Analyze fillets, chamfers and holes on 3D geometrical STEP file

Sohail, Zunaira (2025) Analyze fillets, chamfers and holes on 3D geometrical STEP file. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (3MB) | Preview
Preview	PDF (Configuration Manual) Download (1MB) | Preview

Abstract

This study presents a systematic method for analyzing fillets, chamfers, and holes on 3D geometric models in the STEP file format. CAD models are exchanged between different software platforms using STEP, a widely used neutral data format. However, due to the complexity of the topological and parametric structures embedded in STEP data, the extraction and interpretation of detailed geometric features such as fillets, chamfers, and holes remains challenging. This study proposes an automatic feature recognition method that combines contour representation analysis (B-Rep), topological adjacency mapping, and curvature classification. The developed algorithm detects edge-to-face relationships and distinguishes between fillets with constant radius, corner chamfers, and cylindrical or conical holes. Experimental validation is performed using various industrial STEP models to evaluate the detection accuracy and computational efficiency. The results demonstrate high reliability in shape classification and feature extraction, enabling applications in manufacturing process planning, design verification, and reverse engineering. This research advances the interaction and automation of CAD/CAM processes through intelligent geometry analysis.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Mattos, Agatha UNSPECIFIED
Uncontrolled Keywords:	3D STEP Files; Geometrical models; ISO 10303 express language; 3D CAD modelling; Analyzing feature through machine learning
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Artificial Intelligence for Business
Depositing User:	Ciara O'Brien
Date Deposited:	03 Sep 2026 08:43
Last Modified:	03 Sep 2026 08:43
URI:	https://norma.ncirl.ie/id/eprint/9782

Actions (login required)

View Item