Contextual Mixture of Experts: Integrating Knowledge into Predictive Modeling

TL;DR

This paper introduces the Contextual Mixture of Experts (cMoE), a model that incorporates process knowledge into predictive modeling to enhance accuracy and interpretability in industrial applications.

Contribution

The paper presents a novel cMoE model that explicitly integrates process knowledge during learning, improving predictive performance and interpretability in process industry applications.

Findings

Improved predictive accuracy in quality prediction tasks.

Enhanced interpretability through insights into process variables.

Effective modeling of different operational contexts.

Abstract

This work proposes a new data-driven model devised to integrate process knowledge into its structure to increase the human-machine synergy in the process industry. The proposed Contextual Mixture of Experts (cMoE) explicitly uses process knowledge along the model learning stage to mold the historical data to represent operators' context related to the process through possibility distributions. This model was evaluated in two real case studies for quality prediction, including a sulfur recovery unit and a polymerization process. The contextual mixture of experts was employed to represent different contexts in both experiments. The results indicate that integrating process knowledge has increased predictive performance while improving interpretability by providing insights into the variables affecting the process's different regimes.