Attention Mechanism for Multivariate Time Series Recurrent Model Interpretability Applied to the Ironmaking Industry
This work addresses the need for interpretable AI to gain acceptance from process engineers in the ironmaking industry, though it is incremental as it builds on existing LSTM and attention methods.
The paper tackled the problem of making multivariate time series forecasting models interpretable for process engineers in the ironmaking industry, specifically predicting hot metal temperature in a blast furnace, and achieved reduced prediction error compared to a recurrent-based deep learning architecture.
Data-driven model interpretability is a requirement to gain the acceptance of process engineers to rely on the prediction of a data-driven model to regulate industrial processes in the ironmaking industry. In the research presented in this paper, we focus on the development of an interpretable multivariate time series forecasting deep learning architecture for the temperature of the hot metal produced by a blast furnace. A Long Short-Term Memory (LSTM) based architecture enhanced with attention mechanism and guided backpropagation is proposed to accommodate the prediction with a local temporal interpretability for each input. Results are showing high potential for this architecture applied to blast furnace data and providing interpretability correctly reflecting the true complex variables relations dictated by the inherent blast furnace process, and with reduced prediction error compared to a recurrent-based deep learning architecture.