A novel CFD-MILP-ANN approach for optimizing sensor placement, number, and source localization in large-scale gas dispersion from unknown locations

Illegal practices like open electronic waste incineration release hazardous pollutants, endangering the environment and human health. The Internet of Things (IoT) enables online real-time gas concentrations, but its capability to predict leak sources accurately remains a challenge. A large amount of...

Full description

Bibliographic Details
Main Authors: Lang, Yiming, Ng, Michelle Xin Yi, Yu, Kai Xiang, Chen, Binghui, Tan, Peng Chee, Tan, Khang Wei, Lam, Weng Hoong, Siwayanan, Parthiban, Kim, Kek Seong, Choong, Thomas Shean Yaw, Ten, Joon Yoon, Ban, Zhen Hong
Format: Article
Language:English
Published: Elsevier Ltd 2025
Online Access:http://psasir.upm.edu.my/id/eprint/118650/
http://psasir.upm.edu.my/id/eprint/118650/1/118650.pdf
_version_ 1848867563739545600
author Lang, Yiming
Ng, Michelle Xin Yi
Yu, Kai Xiang
Chen, Binghui
Tan, Peng Chee
Tan, Khang Wei
Lam, Weng Hoong
Siwayanan, Parthiban
Kim, Kek Seong
Choong, Thomas Shean Yaw
Ten, Joon Yoon
Ban, Zhen Hong
author_facet Lang, Yiming
Ng, Michelle Xin Yi
Yu, Kai Xiang
Chen, Binghui
Tan, Peng Chee
Tan, Khang Wei
Lam, Weng Hoong
Siwayanan, Parthiban
Kim, Kek Seong
Choong, Thomas Shean Yaw
Ten, Joon Yoon
Ban, Zhen Hong
author_sort Lang, Yiming
building UPM Institutional Repository
collection Online Access
description Illegal practices like open electronic waste incineration release hazardous pollutants, endangering the environment and human health. The Internet of Things (IoT) enables online real-time gas concentrations, but its capability to predict leak sources accurately remains a challenge. A large amount of historical data is required to train the source localization model, as gas dispersion is affected by wind speed and wind direction. Furthermore, sensor placement critically affects precise detection and prediction. This study introduces an innovative approach integrating Computational Fluid Dynamics (CFD), Mixed-Integer Linear Programming (MILP), and Artificial Neural Network modeling (ANN). CFD was utilized for machine learning model training. The MILP was used to optimize sensor placement, while the ANN model was used to optimize sensor number. The source localization model was again realized by the ANN model with optimized sensors data. The trained model was able to identify the unknown illegal electronic waste treatment locations with 97.22 % accuracy in this study. This method allows for the rapid detection of gas sources, as well as the execution of an emergency response, in line with Sustainable Development Goal Target 3.9.
first_indexed 2025-11-15T14:38:29Z
format Article
id upm-118650
institution Universiti Putra Malaysia
institution_category Local University
language English
last_indexed 2025-11-15T14:38:29Z
publishDate 2025
publisher Elsevier Ltd
recordtype eprints
repository_type Digital Repository
spelling upm-1186502025-07-21T06:39:12Z http://psasir.upm.edu.my/id/eprint/118650/ A novel CFD-MILP-ANN approach for optimizing sensor placement, number, and source localization in large-scale gas dispersion from unknown locations Lang, Yiming Ng, Michelle Xin Yi Yu, Kai Xiang Chen, Binghui Tan, Peng Chee Tan, Khang Wei Lam, Weng Hoong Siwayanan, Parthiban Kim, Kek Seong Choong, Thomas Shean Yaw Ten, Joon Yoon Ban, Zhen Hong Illegal practices like open electronic waste incineration release hazardous pollutants, endangering the environment and human health. The Internet of Things (IoT) enables online real-time gas concentrations, but its capability to predict leak sources accurately remains a challenge. A large amount of historical data is required to train the source localization model, as gas dispersion is affected by wind speed and wind direction. Furthermore, sensor placement critically affects precise detection and prediction. This study introduces an innovative approach integrating Computational Fluid Dynamics (CFD), Mixed-Integer Linear Programming (MILP), and Artificial Neural Network modeling (ANN). CFD was utilized for machine learning model training. The MILP was used to optimize sensor placement, while the ANN model was used to optimize sensor number. The source localization model was again realized by the ANN model with optimized sensors data. The trained model was able to identify the unknown illegal electronic waste treatment locations with 97.22 % accuracy in this study. This method allows for the rapid detection of gas sources, as well as the execution of an emergency response, in line with Sustainable Development Goal Target 3.9. Elsevier Ltd 2025-03 Article PeerReviewed text en cc_by_nc_nd_4 http://psasir.upm.edu.my/id/eprint/118650/1/118650.pdf Lang, Yiming and Ng, Michelle Xin Yi and Yu, Kai Xiang and Chen, Binghui and Tan, Peng Chee and Tan, Khang Wei and Lam, Weng Hoong and Siwayanan, Parthiban and Kim, Kek Seong and Choong, Thomas Shean Yaw and Ten, Joon Yoon and Ban, Zhen Hong (2025) A novel CFD-MILP-ANN approach for optimizing sensor placement, number, and source localization in large-scale gas dispersion from unknown locations. Digital Chemical Engineering, 14. art. no. 100216. pp. 1-22. ISSN 2772-5081; eISSN: 2772-5081 https://linkinghub.elsevier.com/retrieve/pii/S2772508124000784 10.1016/j.dche.2024.100216
spellingShingle Lang, Yiming
Ng, Michelle Xin Yi
Yu, Kai Xiang
Chen, Binghui
Tan, Peng Chee
Tan, Khang Wei
Lam, Weng Hoong
Siwayanan, Parthiban
Kim, Kek Seong
Choong, Thomas Shean Yaw
Ten, Joon Yoon
Ban, Zhen Hong
A novel CFD-MILP-ANN approach for optimizing sensor placement, number, and source localization in large-scale gas dispersion from unknown locations
title A novel CFD-MILP-ANN approach for optimizing sensor placement, number, and source localization in large-scale gas dispersion from unknown locations
title_full A novel CFD-MILP-ANN approach for optimizing sensor placement, number, and source localization in large-scale gas dispersion from unknown locations
title_fullStr A novel CFD-MILP-ANN approach for optimizing sensor placement, number, and source localization in large-scale gas dispersion from unknown locations
title_full_unstemmed A novel CFD-MILP-ANN approach for optimizing sensor placement, number, and source localization in large-scale gas dispersion from unknown locations
title_short A novel CFD-MILP-ANN approach for optimizing sensor placement, number, and source localization in large-scale gas dispersion from unknown locations
title_sort novel cfd-milp-ann approach for optimizing sensor placement, number, and source localization in large-scale gas dispersion from unknown locations
url http://psasir.upm.edu.my/id/eprint/118650/
http://psasir.upm.edu.my/id/eprint/118650/
http://psasir.upm.edu.my/id/eprint/118650/
http://psasir.upm.edu.my/id/eprint/118650/1/118650.pdf