Journal of Product Design, Quality Engineering & Technology

Abstract

AI-assisted generative design has emerged as a transformative approach in modern product innovation, enabling designers and engineers to explore vast solution spaces that were previously impractical using traditional methods. By integrating artificial intelligence, optimization algorithms, and computational creativity, generative design systems can automatically generate, evaluate, and refine thousands of design alternatives based on predefined objectives and constraints. This paper presents a comprehensive review of AI-assisted generative design for product innovation, focusing on its theoretical foundations, algorithmic techniques, system architectures, and practical applications across multiple industries. The study discusses how machine learning, evolutionary algorithms, and deep generative models contribute to design automation and creativity enhancement. Challenges related to interpretability, manufacturability, data dependency, and human–AI collaboration are critically analyzed. Finally, future research directions are outlined, emphasizing the role of explainable AI, sustainable design objectives, and integration with digital manufacturing platforms. The paper aims to provide researchers and practitioners with a structured understanding of the current state and potential of AI-assisted generative design in accelerating product innovation.

Keywords:  Generative design, artificial intelligence, product innovation, design optimization, machine learning, computational creativity