Data-driven fault detection and isolation of nonlinear systems using deep learning for Koopman operator
Author | Bakhtiaridoust, M. |
Author | Yadegar, Meysam |
Author | Meskin, Nader |
Available date | 2023-03-29T11:31:39Z |
Publication Date | 2023-03-01 |
Publication Name | ISA Transactions |
Identifier | http://dx.doi.org/10.1016/j.isatra.2022.08.030 |
Citation | Bakhtiaridoust, M., Yadegar, M., & Meskin, N. (2022). Data-driven fault detection and isolation of nonlinear systems using deep learning for Koopman operator. ISA transactions. |
ISSN | 00190578 |
Abstract | This paper proposes a data-driven actuator fault detection and isolation approach for the general class of nonlinear systems. The proposed method uses a deep neural network architecture to obtain an invariant set of basis functions for the Koopman operator to form a linear Koopman predictor for a nonlinear system. Then, the obtained linear model is used for fault detection and isolation purposes without relying on prior knowledge about the underlying dynamics. Moreover, a recursive method is proposed for fault detection and isolation that is entirely data-driven with the key feature of global validity for the system's whole operating region due to the Koopman operator's global characteristic. Finally, the approach's efficacy is demonstrated using two simulations on a coupled nonlinear system and a two-link manipulator benchmark. |
Language | en |
Publisher | ISA - Instrumentation, Systems, and Automation Society |
Subject | Data-driven Deep learning Dynamic mode decomposition Fault detection and isolation Koopman operator Model-free Neural network Recursive fault detection |
Type | Article |
Volume Number | 134 |
Check access options
Files in this item
Files | Size | Format | View |
---|---|---|---|
There are no files associated with this item. |
This item appears in the following Collection(s)
-
Electrical Engineering [2611 items ]