Cover Image

Production Capacity Prediction and Optimization in the Glycerin Purification Process: A Simulation-Assisted Few-Shot Learning Approach

Chemical process control relies on a tightly controlled, narrow range of margins for critical variables, ensuring process stability and safeguarding equipment from potential accidents. The availability of historical process data is limited to a specific setpoint of operation. This challenge raises i...

Full description

Saved in:
Bibliographic Details
Main Authors: Jitchaiyapoom, Tawesin, Panjapornpon, Chanin, Bardeeniz, Santi, Hussain, Mohd Azlan
Format: Article
Published: MDPI 2024
Subjects:
TP Chemical technology
Online Access:http://eprints.um.edu.my/45362/
https://doi.org/10.3390/pr12040661
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.um.eprints.45362
record_format eprints
spelling my.um.eprints.453622024-10-14T08:46:12Z http://eprints.um.edu.my/45362/ Production Capacity Prediction and Optimization in the Glycerin Purification Process: A Simulation-Assisted Few-Shot Learning Approach Jitchaiyapoom, Tawesin Panjapornpon, Chanin Bardeeniz, Santi Hussain, Mohd Azlan TP Chemical technology Chemical process control relies on a tightly controlled, narrow range of margins for critical variables, ensuring process stability and safeguarding equipment from potential accidents. The availability of historical process data is limited to a specific setpoint of operation. This challenge raises issues for process monitoring in predicting and adjusting to deviations outside of the range of operational parameters. Therefore, this paper proposes simulation-assisted deep transfer learning for predicting and optimizing the final purity and production capacity of the glycerin purification process. The proposed network is trained by the simulation domain to generate a base feature extractor, which is then fine-tuned using few-shot learning techniques on the target learner to extend the working domain of the model beyond historical practice. The result shows that the proposed model improved prediction performance by 24.22% in predicting water content and 79.72% in glycerin prediction over the conventional deep learning model. Additionally, the implementation of the proposed model identified production and product quality improvements for enhancing the glycerin purification process. MDPI 2024-04 Article PeerReviewed Jitchaiyapoom, Tawesin and Panjapornpon, Chanin and Bardeeniz, Santi and Hussain, Mohd Azlan (2024) Production Capacity Prediction and Optimization in the Glycerin Purification Process: A Simulation-Assisted Few-Shot Learning Approach. Processes, 12 (4). p. 661. ISSN 2227-9717, DOI https://doi.org/10.3390/pr12040661 <https://doi.org/10.3390/pr12040661>. https://doi.org/10.3390/pr12040661 10.3390/pr12040661
institution Universiti Malaya
building UM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Malaya
content_source UM Research Repository
url_provider http://eprints.um.edu.my/
topic TP Chemical technology
spellingShingle TP Chemical technology
Jitchaiyapoom, Tawesin
Panjapornpon, Chanin
Bardeeniz, Santi
Hussain, Mohd Azlan
Production Capacity Prediction and Optimization in the Glycerin Purification Process: A Simulation-Assisted Few-Shot Learning Approach
description Chemical process control relies on a tightly controlled, narrow range of margins for critical variables, ensuring process stability and safeguarding equipment from potential accidents. The availability of historical process data is limited to a specific setpoint of operation. This challenge raises issues for process monitoring in predicting and adjusting to deviations outside of the range of operational parameters. Therefore, this paper proposes simulation-assisted deep transfer learning for predicting and optimizing the final purity and production capacity of the glycerin purification process. The proposed network is trained by the simulation domain to generate a base feature extractor, which is then fine-tuned using few-shot learning techniques on the target learner to extend the working domain of the model beyond historical practice. The result shows that the proposed model improved prediction performance by 24.22% in predicting water content and 79.72% in glycerin prediction over the conventional deep learning model. Additionally, the implementation of the proposed model identified production and product quality improvements for enhancing the glycerin purification process.
format Article
author Jitchaiyapoom, Tawesin
Panjapornpon, Chanin
Bardeeniz, Santi
Hussain, Mohd Azlan
author_facet Jitchaiyapoom, Tawesin
Panjapornpon, Chanin
Bardeeniz, Santi
Hussain, Mohd Azlan
author_sort Jitchaiyapoom, Tawesin
title Production Capacity Prediction and Optimization in the Glycerin Purification Process: A Simulation-Assisted Few-Shot Learning Approach
title_short Production Capacity Prediction and Optimization in the Glycerin Purification Process: A Simulation-Assisted Few-Shot Learning Approach
title_full Production Capacity Prediction and Optimization in the Glycerin Purification Process: A Simulation-Assisted Few-Shot Learning Approach
title_fullStr Production Capacity Prediction and Optimization in the Glycerin Purification Process: A Simulation-Assisted Few-Shot Learning Approach
title_full_unstemmed Production Capacity Prediction and Optimization in the Glycerin Purification Process: A Simulation-Assisted Few-Shot Learning Approach
title_sort production capacity prediction and optimization in the glycerin purification process: a simulation-assisted few-shot learning approach
publisher MDPI
publishDate 2024
url http://eprints.um.edu.my/45362/
https://doi.org/10.3390/pr12040661
_version_ 1814047547366309888
score 13.211869

Similar Items