Hybrid modelling for remote process monitoring and optimisation

Received: 18 Apr 2022, Revised: 20 Apr 2022, Accepted: 29 July 2022, Available online: 28 Sep 2022, Version of Record: 28 Sep 2022

Anuar Hamid a
,
Anton Heryanto Hasan b
,
Siti Nurfaqihah Azhari b
,
Zalina Harun b
,
Zulfan A. Putra b
a
East One-Zero-One, Shah Alam, Selangor, 40000, Malaysia
b
PETRONAS Group Technical Solutions (Process Simulation and Optimization), Level 16, Tower 3 Kuala Lumpur City Center, Kuala Lumpur, 50088, Malaysia

Abstract



Process simulation is used to develop a digital twin representation of chemical processes typically for process optimization or what-if scenarios. However, it is known to be computationally expensive and there is an increasing need for process remote monitoring and optimization. This is where machine learning models shine, where they can run up to several orders of magnitude faster than their equivalent first principle process simulation models. Most of the previous work in this area tend to demonstrate the ability of machine learning models to accurately capture complex, non-linear relationships between process parameters in various chemical processes. Two important aspects are rarely discussed, namely the construction of machine learning models using operating data and the deployment of these models. In this paper, we address these two aspects and review the different information silos in industrial settings that need to be considered when working with hybrid models (combining process simulation and machine learning). This is illustrated by a case study for an operating natural gas dehydration unit, covering data management, process simulation, machine learning and visualization. We demonstrate how the hybrid models can be constructed and packaged as an online monitoring and a prediction dashboard. Several unique challenges are also highlighted including the reliability of field data and operational deviations due to operability and controllability - all of which need to be understood in order to successfully translate operating systems to process simulation and machine learning models that are reliable and accurate. While the exact implementation may vary from project to project, the current work serves as an example and highlights the important considerations to make when working with such systems.
Graphical abstract

  1. Download: Download high-res image (160KB)
  2. Download: Download full-size image
Keywords
First principle modeling
Machine learning
Digital process engineering
Process modeling
Process simulation
Process optimization
Multi objective optimization
Dehydration unit
Natural gas
Water dew point
Reboiler duty



Description



   

Indexed in scopus

https://www.scopus.com/authid/detail.uri?authorId=57665222800
      

Article metrics

10.31763/DSJ.v5i1.1674 Abstract views : | PDF views :

   

Cite

   

Full Text

Download

Conflict of interest


“Authors state no conflict of interest”


Funding Information


This research received no external funding or grants


Peer review:


Peer review under responsibility of Defence Science Journal


Ethics approval:


Not applicable.


Consent for publication:


Not applicable.


Acknowledgements:


None.