Hybrid modelling of a batch separation process

Author(s): Ulderico Di Caprio, Min Wu, Furkan Elmaz, Yentl Wouters, Niels Vandervoort, Ali Anwar, Siegfried Mercelis, Steffen Waldherr, Peter Hellinckx, M. Enis Leblebici
Abstract: Applying machine learning (ML) techniques is a complex task when the data quality is poor. Integrating first-principle models and ML techniques, namely hybrid modelling significantly supports this task. This paper introduces a novel approach to developing a hybrid model for dynamic chemical systems. The case in analysis employs one first-principle structure and two ML-based predictors. Two training approaches (serial and parallel), two optimisers (particle swarm optimisation and differential evolution) and two ML functions (multivariate rational function and polynomial) are tested. The polynomial function trained with the differential evolution showed the most accurate and robust results. The training approach does not significantly affect the hybrid model accuracy. However, the main effect of the training approach is on the robustness of the parameter predictions. The coefficients of determination (R²) on the test batches are above 0.95. In addition, it showed satisfactory extrapolation capabilities on different production scales with R²>0.9.
Organisation(s): Functional and Evolutionary Ecology
External organisation(s): Katholieke Universiteit Leuven, University of Antwerp, Janssen Pharmaceutica NV
Journal: Computers and Chemical Engineering
Volume: 177
ISSN: 0098-1354
DOI: https://doi.org/10.1016/j.compchemeng.2023.108319
Publication date: 09-2023
Peer reviewed: Yes
Austrian Fields of Science 2012: 204003 Chemical process engineering, 102019 Machine learning
Keywords
ASJC Scopus subject areas: Chemical Engineering(all), Computer Science Applications
Portal url: https://ucris.univie.ac.at/portal/en/publications/hybrid-modelling-of-a-batch-separation-process(625864bc-db8e-4479-84c7-35caabf55204).html