Output feedback actuator fault detection in nonlinear systems using neural networks

In this paper, a neural network-based scheme for actuator fault detection in unknown, input-affine, nonlinear systems is presented. Neural networks are used for observer design to approximate the unknown system functions. The nonlinear system is in a normal form where the system states are not assumed to be available, i.e., only the system output is available for measurement. Stable neural net tuning algorithms are proposed and a system identification scheme is designed using a Lyapunov-based approach. In the paper, the actuator-fault dynamics are analyzed and a rigorous detectability condition is given for actuator faults relating the actuator desired input signal, neural net-based observer sensitivity, and detectability time. Moreover, the issue of fault propagation through the system dynamics towards the measurable output is addressed and specific conditions under which such faults can be detected are proposed. Simulation results are presented to illustrate the effectiveness of the proposed technique.