Multiagent System Design of Aluminium Production Process and Generative AI Based Manpower Planning
Year: 2025
Type: conference-paper
Abstract: Generative AI and autonomous software agents have increasingly become integral parts of both our social and professional lives. Their growing adoption offers significant advantages in areas such as process optimization and operational efficiency. This study explores the implementation of software agent technology within the context of workforce planning in an aluminium production facility. The goal is to demonstrate how multi-agent systems (MAS) can be applied to enhance decision-making and streamline manpower allocation. The methodology begins with the use of fuzzy logic, which enables decision-making based on expert knowledge and allows integration with conventional control techniques. While not intended to replace traditional methods, fuzzy logic simplifies the implementation of control systems, particularly in complex or uncertain environments. In the preliminary stage of the study, fuzzy logic was utilized to determine the most suitable department for MAS application. The analysis identified the method planning department as an optimal setting. Subsequently, a software agent was developed using Generative AI techniques and applied to a real production line within that department. The agent was designed to perform workforce planning tasks traditionally carried out by experienced staff. Comparative analysis between human decision-making and the agent-based system revealed that the AI-driven solution achieved a high degree of accuracy and operational speed, suggesting a viable alternative for repetitive and rule-based planning processes. This paper presents a novel application of Generative AI in industrial workforce management and contributes to the limited academic literature in this domain. By bridging the gap between academic research and practical industrial needs, the study offers a forward-looking perspective on how AI agents can effectively support complex production planning and resource allocation.
Authors: Alper AYTATLI, Cemalettin KUBAT
Institutions: Bahçeşehir University, İstanbul Gelişim Üniversitesi
Language: English
Topic: AI and HR Technologies
Domain: Social Sciences
Open Access status: green
OpenAlex ID: W7104028484
FWCI:
Cites:
Cited by:
Related to: