Multi-head CNN–RNN for multi-time series anomaly detection: An industrial case study

Canizo, Mikel; Triguero, Isaac; Conde, Angel; Onieva, Enrique

Abstract

Detecting anomalies in time series data is becoming mainstream in a wide variety of industrial applications in which sensors monitor expensive machinery. The complexity of this task increases when multiple heterogeneous sensors provide information of di_erent nature, scales and frequencies from the same machine. Traditionally, machine learning techniques require a separate data preprocessing before training, which tends to be very time-consuming and often requires domain knowledge. Recent deep learning approaches have shown to perform well on raw time series data, eliminating the need for pre-processing. In this work, we propose a deep learning based approach for supervised multitime series anomaly detection that combines a Convolutional Neural Network (CNN) and a Recurrent Neural Network (RNN) in different ways. Unlike other approaches, we use independent CNNs, so-called convolutional heads, to deal with anomaly detection in multi-sensor systems. We address each sensor individually avoiding the need for data pre-processing and allowing for a more tailored architecture for each type of sensor. We refer to this architecture as Multi-head CNN-RNN. The proposed architecture is assessed against a real industrial case study, provided by an industrial partner, where a service elevator is monitored. Within this case study, three type of anomalies are considered: point, context-specific, and collective. The experimental results show that the proposed architecture is suitable for multi-time series anomaly detection as it obtained promising results on the real industrial scenario.

Citation

Canizo, M., Triguero, I., Conde, A., & Onieva, E. (2019). Multi-head CNN–RNN for multi-time series anomaly detection: An industrial case study. Neurocomputing, 363, 246-260. https://doi.org/10.1016/j.neucom.2019.07.034

• Journal Article Type: Article
• Acceptance Date: Jul 14, 2019
• Online Publication Date: Jul 19, 2019
• Publication Date: Oct 21, 2019
• Deposit Date: Jul 17, 2019
• Publicly Available Date: Jul 20, 2020
• Journal: Neurocomputing
• Print ISSN: 0925-2312
• Electronic ISSN: 1872-8286
• Publisher: Elsevier
• Peer Reviewed: Peer Reviewed
• Volume: 363
• Pages: 246-260
• DOI: https://doi.org/10.1016/j.neucom.2019.07.034
• Keywords: Deep learning, Anomaly detection, Convolutional neural networks, Recurrent neural networks, Multi-sensor systems, Industry 4.0
• Public URL: https://nottingham-repository.worktribe.com/output/2315191
• Publisher URL: https://www.sciencedirect.com/science/article/pii/S0925231219309877?via%3Dihub
• Contract Date: Jul 17, 2019