Online fault accommodation control using cerebellar model articulation controller

摘要

This paper presents a learning approach using cerebellar model articulation controller (CMAC) to accommodate faults for a class of multivariable nonlinear systems. A CMAC with Gaussian-type receptive-field basis function is proposed to estimate the unknown fault. Then, an adaptive fault accommodation scheme is derived based on Lyapunov function, so that the proposed control system can accommodate the faults with desired system stability. Finally, the proposed fault accommodation system is applied to an engine system and a tank control system. Simulation results show that the proposed design method can effectively achieve the fault accommodation for these systems.