A machine learning approach for forecasting resilient material delivery in the construction industry.
Saved in:
| Title: | A machine learning approach for forecasting resilient material delivery in the construction industry. |
|---|---|
| Authors: | Zhang, Wennan1 (AUTHOR), Yu, Chenglin1 (AUTHOR), Newman, Stephen T.2 (AUTHOR), Cheung Ho Kin, Dennis3 (AUTHOR), Zhong, Ray Y.1 (AUTHOR) zhongzry@hku.hk |
| Source: | International Journal of Production Research. Jul2026, Vol. 64 Issue 13, p5270-5289. 20p. |
| Subjects: | Hidden Markov models, Supply chain management, Machine learning, Construction industry, Construction industry forecasting, Risk management in business, Statistical decision making, Digital twin |
| Abstract: | In the construction industry, the unpredictable delivery of materials together with the delivery of incorrect materials is a frequent occurrence. This leads to supply chain disruptions and failure to align with other stakeholders. Contractors aim to develop a resilient supply chain by mitigating these risks regarding delivery and controlling costs by being kept well informed of potential delays. In this paper, the authors propose a novel digital twin-enabled model for mapping delivery networks and monitoring supply chain risks. The contingency and disruption amid the construction supply chain provide indisputable evidence for the need for digital twin technology to ensure visibility. The collected data shows the relationship between materials and corresponding machines (MCM) via a hidden transition and usage plan. The paper presents a new improved Hidden Markov Model (HMM) approach entitled the Multi-Material & Machine Hidden Markov Model (M3HMM), as it considers the relationships of usage plans for MCM to forecast delivery and ensure supply chain resilience. The results show that with respect to resilience, M3HMM consistently performs the best compared with other algorithms, including LR, SVR, GMM, LSTM and HMM. It also ultimately enables industrial contractors to enhance their predictive and reactive decision-making, reducing the risk. [ABSTRACT FROM AUTHOR] |
| Copyright of International Journal of Production Research is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| Abstract: | In the construction industry, the unpredictable delivery of materials together with the delivery of incorrect materials is a frequent occurrence. This leads to supply chain disruptions and failure to align with other stakeholders. Contractors aim to develop a resilient supply chain by mitigating these risks regarding delivery and controlling costs by being kept well informed of potential delays. In this paper, the authors propose a novel digital twin-enabled model for mapping delivery networks and monitoring supply chain risks. The contingency and disruption amid the construction supply chain provide indisputable evidence for the need for digital twin technology to ensure visibility. The collected data shows the relationship between materials and corresponding machines (MCM) via a hidden transition and usage plan. The paper presents a new improved Hidden Markov Model (HMM) approach entitled the Multi-Material & Machine Hidden Markov Model (M3HMM), as it considers the relationships of usage plans for MCM to forecast delivery and ensure supply chain resilience. The results show that with respect to resilience, M3HMM consistently performs the best compared with other algorithms, including LR, SVR, GMM, LSTM and HMM. It also ultimately enables industrial contractors to enhance their predictive and reactive decision-making, reducing the risk. [ABSTRACT FROM AUTHOR] |
|---|---|
| ISSN: | 00207543 |
| DOI: | 10.1080/00207543.2025.2482733 |
