A decentralized fault accommodation scheme for nonlinear interconnected systems

In this paper, a novel decentralized detection and accommodation (FDA) methodology is proposed for interconnected nonlinear continuous-time systems by using local subsystem states alone in contrast with traditional distributed FDA schemes where the entire measured or the estimated state vector is needed. First, the detection scheme is revisited where a network of local fault detectors (LFD) is proposed. A fault is detected by generating a residual from the measured and estimated state vectors locally and the fault dynamics are estimated by using an online approximator upon detection. Subsequently, a fault accommodation scheme is initiated in the subsystem by using a second online approximator to augment the control input of each subsystem in order to minimize the effects of the faults on the overall system. Decentralization avoids the transmission of the entire system state vector to each subsystem. Finally the proposed methods are verified in the simulation environment.