AI-Assisted Generative Product Design Integrated with Multi Objective Quality Optimization for Sustainable Manufacturing
Abstract
The convergence of artificial intelligence (AI), generative design algorithms, and sustainable manufacturing paradigms represents a transformative shift in modern industrial engineering. Traditional product design methodologies often struggle to concurrently balance structural integrity, material mass minimization, manufacturing cost, and environmental sustainability across the complete product lifecycle. This paper presents a comprehensive review of AI assisted generative product design frameworks integrated with multi-objective quality optimization techniques tailored for sustainable manufacturing environments. We critically examine state-of-the-art generative modeling architectures—including Topology Optimization (TO), Variational Autoencoders (VAEs), Generative Adversarial Networks (GANs), and Physics Informed Neural Networks (PINNs)—alongside multi-objective optimization (MOO) algorithms such as NSGA-III and Bayesian Optimization. Furthermore, this review explores the seamless integration of Life Cycle Assessment (LCA) indicators, circular economy principles, and additive/subtractive manufacturing constraints into the early-stage conceptual design phase. Quantitative benchmark evaluations demonstrate that AI-driven generative frameworks achieve mass reductions of 22% to 38%, embodied carbon decreases of 18% to 31%, and structural compliance improvements exceeding 25% compared to legacy CAD designs. Finally, key technological challenges, including geometric manufacturability gaps, material anisotropy, high computational training loads, and black-box interpretability, are critically discussed alongside future research directions.
KEYWORDS: Generative Design, Artificial Intelligence, Multi-Objective Optimization, Sustainable Manufacturing, Life Cycle Assessment, Topology Optimization, Additive Manufacturing.
KEYWORDS: Generative Design, Artificial Intelligence, Multi-Objective Optimization, Sustainable Manufacturing, Life Cycle Assessment, Topology Optimization, Additive Manufacturing.
Full Text:
PDF 53-68Refbacks
- There are currently no refbacks.