TechRxiv
DDCLS[HTC+ZFP+OD+YLW+BH](20220121).pdf (1.51 MB)
Download file

A Segmental Autoencoder-based Fault Detection for Nonlinear Dynamic Systems: An Interpretable Learning Framework

Download (1.51 MB)
preprint
posted on 01.02.2022, 03:00 by Hongtian ChenHongtian Chen, Zhuofu Pan, Oguzhan Dogru, Yalin Wang, Biao Huang
This paper presents a segmental autoencoder-based fault detection (FD) framework for nonlinear dynamic systems. The basic idea behind the proposed FD scheme is to identify a generalized kernel representation based on the representation knowledge learned from an autoencoder. By using the system data, several cascades, linking nonlinear operators, are employed to obtain a data-based model which describes the nonlinear dynamic behaviors. With the help of the segmental structure of an autoencoder, a residual generator is then constructed. Rigorous mathematical analysis and an application on a continuous stirred tank reactor demonstrate the effectiveness of the proposed FD method.

Funding

Natural Sciences and Engineering Research Council of Canada

History

Email Address of Submitting Author

hongtian.chen@ieee.org

ORCID of Submitting Author

0000-0002-8600-9668

Submitting Author's Institution

University of Alberta

Submitting Author's Country

Canada

Usage metrics

Licence

Exports