A neuro-fuzzy based sensor and actuator fault estimation scheme for unknown nonlinear systems

In this paper, a new approach for sensor and actuator fault detection and estimation in unknown nonlinear systems is proposed. Model-free structure and no a priori knowledge about the faults are two main properties of the proposed method that make it a viable candidate for real-time applications. First, a neuro-fuzzy technique is used to obtain a nominal models of the system based on input-output data in normal system operation. Actuator and sensor faults are then estimated such that the error between the output of the model and the actual output is minimized. The gradient descent method is used to update the fault estimated values. The estimated values are subsequently used for fault accommodation. Simulation results for a two link planar robot manipulator are presented to demonstrate the effectiveness of the proposed approach.