Abstract

Abstract This paper considers the model-free adaptive fault-tolerant control for a subway train based on multiple point-mass model with the actuator fault under the constraints of speed and traction/braking force. The complex subway train model is first transformed into a compact form dynamic linearization (CFDL) data model with pseudo gradient (PG). The actuator fault function is approximated with radial basis function neural network (RBFNN). Finally a fault-tolerant controller only using saturated input/output (I/O) data is designed. The effectiveness of proposed controller is illustrated by a simulation.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call