Scholarlink

<p>Plastic gears are critical components in mechanical power transmission systems, widely used in automotive, aerospace, robotics, and industrial machinery. The performance and reliability of gears directly affect the efficiency, safety, and service life of mechanical systems. In particular, plastic gears offer advantages such as low noise and lightweight, making them suitable for emerging applications in electric vehicles and precision automation. Accurate prediction of gear lifetime under realistic operating conditions is essential for intelligent maintenance, sustainable manufacturing, and cost reduction in modern industry. However, high-fidelity simulations demand substantial computational time and resources. To overcome this limitation, this study proposes a data-driven surrogate modeling approach for rapid prediction of the remaining useful life (RUL) of plastic gears. The proposed framework has direct industrial applications for automotive, robotics, automation, and additive manufacturing industries, aiming to improve gear reliability, reduce downtime, and support sustainable production. Moreover, this approach aligns with several United Nations Sustainable Development Goals by promoting resource-efficient production and equipment reliability. The proposed method demonstrates the potential of combining AI-driven modeling with multi-physics simulation for intelligent maintenance strategies in mechanical systems.</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

Process structure performance integrated surrogate modeling for rapid remaining useful life prediction of plastic gears in advanced manufacturing systems

  • 期刊论文

  • 发表日期：

    2026年3月31日

查看全文
  • Chil-Chyuan Kuo,
  • Yu-Heng Cai,
  • Zi-Huan Wang,
  • Armaan Farooqui,
  • Song-Hua Huang

摘要

Plastic gears are critical components in mechanical power transmission systems, widely used in automotive, aerospace, robotics, and industrial machinery. The performance and reliability of gears directly affect the efficiency, safety, and service life of mechanical systems. In particular, plastic gears offer advantages such as low noise and lightweight, making them suitable for emerging applications in electric vehicles and precision automation. Accurate prediction of gear lifetime under realistic operating conditions is essential for intelligent maintenance, sustainable manufacturing, and cost reduction in modern industry. However, high-fidelity simulations demand substantial computational time and resources. To overcome this limitation, this study proposes a data-driven surrogate modeling approach for rapid prediction of the remaining useful life (RUL) of plastic gears. The proposed framework has direct industrial applications for automotive, robotics, automation, and additive manufacturing industries, aiming to improve gear reliability, reduce downtime, and support sustainable production. Moreover, this approach aligns with several United Nations Sustainable Development Goals by promoting resource-efficient production and equipment reliability. The proposed method demonstrates the potential of combining AI-driven modeling with multi-physics simulation for intelligent maintenance strategies in mechanical systems.