Have a Question ?
Ask about our products, services, or latest research. Let's discuss how we can help you solve your problem.
Intelligent Threshold Prediction in Hybrid Mesh Segmentation using Machine Learning Classifiers
Vaibhav J Hase, Yogesh J Bhalerao, Saurabh Verma, Vishnu D Wakshaure, G J Vikhe Patil
Volume 8, Issue IX, September 2018
International Journal of Management, Technology And Engineering
September 2018
2nd International Conference on Emerging Trends in Science, Engineering & Technology, Pune, India
This paper reports an algorithm to recognize complex intersecting holes from CAD mesh models based on hybrid mesh segmentation. The algorithm involves three steps viz. preprocessing, hybrid mesh segmentation and hole recognition. In the preprocessing step, we build a topology of the imported CAD mesh model. In the Hybrid Mesh Segmentation step, we cluster facets into groups based on mesh attributes. The facets in the clusters are then subjected to several conformal tests, to identify the type of analytical surface it might be representing, such as a plane, cylinder, cone, torus or sphere. In this research, a rule-based approach is used for compound hole detection along with hole chains. This algorithm has been implemented in VC++ and has been extensively tested on models taken from NIST repository for complex intersecting holes. The innovation lies in complex intersecting hole detection and parameterization. The proposed approach outperforms the existing techniques favorably and is found to be robust and consistent. This extracted feature information can be utilized during all stages of the design-to-manufacturing cycle.
Want to know more about this work ?
Ask about this publication or similar work. Get in touch with the paper author.