Monitoring of a Dynamic System Based on Autoencoders

Monitoring of a Dynamic System Based on Autoencoders

Aomar Osmani, Massinissa Hamidi, Salah Bouhouche

Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence
Main track. Pages 1836-1843. https://doi.org/10.24963/ijcai.2019/254

Monitoring industrial infrastructures are undergoing a critical transformation with industry 4.0.  Monitoring solutions must follow the system behavior in real time and must adapt to its continuous change. We propose in this paper an autoencoder model-based approach for tracking abnormalities in industrial application. A set of sensors collects data from turbo-compressors and an original two-level machine learning LSTM autoencoder architecture defines a continuous nominal vibration model. Normalized thresholds (ISO 20816) between the model and the system generates a possible abnormal situation to diagnose. Experimental results, including hyper-parameter optimization on large real data and domain expert analysis, show that our proposed solution gives promising results. 
Keywords:
Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
Machine Learning: Time-series;Data Streams
Multidisciplinary Topics and Applications: Real-Time Systems
Machine Learning Applications: Other Applications
Machine Learning Applications: Applications of Unsupervised Learning