Sustainable Scheduling in Manufacturing: Integrating NSGA-II and Discrete-Event Simulation for Hybrid Flowshop Environments
Open Access
- 22 November 2024
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 94-103
Abstract
One of the most important strategies for sustainable manufacturing systems is sustainable scheduling. It involves allocating a set of production jobs within a manufacturing environment while ensuring the fulfilment of the objectives on the environmental, social, and economic dimensions. However, achieving these objectives is complex, as it often needs balancing competing priorities among the three dimensions. In this paper, a three-objectives non-dominated sorting genetic algorithm II (NSGA-II) coupled with an event-based simulation is proposed for a hybrid flowshop problem, to reach a sustainable scheduling. This simulation-optimization approach, which encompasses the Triple-Bottom Line (TBL) objectives, aims to minimize total energy consumption as the environmental dimension, minimize a labor indicator as the social dimension, and minimize the Mean Completion Time (MCT) as the economic dimension, simultaneously. NSGA-II, as a meta-heuristic, is utilized for exploring and exploiting potential solutions within the feasible region, while the event-based simulation is used for evaluating the solutions and the fitness functions of the three dimensions. Consequently, this coupling approach promptly and efficiently explores the set of non-dominated solutions, or Pareto front, to analyze the real trade-off between the TBL. Additionally, validation experiments were carried out in a defined and simulated hybrid flowshop environment, featuring dynamic arrivals, to examine two cases: one consisting of homogeneously skilled workers (Case A) and another comprising heterogeneously skilled workers (Case B). Furthermore, a comparison among the three single-objective algorithms (one for each TBL target) is provided. The preliminary results suggest that the proposed approach achieves reasonable solutions for the hybrid flowshop problem and can be a consistent method for decision-making in sustainable manufacturing.Keywords
This publication has 20 references indexed in Scilit:
- Knowledge graph embedding learning system for defect diagnosis in additive manufacturingComputers in Industry, 2023
- Flexible job shop scheduling problem under Industry 5.0: A survey on human reintegration, environmental consideration and resilience improvementJournal of Manufacturing Systems, 2023
- The perceived relationship between digitalization and ecological, economic, and social sustainabilityJournal of Cleaner Production, 2021
- Scheduling for sustainable manufacturing: A reviewJournal of Cleaner Production, 2018
- A novel mathematical model and multi-objective method for the low-carbon flexible job shop scheduling problemSustainable Computing: Informatics and Systems, 2017
- An approach to the prioritization of sustainable maintenance drivers in the TBL frameworkIFAC-PapersOnLine, 2016
- Governance mechanism in control architectures for flexible manufacturing systemsIFAC-PapersOnLine, 2015
- Multi-objective permutation flow shop scheduling problem: Literature review, classification and current trendsOmega, 2014
- Reducing ergonomic risks by job rotation schedulingOR Spectrum, 2012
- Scheduling2012