Application of Ant Colony Optimization for Job Shop Scheduling in the Pharmaceutical Industry

Simple item page
dc.contributor.authorLACHTAR Nadia
dc.contributor.authorDRISS Imen (Co-Auteur)
dc.date.accessioned2025-09-11T10:29:49Z
dc.date.available2025-09-11T10:29:49Z
dc.date.issued2023
dc.descriptionJournal Européen des Systèmes Automatisés. Vol. 56, No. 5, October, 2023, pp. 713-723 https://doi.org/10.18280/jesa.560501
dc.description.abstractScheduling problems in the industrial sector are among the most studied optimization problems. Improving resource efficiency and minimizing production costs have become important concerns for industry managers. Seeking the best way to maximize profit is now a primary objective for any business. This is the context in which our study is positioned. It focuses on the resolution of job shop scheduling problems (JSSP). Considering that production challenges in industries are complex and require the consideration of multiple factors, we turn to the use of artificial intelligence tools for their resolution. Pharmaceutical manufacturing often involves a large number of resources, machines, and tasks, leading to high complexity in the JSSP. Ant colony optimization (ACO) is innovative and excels in its ability to handle this complexity by seeking optimal solutions while avoiding computational pitfalls. It can efficiently explore vast search spaces and leverage ant parallelism to reach the best solution in a short period of time, which is crucial in the pharmaceutical context where deadlines and quality constraints are paramount. Thus, in order to address the JSSP, this work suggests and puts into practice a method that involves the application of an ACO approach with the goal of minimizing the makespan. We validated our approach by comparing it with various algorithms through benchmarks taken from the published research. The suggested approach proved to be effective as the produced solutions were of high quality and showed that it could achieve results that are closer to the ideal solution for larger-scale issues than other algorithms with an average percentage relative error of just 0.67%. Furthermore, application of ACO in the context of BIOCARE's pharmaceutical laboratories’ production led to an improvement of approximately 3 hours in their weekly planning.
dc.identifier.urihttp://dspace.ensti-annaba.dz:4000/handle/123456789/771
dc.language.isoen
dc.publisherJournal Européen des Systèmes Automatisés
dc.titleApplication of Ant Colony Optimization for Job Shop Scheduling in the Pharmaceutical Industry
dc.typeArticle
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
DRISS Imen - Application of Ant Colony Optimization for Job Shop Scheduling in the Pharmaceutical Industry.pdf
Size:
2.54 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed to upon submission
Description:
Download
Collections
Articles