Anomaly Detection for Multivariate Time Series on Large-scale Fluid Handling Plant Using Two-stage Autoencoder

被引:6
作者
Naito, Susumu [1 ]
Taguchi, Yasunori [1 ]
Nakata, Kouta [1 ]
Kato, Yuichi [1 ]
机构
[1] Toshiba Co Ltd, Corp R&D Ctr, Kawasaki, Kanagawa, Japan
来源
21ST IEEE INTERNATIONAL CONFERENCE ON DATA MINING WORKSHOPS ICDMW 2021 | 2021年
关键词
anomaly detection; multivariate time series; neural networks; autoencoders; unsupervised learning;
D O I
10.1109/ICDMW53433.2021.00072
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
This paper focuses on anomaly detection for multivariate time series data in large-scale fluid handling plants with dynamic components, such as power generation, water treatment, and chemical plants, where signals from various physical phenomena are observed simultaneously. In these plants, the need for anomaly detection techniques is increasing in order to reduce the cost of operation and maintenance, in view of a decline in the number of skilled engineers and a shortage of manpower. However, considering the complex behavior of high-dimensional signals and the demand for interpretability, the techniques constitute a major challenge. We introduce a Two-Stage AutoEncoder (TSAE) as an anomaly detection method suitable for such plants. This is a simple autoencoder architecture that makes anomaly detection more interpretable and more accurate, in which based on the premise that plant signals can be separated into two behaviors that have almost no correlation with each other, the signals are separated into long-term and short-term components in a stepwise manner, and the two components are trained independently to improve the inference capability for normal signals. Through experiments on two publicly available datasets of water treatment systems, we have confirmed the high detection performance, the validity of the premise, and that the model behavior was as intended, i.e., the technical effectiveness of TSAE.
引用
收藏
页码:542 / 551
页数:10
相关论文
共 23 条
[1]  
Angiulli F., 2002, Principles of Data Mining and Knowledge Discovery. 6th European Conference, PKDD 2002. Proceedings (Lecture Notes in Artificial Intelligence Vol.2431), P15
[2]   USAD : UnSupervised Anomaly Detection on Multivariate Time Series [J].
Audibert, Julien ;
Michiardi, Pietro ;
Guyard, Frederic ;
Marti, Sebastien ;
Zuluaga, Maria A. .
KDD '20: PROCEEDINGS OF THE 26TH ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY & DATA MINING, 2020, :3395-3404
[3]  
Chalapathy R., 2019, ARXIV190103407
[4]   A Multimodal Anomaly Detector for Robot-Assisted Feeding Using an LSTM-Based Variational Autoencoder [J].
Park D. ;
Hoshi Y. ;
Kemp C.C. .
IEEE Robotics and Automation Letters, 2018, 3 (03) :1544-1551
[5]  
Filonov P., 2016, MULTIVARIATE IND TIM, P1
[6]   A Dataset to Support Research in the Design of Secure Water Treatment Systems [J].
Goh, Jonathan ;
Adepu, Sridhar ;
Junejo, Khurum Nazir ;
Mathur, Aditya .
CRITICAL INFORMATION INFRASTRUCTURES SECURITY (CRITIS 2016), 2018, 10242 :88-99
[7]  
Goodfellow IJ, 2014, ADV NEUR IN, V27, P2672
[8]  
Guo Y., 2018, P AS C MACH LEARN, P97
[9]   Outlier Detection for Temporal Data: A Survey [J].
Gupta, Manish ;
Gao, Jing ;
Aggarwal, Charu C. ;
Han, Jiawei .
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2014, 26 (09) :2250-2267
[10]  
Heras JM, 2014, AI MAG, V35, P37