Sensor Fault Detection and Isolation in Autonomous Nonlinear Systems Using Neural Network-Based Observers

TL;DR

This paper introduces a neural network-based observer method for detecting and isolating sensor faults in nonlinear systems, demonstrating robustness and effectiveness through simulations.

Contribution

It develops a novel neural network-based observer approach for sensor fault detection and isolation applicable to general nonlinear systems.

Findings

Effective detection of sensor faults using predicted vs. actual outputs

Successful isolation of faulty sensors through threshold comparison

Robust performance demonstrated in simulations with Kuramoto oscillators

Abstract

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.