Loughborough University
Browse

File(s) under permanent embargo

Reason: Publisher requirement.

Optimal control policies of a crystallization process using inverse reinforcement learning

conference contribution
posted on 2022-03-10, 10:31 authored by Paul AnandanPaul Anandan, Chris Rielly, Brahim BenyahiaBrahim Benyahia
Crystallization is widely used in the pharmaceutical industry to purify reaction intermediates and final active pharmaceutical ingredients. This work presents a novel implementation of Inverse Reinforcement Learning (IRL) approach where an agent observes the expert’s optimal control policies of a crystallization process and attempts to mimic its performance. In essence, an Apprenticeship Learning (AL) setup was developed where the expert demonstrates the control task to the IRL agent to help attain effective control performance when compared to the expert. This is achieved through repeated execution of “exploitation policies” that simply maximizes the rewards over the consecutive IRL training episodes. The cooling crystallization of paracetamol is used as a case study and both proportional integral derivative (PID) and Model Predictive Control (MPC) strategies were considered as expert systems. A model based IRL technique is implemented to achieve effective trajectory tracking which ensures final crystal size considered as the critical quality attributes, by reducing the deviation from the optimal reference trajectories namely process temperature, supersaturation, and particle size. The performance of the trained IRL agent was validated against the PID and MPC and tested in presence of noisy measurements and model uncertainties.

Funding

ARTICULAR: ARtificial inTelligence for Integrated ICT-enabled pharmaceUticaL mAnufactuRing

Engineering and Physical Sciences Research Council

Find out more...

History

School

  • Aeronautical, Automotive, Chemical and Materials Engineering

Department

  • Chemical Engineering

Published in

32nd European Symposium on Computer Aided Process Engineering: ESCAPE-32

Pages

1093-1098

Source

32nd European Symposium on Computer Aided Process Engineering (ESCAPE32)

Publisher

Elsevier

Version

  • AM (Accepted Manuscript)

Rights holder

© Elsevier

Publisher statement

This paper was accepted for publication in the 32nd European Symposium on Computer Aided Process Engineering: ESCAPE-32 and the definitive published version is available at https://doi.org/10.1016/B978-0-323-95879-0.50183-1.

Acceptance date

2022-01-24

Publication date

2022-08-01

Copyright date

2022

ISBN

9780323958790; 9780323958806

ISSN

1570-7946

Book series

Computer Aided Chemical Engineering; Volume 51

Language

  • en

Editor(s)

Ludovic Montastruc; Stéphane Negny

Location

Toulouse, France

Event dates

12th June 2022 - 15th June 2022

Depositor

Dr Brahim Benyahia. Deposit date: 9 March 2022

Usage metrics

    Loughborough Publications

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC