Data-driven Process Systems Engineering Lab

  • Home
  • Research
  • The Group
  • Fani Boukouvala
  • News
  • Publications
  • Tools
  • Gallery
  • Links

Research

  • Overview
  • Data-driven Optimization
  • Hybrid Modeling
  • Energy Systems
  • Manufacturing

Hybrid Modeling

Our aim is to develop new techniques to efficiently integrate modern data-analytics and machine learning techniques with chemical engineering fundamentals and first-principle modeling.

Relevant Publications

  1. Reduced-order Modeling
    • Machine learning-based surrogate modeling for data-driven optimization: a comparison of subset selection for regression techniques
    • Nonlinear Variable Selection Algorithms for Surrogate Modeling
    • Reduced order Discrete Element Method (DEM) modeling
    • Improving continuous powder blending performance using Projection to Latent Structures regression
    • Computational Approaches for Studying the Granular Dynamics of Continuous Blending Processes, 2 – Population Balance and Data-Based Methods
    • Dynamic Data-Driven Modeling of Pharmaceutical Processes

  2. Surrogate Modeling
    • Surrogate-Based Optimization for Mixed-Integer Nonlinear Problems
    • Machine learning-based surrogate modeling for data-driven optimization: a comparison of subset selection for regression techniques
    • Nonlinear Variable Selection Algorithms for Surrogate Modeling
    • Teaching data-analytics through process design
    • Surrogate-based optimization of expensive flowsheet models for continuous pharmaceutical manufacturing

Copyright © 2018 Fani Boukouvala