Scholarlink

<p>The cutting-edge computational approach Generative design applies algorithms, machine learning, and physics-based principles to create, analyse, and optimize design solutions within predefined constraints. This methodology has emerged as a transformative tool in engineering to explore innovative solutions that balance performance, efficiency, and feasibility. Our study presents a detailed review of the state-of-the-art in generative design, focusing on its core methodologies that include AI-driven, optimization-based, and physics-based approaches. The integration of advanced technologies, like high-performance computing, multi-objective optimization, and additive manufacturing, is also examined, highlighting their role in expanding generative design capability. The review discusses key challenges, including computational resource requirements and the need for high-quality datasets, while emphasizing opportunities to create sustainable, efficient, and adaptive design solutions. By synthesizing the current advances and identifying future directions, this work aims to provide researchers and practitioners with comprehensive understanding of generative design and its potential to revolutionize engineering practices. Unlike previous reviews that focus primarily on specific algorithms or limited application domains, this review distinctly categorizes generative design approaches into AI-based, optimization-based, and physics-based paradigms, integrates an extensive dataset overview, and introduces a comparative framework to evaluate their engineering applicability.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Generative Design for Engineering Applications: A State-of-the-Art Review

  • 期刊论文

  • 发表日期：

    2025年7月1日

查看全文
  • Mohad Tanveer,
  • Muhammad Muzammil Azad,
  • Dohoon Kim,
  • Salman Khalid,
  • Heung Soo Kim

摘要

The cutting-edge computational approach Generative design applies algorithms, machine learning, and physics-based principles to create, analyse, and optimize design solutions within predefined constraints. This methodology has emerged as a transformative tool in engineering to explore innovative solutions that balance performance, efficiency, and feasibility. Our study presents a detailed review of the state-of-the-art in generative design, focusing on its core methodologies that include AI-driven, optimization-based, and physics-based approaches. The integration of advanced technologies, like high-performance computing, multi-objective optimization, and additive manufacturing, is also examined, highlighting their role in expanding generative design capability. The review discusses key challenges, including computational resource requirements and the need for high-quality datasets, while emphasizing opportunities to create sustainable, efficient, and adaptive design solutions. By synthesizing the current advances and identifying future directions, this work aims to provide researchers and practitioners with comprehensive understanding of generative design and its potential to revolutionize engineering practices. Unlike previous reviews that focus primarily on specific algorithms or limited application domains, this review distinctly categorizes generative design approaches into AI-based, optimization-based, and physics-based paradigms, integrates an extensive dataset overview, and introduces a comparative framework to evaluate their engineering applicability.