Echo State Networks Based Data-Driven Adaptive Fault Tolerant Control With Its Application to Electromechanical System

This paper is concerned with the echo state networks (ESNs) based adaptive sensor fault detection mechanism and fault tolerant control (FTC) design approach for a class of multi-input single-output discrete-time model free systems in the data-based framework. The main feature of the paper is the novel realization of fault detection and estimation (FDE) and FTC for the considered systems. Because of the complexity of fault detection and FTC in practical industrial processes, it will cause more difficulties in the controller design and the stability analysis. Since the ESN has good ability of short-term memory, which means that the learning and training of ESN is faster than that of recurrent neural network, it is utilized to estimate the unknown sensor fault dynamics. After the fault is detected, the FTC strategy is calculated based on the ESN and optimality criterion. Then, it is proved that all the signals including tracking error are bounded. In the end, the feasibility of the developed FDE method and FTC scheme is verified by an example.