Prediction of Consumables Requirement in PEB Manufacturing Using Probabilistic Grouping and Random Forest Regression

Prediction of Consumables Requirement in PEB Manufacturing Using Probabilistic Grouping and Random Forest Regression
  IJETT-book-cover           
  
© 2025 by IJETT Journal
Volume-73 Issue-8
Year of Publication : 2025
Author : Ringle Raja, Hemalatha, Vincent Sam Jebadurai, Elizabeth Amudhini Stephen, Athish
DOI : 10.14445/22315381/IJETT-V73I8P122

How to Cite?
Ringle Raja, Hemalatha, Vincent Sam Jebadurai, Elizabeth Amudhini Stephen, Athish,"Prediction of Consumables Requirement in PEB Manufacturing Using Probabilistic Grouping and Random Forest Regression", International Journal of Engineering Trends and Technology, vol. 73, no. 8, pp.254-261, 2025. Crossref, https://doi.org/10.14445/22315381/IJETT-V73I8P122

Abstract
Within the Pre-Engineered Buildings (PEBs) framework, error-free consumable prediction poses a significant challenge due to the inherent variation in project designs, component types, and fabrication scales. Conventional estimation practices may not be able to capture such complexities, thus leading to inefficiencies, cost overruns, and wastage of excess materials. The current research introduces a data-driven methodology that applies machine learning techniques, especially Random Forest Regression (RFR), to develop a robust predictive model trained on concurrent PEB projects. The total fabrication tonnage of each project is broken down into different amounts of individual components, which are further used as structured inputs for predictive model training. A multi-output forecasting strategy is employed to facilitate concurrent forecasting of multiple consumable needs for similar future projects in a single execution. Probabilistic clustering based on major fabrication consumables and scales is applied to enhance the accuracy and precision of the forecasts produced by the model. Hyperparameters are tuned through GridSearchCV; hence, the exactness and model generalization are improved. The proposed methodology demonstrates significant improvements in forecasting accuracy, facilitating improved resource planning, cost effectiveness, and sustainability in PEB fabrication processes. The results highlight the potential advantages of incorporating machine learning methodologies in construction planning for facilitating more intelligent and scalable decision-making practices.

Keywords
Artificial Intelligence (AI), Machine Learning (ML), Consumable prediction, Pre-Engineered Buildings (PEB), Random Forest Regression.

References
[1] Amir Sadatnya et al., “Machine Learning for Construction Crew Productivity Prediction using Daily Work Reports,” Automation in Construction, vol. 152. 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Yu Gao, Jiayuan Wang, and Xiaoxiao Xu, “Machine Learning in Construction and Demolition Waste Management: Progress, Challenges, and Future Directions,” Automation in Construction, vol. 162, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Hanane Zermane et al., “Forecasting Material Quantity using Machine Learning and Times Series Techniques,” Journal of Electrical Engineering, vol. 75, no. 3, pp. 237-248, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Jaemin Jeong et al., “Learning-Driven Construction Productivity Prediction for Prefabricated External Insulation Wall System,” Automation in Construction, vol. 141, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[5] K. Karthick, R. Dharmaprakash, and S. Sathya, “Predictive Modeling of Energy Consumption in the Steel Industry Using CatBoost Regression: A Data-Driven Approach for Sustainable Energy Management,” International Journal of Robotics and Control Systems, vol. 4, no. 1, pp. 33-49, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Yuanyuan Li et al., “Machine Learning and Optimization for Production Rescheduling in Industry 4.0,” The International Journal of Advanced Manufacturing Technology, vol. 110, no. 9-10, pp. 2445-2463, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Balduíno César Mateus et al., “Forecasting Steel Production in the World - Assessments Based on Shallow and Deep Neural Networks,” Applied Sciences, vol. 13, no. 1, pp. 1-17, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Faiq Mohammed et al., “Application Intelligent Predicting Technologies in Construction Productivity,” American Journal of Engineering and Technology Management, vol. 1, no. 3, pp. 39-48, 2016.
[Google Scholar] [Publisher Link]
[9] M.Z. Naser, “Machine Learning for All! Benchmarking Automated, Explainable, and Coding-Free Platforms on Civil and Environmental Engineering Problems,” Journal of Infrastructure Intelligence and Resilience, vol. 2, no. 1, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Suresh Babu Rajasekaran, “Applications of Machine Learning in Manufacturing: Benefits, Issues, and Strategies,” International Journal of Computing and Artificial Intelligence, vol. 4, no. 1, pp. 1-11, 2023.
[CrossRef] [Publisher Link]
[11] Mohamed A. Shaheen, Rebecca Presswood, and Sheida Afshan, “Application of Machine Learning to Predict the Mechanical Properties of High Strength Steel at Elevated Temperatures Based on the Chemical Composition,” Structures, vol. 52, pp. 17-29, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[12] S.M. Taslim Uddin Raju et al., “An Approach for Demand Forecasting in Steel Industries Using Ensemble Learning,” Complexity, vol. 2022, no. 1, pp. 1-19, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Shashank Reddy Vadyala et al., “A Review of Physics-Based Machine Learning in Civil Engineering,” Results in Engineering, vol. 13, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Ahsan Waqar, “Intelligent Decision Support Systems in Construction Engineering: An Artificial Intelligence and Machine Learning Approach,” Expert Systems with Applications, vol. 249, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[15] William Villegas-Ch, Alexandra Maldonado Navarro, and Santiago Sanchez-Viteri, “Optimization of Inventory Management through Computer Vision and Machine Learning Technologies,” Intelligent Systems with Applications, vol. 24, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Qing Xia et al., “A Method Towards Smart Manufacturing Capabilities and Performance Measurement,” Procedia, vol. 39, pp. 851-858, 2019.
[CrossRef] [Google Scholar] [Publisher Link]