A Causal-based Framework for Multimodal Multivariate Time Series Validation Enhanced by Unsupervised Deep Learning as an Enabler for Industry 4.0
This work addresses validation challenges for Industry 4.0 by providing a framework to improve data quality and anomaly detection in industrial processes, though it appears incremental as it builds on existing methods like autoencoders and causal discovery.
The paper tackles the problem of validating multimodal multivariate time series in industrial processes by proposing a framework that uses unsupervised deep learning for anomaly detection and causal discovery to exclude biased data and uncover unknown causal relations. It successfully evaluates a Long Short-Term Memory Autoencoder on blast furnace data, identifying a research roadmap for combining causal discovery and representation learning to enable unsupervised root cause analysis.
An advanced conceptual validation framework for multimodal multivariate time series defines a multi-level contextual anomaly detection ranging from an univariate context definition, to a multimodal abstract context representation learnt by an Autoencoder from heterogeneous data (images, time series, sounds, etc.) associated to an industrial process. Each level of the framework is either applicable to historical data and/or live data. The ultimate level is based on causal discovery to identify causal relations in observational data in order to exclude biased data to train machine learning models and provide means to the domain expert to discover unknown causal relations in the underlying process represented by the data sample. A Long Short-Term Memory Autoencoder is successfully evaluated on multivariate time series to validate the learnt representation of abstract contexts associated to multiple assets of a blast furnace. A research roadmap is identified to combine causal discovery and representation learning as an enabler for unsupervised Root Cause Analysis applied to the process industry.