DEVELOPMENT OF OPTIMIZATION MODELS FOR AUTOMOTIVE PRODUCTION PROCESSES: TAGUCHI AND NEURO-FUZZY METHODS AT RENAULT

Abstract

This research investigates the development and application of advanced optimization techniques and mathematical modeling to enhance automotive production processes, using Renault’s operations in Morocco as a case study. The study addresses inefficiencies within the supply chain by integrating two powerful methodologies: the Taguchi method and neuro-fuzzy models. The Taguchi approach identifies optimal process parameters, improving consistency, reducing variability, and enhancing resource utilization. Simultaneously, the neuro-fuzzy model provides adaptability, effectively managing the dynamic and often unpredictable nature of modern supply chains. The combined use of these techniques leads to significant outcomes, including better resource efficiency, considerable cost reductions, and stronger adherence to environmental sustainability principles. Furthermore, the hybrid approach helps in minimizing process variability, enabling more precise decision-making and strategic planning. Beyond improving production processes, the study emphasizes the adaptability and efficacy of these integrated methods, making them highly valuable for broader industrial and policy-making applications. The findings highlight the critical importance of leveraging innovative, data-driven optimization strategies to shape sustainable, efficient, and resilient automotive supply chain systems. The research underscores the relevance of these methods in supporting industrial evolution and addressing global sustainability challenges, reinforcing their role in fostering eco-friendly and cost-effective solutions across industries. This underscores a compelling blueprint for the automotive industry to drive lasting improvements and foster systemic transformation.