Integration of first-principle models and machine learning in a modeling framework: An application to flocculation

Nima Nazemzadeh, Alina Anamaria Malanca, Rasmus Fjordbak Nielsen, Krist V. Gernaey, Martin Peter Andersson, Seyed Soheil Mansouri*

*Corresponding author for this work

Research output: Contribution to journalJournal articleResearchpeer-review

Abstract

In this paper, an integrated hybrid modeling approach with first-principles is implemented to model a flocculation process. The application of the framework is demonstrated through a laboratory-scale flocculation case of silica particles in water. In this modeling framework, it is demonstrated that the integration of first-principles models and machine-learning approaches accurately predicts the dynamics of the system. The first-principles model used in this study incorporates a population balance and mass balance models combined with the kinetic expressions of the agglomeration and breakage phenomena. The prediction of such modeling framework is compared with a fully first-principles model, and moreover with a hybrid model that was developed in a prior work, which used a population balance model as the first principles model and a deep learning algorithm for the determination of the flocculation kinetic parameters.
Original languageEnglish
Article number116864
JournalChemical Engineering Science
ISSN0009-2509
DOIs
Publication statusAccepted/In press - 2021

Keywords

  • Hybrid modeling
  • Machine learning
  • Flocculation
  • Mechanistic model
  • Population balance model

Fingerprint

Dive into the research topics of 'Integration of first-principle models and machine learning in a modeling framework: An application to flocculation'. Together they form a unique fingerprint.

Cite this