Actuator and sensor fault diagnosis of nonlinear dynamic systems via genetic neural networks and adaptive parameter estimation technique

This paper presents a novel approach to the fault detection and diagnosis of actuators and sensors in nonlinear systems. First, a known nonlinear system is considered, where an adaptive diagnostic model incorporating the estimate of the fault is constructed. The diagnostic algorithm is then developed to minimise the possible modelling error. Furthermore, unknown nonlinear systems are studied and a feedforward neural network trained to estimate the system under healthy conditions. Genetic algorithms is proposed as a means of optimising the weighting connections of neural network and to assist the diagnosis of the fault.