Contextual Mixture of Experts: Integrating Knowledge into Predictive Modeling
This work addresses the need for better human-machine synergy in the process industry by making models more interpretable and effective, though it is incremental as it builds on existing mixture of experts methods.
The paper tackled the problem of integrating process knowledge into predictive models for industrial processes, resulting in increased predictive performance and improved interpretability in two real case studies.
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.