Scholarlink

<p>The growing demand for high-quality, flexible, and efficiently produced components with minimal material waste has driven the need for advanced manufacturing processes. Despite the widespread adoption of computers in manufacturing, the seamless integration of Computer-Aided Design (CAD) and Computer-Aided Manufacturing (CAM) remains a significant challenge. Feature Recognition (FR) serves as a critical link in bridging this gap by enabling the automated identification of geometric features essential for manufacturing processes. This study presents a novel methodology for extracting and classifying rotational features into three categories: primary features (cylindrical, conical, and toroidal surfaces), secondary features (chamfers, fillets, and threads), and C-axis features (radial and axial holes). The developed algorithms PTFRA for primary features, STFRA for secondary features, and CT FRA for C-axis features utilize Boundary Representation (B-Rep) data extracted from STEP AP214 files as input. A benchmark problem was used to validate these algorithms, demonstrating their accuracy and reliability in identifying various features. Results from problem showed that, using B-Rep data from STEP AP214, the system successfully identified cylinders, cones, toroids, chamfers, fillets, threads, and radial/axial holes, including cases of intersecting features. This benchmark testing demonstrated accurate and reliable recognition, showing that the methodology can serve as a robust input to CAPP and CAM workflows. When integrated with prismatic feature recognition algorithms, this methodology can further enhance its applicability to a wide range of industrial scenarios.</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

A novel approach to classification and automated feature extraction for rotational parts using STEP AP214 file

  • 期刊论文

  • 发表日期：

    2025年9月17日

查看全文
  • Sridhar Meka,
  • Sreeramulu Dowluru,
  • Lingaraju Dumpala

摘要

The growing demand for high-quality, flexible, and efficiently produced components with minimal material waste has driven the need for advanced manufacturing processes. Despite the widespread adoption of computers in manufacturing, the seamless integration of Computer-Aided Design (CAD) and Computer-Aided Manufacturing (CAM) remains a significant challenge. Feature Recognition (FR) serves as a critical link in bridging this gap by enabling the automated identification of geometric features essential for manufacturing processes. This study presents a novel methodology for extracting and classifying rotational features into three categories: primary features (cylindrical, conical, and toroidal surfaces), secondary features (chamfers, fillets, and threads), and C-axis features (radial and axial holes). The developed algorithms PTFRA for primary features, STFRA for secondary features, and CT FRA for C-axis features utilize Boundary Representation (B-Rep) data extracted from STEP AP214 files as input. A benchmark problem was used to validate these algorithms, demonstrating their accuracy and reliability in identifying various features. Results from problem showed that, using B-Rep data from STEP AP214, the system successfully identified cylinders, cones, toroids, chamfers, fillets, threads, and radial/axial holes, including cases of intersecting features. This benchmark testing demonstrated accurate and reliable recognition, showing that the methodology can serve as a robust input to CAPP and CAM workflows. When integrated with prismatic feature recognition algorithms, this methodology can further enhance its applicability to a wide range of industrial scenarios.