Model-Free Geometric Fault Detection and Isolation for Nonlinear Systems Using Koopman Operator

Mohammadhosein Bakhtiaridoust,Nader Meskin,Mohammad Noorizadeh,Meysam Yadegar

doi:10.1109/access.2022.3146417

Mohammadhosein Bakhtiaridoust, Nader Meskin + Show 2 more

Open Access

https://doi.org/10.1109/access.2022.3146417

Copy DOI

Abstract

This paper presents a model-free fault detection and isolation (FDI) method for nonlinear dynamical systems using Koopman operator theory and linear geometric technique. The key idea is to obtain a Koopman-based reduced-order model of a nonlinear dynamical system and apply the linear geometric FDI method to detect and isolate faults in the system. Koopman operator is an infinite-dimensional, linear operator which lifts the nonlinear dynamic data into an infinite-dimensional space where the correlations of dynamic data behave linearly. However, due to the infinite dimensionality of this operator, an approximation of the operator is needed for practical purposes. In this work, the Koopman framework is adopted toward nonlinear dynamical systems in combination with the linear geometric approach for fault detection and isolation. In order to demonstrate the efficacy of the proposed FDI solution, a mathematical nonlinear dynamical system, and an experimental three-tank setup are considered. Results show a remarkable performance of the proposed geometric Koopman-based fault detection and isolation (K-FDI) technique.

Highlights

T HE issues of reliability, operating safety, availability, and environmental protection concerns in modern control systems have become significantly important and received more attention during recent years since faults may result in irreparable consequences for the safe and efficient operation of the system
Fault detection evaluates whether a fault has occurred or the system is operating under a normal condition
Since the proper orthogonal decomposition is an Singular Value Decomposition (SVD)-based method, choosing the order of truncation is of great importance

Summary

Introduction

T HE issues of reliability, operating safety, availability, and environmental protection concerns in modern control systems have become significantly important and received more attention during recent years since faults may result in irreparable consequences for the safe and efficient operation of the system. This gives rise to demands for research on fault detection and isolation (FDI) approaches. The term "fault" means any unexpected deviation of system function that disturbs the system’s normal operation [1]. FDI methods can be broadly classified as model-based and model-free [3]

Methods

Results

Conclusion