus, a finite time adaptive tracking control law is proposed. Based on the Lyapunov method, the stability of the proposed controller in finite time is analyzed. The proposed method does not only update the input and output weights of the neural network online, but also introduces reinforcement learning (Actor–Critic network) to optimize the key controller parameter in real time and enhance system robustness. Simulation and experimental results show that the proposed controller can effectively suppress the air gap vibration with time delay and uncertain dynamics, and significantly improve the performance of levitation control.
The suspension system of maglev vehicle needs strong robustness and anti-jamming ability in the process of operation and fluctuation control. In order to solve the open-loop instability and strong nonlinearity of the mechanical equation of the suspension system of Maglev vehicle, the non-linear dynamic equation is established. At present, the research based on single electromagnet and rigid track is the most common. However, based on this method, it is impossible to study the coupled vibration caused by track factors. Therefore, based on the dynamic equation of a single span simply supported beam of flexible track and the non-linear equation of the suspended electromagnet itself, an overall control model is needed to discuss the control strategy. Based on this dynamic model, the singularities of the system are solved according to Hurwitz criterion, and the characteristic equation corresponding to Jacobian matrix is obtained. The stability analysis shows that the system is unstable. At the same time, the necessity of using feedback control method to control air gap has been proved. On this basis, a sliding mode adaptive state feedback controller for maglev system is designed based on RBF network approximation principle. The corresponding simulation and experimental results are given. The simulation and experimental results show that the controller can ensure the vehicle's stable suspension and effectively suppress external interference. Compared with the traditional PID and fuzzy controllers, the controller can guarantee faster dynamic response, stronger robustness and smaller overshoot while considering the flexible track and external disturbances.
29 June 2022 in IEEE Transactions on Instrumentation and Measurement
In a smartphone, the global navigation satellite system (GNSS) receiver is dominant in providing position information for users. However, GNSS signals are vulnerable to the environment, i.e., city canyons and tunnels. Pedestrian dead reckoning (PDR) exploring human walking gaits is another effective method to determine pedestrian position. Accelerometers and gyroscope sensors are available in smartphones to detect pedestrians’ steps and carry out PDR. Aiming to improve smartphone position accuracy, we propose two different factor graph optimization (FGO)-PDR/GNSS integration models. First, the position from PDR and GNSS is integrated using FGO. Second, given the negative influences of the heading angle errors and the inconsistency between a smartphone and the pedestrian walking direction, PDR step length and GNSS are integrated using FGO. Android smartphones were utilized to collect different datasets and evaluate the proposed methods; experimental results indicated the superior performance of the proposed methods.
18 January 2022 in IEEE Transactions on Transportation Electrification
In order to ensure the suspension stability of maglev train, the active control problems of static suspension and dynamic suspension are studied. First, the mathematical model of dynamic suspension characteristics of medium- and low-speed maglev train is established. Second, the PID controller is studied. The results show that the controller is very sensitive to time-varying disturbances such as nonuniformity and load, which leads to the decrease in system robustness. In order to suppress the disturbance effectively, a suspension control method based on the sliding mode reaching law is proposed. Based on the bifurcation phenomenon, the bifurcation point is solved to determine the main control parameters. On the basis of this, an acceleration feedback correction and adaptive control module based on the radial basis function (RBF) network is constructed to effectively suppress the vibration of the electromagnet. The controller consists of a sliding mode bifurcation control law, an acceleration feedback correction module, and an adaptive compensation loop. The simulation and experimental results show that the proposed control algorithm can significantly reduce the variation range of suspension gap with a smoother control current in the presence of complex disturbances and significantly suppress the coupled vibration.
11 January 2022 in IEEE Transactions on Vehicular Technology
Maglev train is a new vehicle of rail transit. The time-varying load caused by large capacity is an important test of suspension system. If the state variable matrix and parameter matrix caused by time-varying mass cannot be estimated effectively, it is very likely to lead to the decline of suspension performance and instability. Firstly, an NNs state observer based on neural network is proposed to effectively estimate the system state and parameter matrix. Secondly, based on the NNs observer model, an inverse control algorithm with stronger regulation ability is designed by integrating the output limited characteristics and Lyapunov function, which can ensure the stability of the system when disturbed. The simulation results show that the control algorithm proposed in this paper can have faster response speed and stability in the flotation process of 16mm-10mm, and has better anti-disturbance ability in the face of time-varying mass disturbance. Finally, based on the single point suspension experimental platform, the effectiveness and practicability of the proposed control algorithm are verified, and the correctness of the proposed NNs observer model is also verified.