skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Deep anomaly detection for industrial systems: a case study

Abstract

We explore the use of deep neural networks for anomaly detection of industrial systems where the data are multivariate time series measurements. We formulate the problem as a self-supervised learning where data under normal operation are used to train a deep neural network autoregressive model, i.e., use a window of time series data to predict future data values. The aim of such a model is to learn to represent the system dynamic behavior under normal conditions, while expect higher model vs. measurement discrepancies under faulty conditions. In real world applications, many control settings are discrete in nature. In this paper, vector embedding and joint losses are employed to deal with such situations. Both LSTM and CNN based deep neural network backbones are studied on the Secure Water Treatment (SWaT) testbed datasets. Also, Support Vector Data Description (SVDD) method is adapted to such anomaly detection settings with deep neural networks. Evaluation methods and results are discussed based on the SWaT dataset along with potential pitfalls.

Authors:
; ; ; ;
Publication Date:
Research Org.:
GE Research
Sponsoring Org.:
USDOE Office of Fossil Energy (FE)
OSTI Identifier:
1717878
Report Number(s):
DOE-GR-FE0031763-1
DOE Contract Number:  
FE0031763
Resource Type:
Conference
Resource Relation:
Conference: THE ANNUAL CONFERENCE OF THE PHM SOCIETY 2020 Virtual Conference November 9 – 13, 2020
Country of Publication:
United States
Language:
English
Subject:
anomaly detection, deep neural network

Citation Formats

Xue, Feng, Yan, Weizhong, Wang, Tianyi, Huang, Hao, and Feng, Bojun. Deep anomaly detection for industrial systems: a case study. United States: N. p., 2020. Web. doi:10.36001/phmconf.2020.v12i1.1186.
Xue, Feng, Yan, Weizhong, Wang, Tianyi, Huang, Hao, & Feng, Bojun. Deep anomaly detection for industrial systems: a case study. United States. https://doi.org/10.36001/phmconf.2020.v12i1.1186
Xue, Feng, Yan, Weizhong, Wang, Tianyi, Huang, Hao, and Feng, Bojun. 2020. "Deep anomaly detection for industrial systems: a case study". United States. https://doi.org/10.36001/phmconf.2020.v12i1.1186. https://www.osti.gov/servlets/purl/1717878.
@article{osti_1717878,
title = {Deep anomaly detection for industrial systems: a case study},
author = {Xue, Feng and Yan, Weizhong and Wang, Tianyi and Huang, Hao and Feng, Bojun},
abstractNote = {We explore the use of deep neural networks for anomaly detection of industrial systems where the data are multivariate time series measurements. We formulate the problem as a self-supervised learning where data under normal operation are used to train a deep neural network autoregressive model, i.e., use a window of time series data to predict future data values. The aim of such a model is to learn to represent the system dynamic behavior under normal conditions, while expect higher model vs. measurement discrepancies under faulty conditions. In real world applications, many control settings are discrete in nature. In this paper, vector embedding and joint losses are employed to deal with such situations. Both LSTM and CNN based deep neural network backbones are studied on the Secure Water Treatment (SWaT) testbed datasets. Also, Support Vector Data Description (SVDD) method is adapted to such anomaly detection settings with deep neural networks. Evaluation methods and results are discussed based on the SWaT dataset along with potential pitfalls.},
doi = {10.36001/phmconf.2020.v12i1.1186},
url = {https://www.osti.gov/biblio/1717878}, journal = {},
number = ,
volume = ,
place = {United States},
year = {Fri Nov 13 00:00:00 EST 2020},
month = {Fri Nov 13 00:00:00 EST 2020}
}

Conference:
Other availability
Please see Document Availability for additional information on obtaining the full-text document. Library patrons may search WorldCat to identify libraries that hold this conference proceeding.

Save / Share: