Overview

The inverse identification of population balance equations (PBEs) for particulate systems remains a long-standing challenge in chemical engineering. Traditional inverse design approaches are often ill-posed due to their reliance on specific data characteristics, while neural network surrogates lack physical interpretability.

To address this gap, the Multi-Dimensional Breakage Population Balance Equation Identification (mPBE-ID) algorithm, developed by the speaker, integrates breakage-informed constrained sparse regression to efficiently extract breakage PBEs from a library of candidate functions. This approach yields sparse, interpretable models that explicitly describe particulate fragmentation. The speaker demonstrates that leveraging sparse regression provides a robust strategy for extracting mechanistic insights via equation discovery, with potential for extension across diverse engineering systems.

Speaker

Janice Leong Suet Lin, PhD Graduate, Monash University Malaysia

Janice is a PhD graduate in chemical engineering with a passion for applying mathematics and computational modelling to uncover insights in science and engineering. Her research focuses on population balance modelling of particulate systems. In particular, her doctoral work centres on discovering the underlying phenomenological laws governing particulate breakage directly from data, enabling a mechanistic understanding of how particle size and shape distributions evolve over time.

Her work represents a paradigm shift in addressing the inverse problem of inferring multi-dimensional breakage population balance equations from data, with important implications for the optimization and control of particulate fragmentation systems. More broadly, her research demonstrates the potential for these techniques to be extended beyond particulate systems to a wide range of engineering application.

The material presented has not been peer-reviewed. Any opinions are the presenter’s own and do not necessarily represent those of IChemE or the CAPE Special Interest Group. The information is given in good faith but without any liability on the part of IChemE.

Time

10:00–11:00 BST.

Software

The presentation will be delivered via Microsoft Teams. We recommend downloading the app from the Microsoft website, rather than using the web portal.