Explaining and Integrating Machine Learning Models with Rigorous Simulation

• Published in: Chemie ingenieur technik Vol. 93; no. 12; pp. 1998 - 2009
• Main Authors: Schöneberger, Jan C., Aker, Burcu, Fricke, Armin
• Format: Journal Article
• Language: English
• Published: 01.12.2021
• Subjects: Artificial neuronal network; Flowsheet simulation; Machine learning; Pre‐reformer reactor; Surrogate model
• ISSN: 0009-286X; 1522-2640
• DOI: 10.1002/cite.202100089

First‐principle flowsheet simulation is a reliable data resource for training machine learning (ML) models for process industry, especially when plant data is not available. Process simulators play an even more important role for evaluation and validation of ML models. In this work, we present a workflow for building and evaluating ML models based on data generated by a commercial flowsheet simulator. The resulting hybrid models, combining data‐driven predictions with mass and energy balances, have much lower calculation times than the rigorous models. The implementation of such models shows great potential for solving more complex process engineering problems on the high‐dimensional space in the future, while saving the process engineer's time in the present. We present a workflow for building and evaluating machine learning (ML) models based on data generated by rigorous simulation. For this purpose, the ML models are implemented in a flowsheet simulator as unit operations. These unit operations are hybrid models, combining data‐driven predictions with mass and energy balances.