TY  - EJOU
AU  - Lee, Byeongcheon 
AU  - Kim, Sangmin 
AU  - Maqsood, Muazzam 
AU  - Moon, Jihoon 
AU  - Rho, Seungmin 

TI  - Advancing Autoencoder Architectures for Enhanced Anomaly Detection in Multivariate Industrial Time Series
T2  - Computers, Materials \& Continua

PY  - 2024
VL  - 81
IS  - 1
SN  - 1546-2226

AB  - In the context of rapid digitization in industrial environments, how effective are advanced unsupervised learning models, particularly hybrid autoencoder models, at detecting anomalies in industrial control system (ICS) datasets? This study is crucial because it addresses the challenge of identifying rare and complex anomalous patterns in the vast amounts of time series data generated by Internet of Things (IoT) devices, which can significantly improve the reliability and safety of these systems. In this paper, we propose a hybrid autoencoder model, called ConvBiLSTM-AE, which combines convolutional neural network (CNN) and bidirectional long short-term memory (BiLSTM) to more effectively train complex temporal data patterns in anomaly detection. On the hardware-in-the-loop-based extended industrial control system dataset, the ConvBiLSTM-AE model demonstrated remarkable anomaly detection performance, achieving F1 scores of 0.78 and 0.41 for the first and second datasets, respectively. The results suggest that hybrid autoencoder models are not only viable, but potentially superior alternatives for unsupervised anomaly detection in complex industrial systems, offering a promising approach to improving their reliability and safety.
KW  - Advanced anomaly detection; autoencoder innovations; unsupervised learning; industrial security; multivariate time series analysis

DO  - 10.32604/cmc.2024.054826