Scholarlink

<p>Sheet metal forming is a critical manufacturing process widely employed in automotive, aerospace, and structural engineering industries, where accurate prediction of forming force, friction behavior, and mechanical properties is essential for ensuring product quality and reducing production cost. In recent years, intelligent modeling techniques have emerged as powerful alternatives for improving predictive accuracy and computational efficiency. This comprehensive review systematically analyzes state-of-the-art intelligent approaches, including Artificial Neural Networks, Support Vector Machines, Deep Learning, Fuzzy Logic Systems, Genetic Algorithms, Particle Swarm Optimization, and hybrid metaheuristic frameworks applied to sheet metal forming processes such as deep drawing, bending, stamping, and rolling. The review critically compares modeling strategies based on prediction accuracy, generalization capability, training complexity, interpretability, and integration with finite element simulations. Additionally, recent advancements in data-driven digital twins, physics-informed machine learning, and multi-objective optimization for force and friction modeling are discussed. This review provides a consolidated technical foundation for researchers and industry practitioners seeking advanced predictive modeling solutions in sheet metal forming.</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

Intelligent Modeling Techniques for Physical and Mechanical Properties Prediction in Sheet Metal Forming: A Comprehensive Review

  • 期刊论文

  • 发表日期：

    2026年6月3日

查看全文
  • V. Shiva Narayana Reddy,
  • Amita Johar,
  • A. Anil Kumar Reddy,
  • M. Ramakanth Reddy,
  • Aseenababu Shaik,
  • Perumalla Janaki Ramulu

摘要

Sheet metal forming is a critical manufacturing process widely employed in automotive, aerospace, and structural engineering industries, where accurate prediction of forming force, friction behavior, and mechanical properties is essential for ensuring product quality and reducing production cost. In recent years, intelligent modeling techniques have emerged as powerful alternatives for improving predictive accuracy and computational efficiency. This comprehensive review systematically analyzes state-of-the-art intelligent approaches, including Artificial Neural Networks, Support Vector Machines, Deep Learning, Fuzzy Logic Systems, Genetic Algorithms, Particle Swarm Optimization, and hybrid metaheuristic frameworks applied to sheet metal forming processes such as deep drawing, bending, stamping, and rolling. The review critically compares modeling strategies based on prediction accuracy, generalization capability, training complexity, interpretability, and integration with finite element simulations. Additionally, recent advancements in data-driven digital twins, physics-informed machine learning, and multi-objective optimization for force and friction modeling are discussed. This review provides a consolidated technical foundation for researchers and industry practitioners seeking advanced predictive modeling solutions in sheet metal forming.