Sensor Fault Detection and Isolation in Autonomous Nonlinear Systems Using Neural Network-Based Observers
This addresses sensor reliability issues in autonomous nonlinear systems, offering a robust solution for fault detection and isolation, though it is incremental as it builds on existing observer techniques.
The paper tackles sensor fault detection and isolation in nonlinear systems by developing a neural network-based observer method, achieving accurate fault identification with theoretical and empirical thresholds validated through simulations on Kuramoto oscillators.
This paper presents a novel observer-based approach to detect and isolate faulty sensors in nonlinear systems. The proposed sensor fault detection and isolation (s-FDI) method applies to a general class of nonlinear systems. Our focus is on s-FDI for two types of faults: complete failure and sensor degradation. The key aspect of this approach lies in the utilization of a neural network-based Kazantzis-Kravaris/Luenberger (KKL) observer. The neural network is trained to learn the dynamics of the observer, enabling accurate output predictions of the system. Sensor faults are detected by comparing the actual output measurements with the predicted values. If the difference surpasses a theoretical threshold, a sensor fault is detected. To identify and isolate which sensor is faulty, we compare the numerical difference of each sensor meassurement with an empirically derived threshold. We derive both theoretical and empirical thresholds for detection and isolation, respectively. Notably, the proposed approach is robust to measurement noise and system uncertainties. Its effectiveness is demonstrated through numerical simulations of sensor faults in a network of Kuramoto oscillators.