Staff View: Digital twin-aided transfer learning for energy efficiency optimization of thermal spray dryers: Leveraging shared drying characteristics across chemicals with limited data

Digital twin-aided transfer learning for energy efficiency optimization of thermal spray dryers: Leveraging shared drying characteristics across chemicals with limited data

Efficient energy management is crucial for spray -drying units as it can substantially improve product yield, reduce operating costs, and enhance energy utilization. However, due to limited data problems, the monitoring performance of the energy efficiency of a model is inefficient and unreliable, m...

Full description

Saved in:

Bibliographic Details
Main Authors:	Bardeeniz, Santi, Panjapornpon, Chanin, Fongsamut, Chalermpan, Ngaotrakanwiwat, Pailin, Hussain, Mohamed Azlan
Format:	Article
Published:	Elsevier 2024
Subjects:	TK Electrical engineering. Electronics Nuclear engineering TP Chemical technology
Online Access:	http://eprints.um.edu.my/45767/ https://doi.org/10.1016/j.applthermaleng.2024.122431
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my.um.eprints.45767
record_format	eprints
spelling	my.um.eprints.457672024-11-12T01:29:34Z http://eprints.um.edu.my/45767/ Digital twin-aided transfer learning for energy efficiency optimization of thermal spray dryers: Leveraging shared drying characteristics across chemicals with limited data Bardeeniz, Santi Panjapornpon, Chanin Fongsamut, Chalermpan Ngaotrakanwiwat, Pailin Hussain, Mohamed Azlan TK Electrical engineering. Electronics Nuclear engineering TP Chemical technology Efficient energy management is crucial for spray -drying units as it can substantially improve product yield, reduce operating costs, and enhance energy utilization. However, due to limited data problems, the monitoring performance of the energy efficiency of a model is inefficient and unreliable, making it difficult to adjust operating conditions and hindering effective utility management. Therefore, this study proposes a long shortterm memory -based transfer learning model with shared source -target characteristics for enhancing energy efficiency trackability under limited efficiency labels. Utilizing a long short-term memory structure improves the capability of capturing the process dynamic behavior. Synchronously, the digital twin -aided transfer learning concept supports the model by leveraging the parameters learned from the simulated source domain to assist the performance of the model in a limited data domain with different chemicals. The reliability and accuracy of the model are verified by a real industrial case study involving the detergent powder drying process. Results show that the model testing achieved an r -squared value of 0.938, outperforming conventional techniques by boosting the performance of the network up to 14.53 % and reducing surplus energy on demand and supply by 50.05 % and 81.27 %, respectively. The proposed model reveals the interconnection between source and target accuracy and provides a reliable learning process of the target domain observed based on the distribution of the testing performance. Notably, the model deployment indicates a considerable decrease of 16.63 % in natural gas consumption, leading to an enhancement of 11.92 % in evaporation efficiency and the prevention of 483 tonnes of carbon emissions annually. Elsevier 2024-04 Article PeerReviewed Bardeeniz, Santi and Panjapornpon, Chanin and Fongsamut, Chalermpan and Ngaotrakanwiwat, Pailin and Hussain, Mohamed Azlan (2024) Digital twin-aided transfer learning for energy efficiency optimization of thermal spray dryers: Leveraging shared drying characteristics across chemicals with limited data. Applied Thermal Engineering, 242. p. 122431. ISSN 1359-4311, DOI https://doi.org/10.1016/j.applthermaleng.2024.122431 <https://doi.org/10.1016/j.applthermaleng.2024.122431>. https://doi.org/10.1016/j.applthermaleng.2024.122431 10.1016/j.applthermaleng.2024.122431
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	TK Electrical engineering. Electronics Nuclear engineering TP Chemical technology
spellingShingle	TK Electrical engineering. Electronics Nuclear engineering TP Chemical technology Bardeeniz, Santi Panjapornpon, Chanin Fongsamut, Chalermpan Ngaotrakanwiwat, Pailin Hussain, Mohamed Azlan Digital twin-aided transfer learning for energy efficiency optimization of thermal spray dryers: Leveraging shared drying characteristics across chemicals with limited data
description	Efficient energy management is crucial for spray -drying units as it can substantially improve product yield, reduce operating costs, and enhance energy utilization. However, due to limited data problems, the monitoring performance of the energy efficiency of a model is inefficient and unreliable, making it difficult to adjust operating conditions and hindering effective utility management. Therefore, this study proposes a long shortterm memory -based transfer learning model with shared source -target characteristics for enhancing energy efficiency trackability under limited efficiency labels. Utilizing a long short-term memory structure improves the capability of capturing the process dynamic behavior. Synchronously, the digital twin -aided transfer learning concept supports the model by leveraging the parameters learned from the simulated source domain to assist the performance of the model in a limited data domain with different chemicals. The reliability and accuracy of the model are verified by a real industrial case study involving the detergent powder drying process. Results show that the model testing achieved an r -squared value of 0.938, outperforming conventional techniques by boosting the performance of the network up to 14.53 % and reducing surplus energy on demand and supply by 50.05 % and 81.27 %, respectively. The proposed model reveals the interconnection between source and target accuracy and provides a reliable learning process of the target domain observed based on the distribution of the testing performance. Notably, the model deployment indicates a considerable decrease of 16.63 % in natural gas consumption, leading to an enhancement of 11.92 % in evaporation efficiency and the prevention of 483 tonnes of carbon emissions annually.
format	Article
author	Bardeeniz, Santi Panjapornpon, Chanin Fongsamut, Chalermpan Ngaotrakanwiwat, Pailin Hussain, Mohamed Azlan
author_facet	Bardeeniz, Santi Panjapornpon, Chanin Fongsamut, Chalermpan Ngaotrakanwiwat, Pailin Hussain, Mohamed Azlan
author_sort	Bardeeniz, Santi
title	Digital twin-aided transfer learning for energy efficiency optimization of thermal spray dryers: Leveraging shared drying characteristics across chemicals with limited data
title_short	Digital twin-aided transfer learning for energy efficiency optimization of thermal spray dryers: Leveraging shared drying characteristics across chemicals with limited data
title_full	Digital twin-aided transfer learning for energy efficiency optimization of thermal spray dryers: Leveraging shared drying characteristics across chemicals with limited data
title_fullStr	Digital twin-aided transfer learning for energy efficiency optimization of thermal spray dryers: Leveraging shared drying characteristics across chemicals with limited data
title_full_unstemmed	Digital twin-aided transfer learning for energy efficiency optimization of thermal spray dryers: Leveraging shared drying characteristics across chemicals with limited data
title_sort	digital twin-aided transfer learning for energy efficiency optimization of thermal spray dryers: leveraging shared drying characteristics across chemicals with limited data
publisher	Elsevier
publishDate	2024
url	http://eprints.um.edu.my/45767/ https://doi.org/10.1016/j.applthermaleng.2024.122431
_version_	1816130456386535424
score	13.244413

Digital twin-aided transfer learning for energy efficiency optimization of thermal spray dryers: Leveraging shared drying characteristics across chemicals with limited data

Similar Items