Quantifying the Role of AI in Part Reduction and Assembly Optimization for Sustainable DFMA

Abstract

This paper explores the pivotal role of Artificial Intelligence (AI) in advancing Design for Manufacturing and Assembly (DFMA) to meet the growing demands of sustainable manufacturing. DFMA, with its emphasis on reducing part counts and simplifying assembly, directly contributes to objectives such as material conservation, energy efficiency, and improved product disassembly, which are key factors in sustainable engineering. As AI becomes increasingly embedded in design and production, it transforms traditional DFMA from a static, rule-based process into a dynamic, data-driven system. Through technologies like generative design, reinforcement learning, and computer vision, AI facilitates intelligent part consolidation, optimized assembly sequencing, and lifecycle-oriented decision-making. The paper analyzes four significant research studies demonstrating AI’s impact on sequencing, integration of multifunctional parts, and adaptive assembly planning.  Real-world applications in industries such as aerospace, automotive, and electronics have shown up to 95 percent reductions in part count, 60 percent faster assembly processes, and notable energy savings. Supporting case studies such as AI-driven PCB layout optimization and generative redesign of aerospace components illustrate these outcomes. Moreover, the   integration   of   AI   with   sustainability tools   like   life   cycle   assessment (LCA) further ensures environmentally responsible design from the outset. The paper ultimately argues that AI does not simply support DFMA; it redefines it by embedding intelligence throughout the development cycle, enabling closed- loop, sustainable product engineering that aligns performance with environmental impact.