Volume 23, Issue 1 (3-2026)
jor 2026, 23(1): 0-0 |
Back to browse issues page
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Espidkar B, Mehrabian A, Harsej F, Amoozad Khalili H. A Machine Learning-Based Decision-Making Framework for the Green Flexible Job Shop Scheduling Problem Considering Preventive Maintenance. jor 2026; 23 (1)
URL: http://jamlu.lahijan.iau.ir/article-1-2322-en.html
URL: http://jamlu.lahijan.iau.ir/article-1-2322-en.html
Department of Industrial Engineering, AK.C., Islamic Azad University, Aliabad Katoul, Iran , mehrabian.project@aliabadiau.ac.ir
Abstract: (230 Views)
This study focuses on one of the critical issues in manufacturing systems, namely the Flexible Job Shop Scheduling Problem (FJSP), which is addressed with considerations for environmental aspects and preventive maintenance. In this regard, the present paper develops a machine learning–based decision-making framework. To achieve this objective, a mathematical model is proposed that aims to minimize delivery tardiness, greenhouse gas emissions, and energy consumption, while incorporating preventive maintenance operations. To handle uncertainty, a data-driven approach based on fuzzy optimization and the Random Forest Regression (RFR) algorithm is developed. Subsequently, to tackle the multi-objective nature and complexity of the proposed model, an efficient solution approach combining a Genetic Algorithm (GA) with a normalized weighted sum method is presented. A sensitivity analysis is then conducted to examine the impact of key model parameters on the problem. The results indicate the efficiency and effectiveness of the proposed approach, as it is capable of delivering high-quality solutions within a reasonable computational time. Moreover, the developed machine learning algorithm provides reliable estimations of key parameters. According to the findings, an increase in processing time significantly raises total tardiness, greenhouse gas emissions, and energy consumption. Additionally, the results show that as the setup time parameter increases, all three objective functions—tardiness, emissions, and energy usage—also increase.
Keywords: Flexible Job Shop Scheduling, Preventive Maintenance, Machine Learning-Based Decision-Making, Genetic Algorithm
Send email to the article author
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
