Attention Mechanism for Multivariate Time Series Recurrent Model Interpretability Applied to the Ironmaking Industry

TL;DR

This paper introduces an interpretable LSTM-based deep learning model with attention mechanisms for multivariate time series forecasting of hot metal temperature in blast furnaces, enhancing interpretability and reducing prediction error.

Contribution

It develops a novel attention-enhanced LSTM architecture with guided backpropagation for local interpretability in industrial time series forecasting.

Findings

High potential for blast furnace data application

Provides accurate local interpretability of variables

Reduces prediction error compared to traditional RNNs

Abstract

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.