Neuro-adaptive fault-tolerant control of high speed trains under traction-braking failures using self-structuring neural networks

Gao, Ruizhen; Wang, Yujuan; Lai, Junfeng; Gao, Hui

doi:10.1016/j.ins.2016.05.033

Cited by 40 publications

(19 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Section: Introductionmentioning

confidence: 99%

“…On the other hand, as the major problem affecting the operation of HSTs, actuator faults have been addressed in some effective fault-tolerant methods [6][7][8]. Gao et al [6] proposed an adaptive fault-tolerant control method based on self-organizing neural network to attenuate the effects of uncertainty and actuator faults on the train system. Liu et al [7] designed a piecewise time-varying model to describe the train dynamic model with variable parameters, and for the system with actuator failures, a fault-tolerant control scheme with adaptive backstepping was established to ensure the accurate position tracking of HSTs.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Adaptive Fault-Tolerant Sliding Mode Control for High-Speed Trains With Actuator Faults Under Strong Winds

Zhang

Kong

2020

IEEE Access

View full text Add to dashboard Cite

This paper addresses the fault-tolerant control problem for high-speed trains (HSTs) with actuator faults under strong winds. For the healthy system, a non-singular fast terminal sliding mode surface is introduced into the controller, which ensures the system fast converge to the equilibrium point with finite time, and the radial basis function neural network (RBFNN) with the adaptive compensation term of the error is used to approximate the unknown nonlinear disturbances of the train system in strong winds and predict the time delay generated in the train communication network. Through the RBFNN observer established specifically for actuator failures, the real effective factors are identified. Combining with the identified effective factors and predicted time delay, an adaptive fault-tolerant sliding mode control method is established for train systems. With dynamic parameters and position update strategy guided by negative gradient thought, an improved particle swarm optimization algorithm is proposed to optimize the uncertain parameters of control method, which weakens the chattering phenomenon from the sliding mode controller and improves the control accuracy. Simulation results show that the proposed method has better tracking performance and real-time performance compared with other fault-tolerant control methods under various operating conditions, which ensures the running safety of HSTs under different strong winds.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Adaptive Fault-Tolerant Sliding Mode Control for High-Speed Trains With Actuator Faults Under Strong Winds

Zhang

Kong

2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Song develops the fault-tolerant adaptive control strategy with virtual parameters-based approach [11]. Gao uses the self-structuring neural networks in the fault tolerant control for high speed trains [12]. Modern methods try to preserve the adhesion state at the optimal operation range to obtain the maximum adhesion utilization [13]- [15].…”

Section: Introductionmentioning

confidence: 99%

Adhesion Control of Heavy-Duty Locomotive Based on Axle Traction Control System

et al. 2019

View full text Add to dashboard Cite

The traction force of heavy-duty locomotive is reduced significantly and unable to fulfill the actual traction demand when the wheel slip phenomenon occurs. Aiming at this problem, an adhesion control method is proposed in this paper. The proposed method achieves online search of optimal traction torque based on adhesion coefficient-slip ratio relationship which is analyzed using Polach model. The optimal traction torque is the maximum torque which is operating under current wheel-rail condition without slip phenomenon. The proposed method detects wheel slip phenomenon by wheel slip velocity and wheel acceleration. Each axle in locomotive achieves individual traction torque adjustment by utilizing the advantage of axle control system. Considering the complexity of real heavy-duty locomotive, a co-simulation model is proposed by using MATLAB/Simulink to build the electric power circuit and control system as well as SIMPACK to build the locomotive mechanical system. The simulation is realized based on the StarSim real-time simulator platform and the experimental results verify the effectiveness of the proposed method. INDEX TERMS Adhesion control, axle traction control, heavy-duty locomotive, optimal traction torque.

show abstract

“…As a consequence, compensating for the faults is significant, and can be utilized in numerous systems . To now, there have been only a few scholars devoted to handling the problem of HSTs with actuator faults .…”

Section: Introductionmentioning

confidence: 99%

“…As a consequence, compensating for the faults is significant, and can be utilized in numerous systems [19,20]. To now, there have been only a few scholars devoted to handling the problem of HSTs with actuator faults [21][22][23]. Motivated by the current analysis, the main contribution is the design of a composite control scheme for HSTs subject to running resistance, ramp resistance, unknown gusts and actuator faults to handle with the tracking problem which is full of challenge.…”

Section: Introductionmentioning

confidence: 99%

Composite Disturbance‐Observer‐Based Control and Control for High Speed Trains with Actuator Faults

Dong

Lin

Yao

et al. 2017

Asian Journal of Control

View full text Add to dashboard Cite

To guarantee the position and velocity tracking performance of high speed trains (HSTs) with actuator faults, a composite control algorithm consisting of the disturbance‐observer‐based control (DOBC) and ℋ∞ control is proposed. Based on the multiple point‐mass model, the dynamics of HSTs is established by a cascade of carriages which are connected by flexible couplers, during the procedure of which, the running resistance, actuator faults and multiple disturbances are taken into account. The multiple disturbances are composed of two parts, one of which is the ramp resistance due to the track slope, the other is unknown gusts which can be modeled as a harmonic disturbance with time‐varying frequency. The unknown gusts is estimated and rejected via the DOBC methodology, meanwhile, the running resistance and the ramp resistance are attenuated by the ℋ∞ control methodology. According to the Lyapunov stability analysis and LMI‐based algorithms, main results are derived such that the closed‐loop system is asymptotically stable and the desired performance can be guaranteed. Compared with the numeral simulation results with the single ℋ∞ control method, it is demonstrated that the proposed control methodology is more effective and the system has a higher precision of position and velocity tracking.

show abstract

Neuro-adaptive fault-tolerant control of high speed trains under traction-braking failures using self-structuring neural networks

Cited by 40 publications

References 21 publications

Adaptive Fault-Tolerant Sliding Mode Control for High-Speed Trains With Actuator Faults Under Strong Winds

Adaptive Fault-Tolerant Sliding Mode Control for High-Speed Trains With Actuator Faults Under Strong Winds

Adhesion Control of Heavy-Duty Locomotive Based on Axle Traction Control System

Composite Disturbance‐Observer‐Based Control and Control for High Speed Trains with Actuator Faults

Contact Info

Product

Resources

About