Automatic hole recognition and classification for a set of B-rep models representing an injection mold

Jiing Yih Lai; Pei Pu Song; Yao Chen Tsai; Chia Hsiang Hsu

doi:10.18178/ijmerr.9.8.1189-1197

Automatic hole recognition and classification for a set of B-rep models representing an injection mold

Jiing Yih Lai, Pei Pu Song, Yao Chen Tsai, Chia Hsiang Hsu

Department of Mechanical Engineering

Research output: Contribution to journal › Article › peer-review

Abstract

A hole recognition algorithm for all hole types in a mold set is proposed. The algorithm can recognize holes of both circular and non-circular types, and blind and through types. It can also detect ladder holes, each of which is composed of a series of holes connected in sequence, and related holes that pass across different CAD models. The proposed hole recognition algorithm is divided into five steps: (1) facial composition is searched for each hole, (2) the holes are evaluated as either through or blind, (3) related holes are detected on each CAD model, (4) related holes passing across different CAD models are detected, and (5) data is output. Three mold sets were used to demonstrate the feasibility of the proposed method, and the results were compared with those from commercial software.

Original language	English
Pages (from-to)	1189-1197
Number of pages	9
Journal	International Journal of Mechanical Engineering and Robotics Research
Volume	9
Issue number	8
DOIs	https://doi.org/10.18178/ijmerr.9.8.1189-1197
State	Published - 1 Aug 2020

Keywords

B-rep model
Feature classification
Feature recognition
Hole recognition
Injection mold

Access to Document

10.18178/ijmerr.9.8.1189-1197

Cite this

@article{bbd08a5555074f579137f8ce99f7e995,

title = "Automatic hole recognition and classification for a set of B-rep models representing an injection mold",

abstract = "A hole recognition algorithm for all hole types in a mold set is proposed. The algorithm can recognize holes of both circular and non-circular types, and blind and through types. It can also detect ladder holes, each of which is composed of a series of holes connected in sequence, and related holes that pass across different CAD models. The proposed hole recognition algorithm is divided into five steps: (1) facial composition is searched for each hole, (2) the holes are evaluated as either through or blind, (3) related holes are detected on each CAD model, (4) related holes passing across different CAD models are detected, and (5) data is output. Three mold sets were used to demonstrate the feasibility of the proposed method, and the results were compared with those from commercial software.",

keywords = "B-rep model, Feature classification, Feature recognition, Hole recognition, Injection mold",

author = "Lai, {Jiing Yih} and Song, {Pei Pu} and Tsai, {Yao Chen} and Hsu, {Chia Hsiang}",

note = "Publisher Copyright: {\textcopyright} 2020 Int. J. Mech. Eng. Rob. Res.",

year = "2020",

month = aug,

day = "1",

doi = "10.18178/ijmerr.9.8.1189-1197",

language = "???core.languages.en_GB???",

volume = "9",

pages = "1189--1197",

journal = "International Journal of Mechanical Engineering and Robotics Research",

issn = "2278-0149",

number = "8",

}

TY - JOUR

T1 - Automatic hole recognition and classification for a set of B-rep models representing an injection mold

AU - Lai, Jiing Yih

AU - Song, Pei Pu

AU - Tsai, Yao Chen

AU - Hsu, Chia Hsiang

PY - 2020/8/1

Y1 - 2020/8/1

N2 - A hole recognition algorithm for all hole types in a mold set is proposed. The algorithm can recognize holes of both circular and non-circular types, and blind and through types. It can also detect ladder holes, each of which is composed of a series of holes connected in sequence, and related holes that pass across different CAD models. The proposed hole recognition algorithm is divided into five steps: (1) facial composition is searched for each hole, (2) the holes are evaluated as either through or blind, (3) related holes are detected on each CAD model, (4) related holes passing across different CAD models are detected, and (5) data is output. Three mold sets were used to demonstrate the feasibility of the proposed method, and the results were compared with those from commercial software.

AB - A hole recognition algorithm for all hole types in a mold set is proposed. The algorithm can recognize holes of both circular and non-circular types, and blind and through types. It can also detect ladder holes, each of which is composed of a series of holes connected in sequence, and related holes that pass across different CAD models. The proposed hole recognition algorithm is divided into five steps: (1) facial composition is searched for each hole, (2) the holes are evaluated as either through or blind, (3) related holes are detected on each CAD model, (4) related holes passing across different CAD models are detected, and (5) data is output. Three mold sets were used to demonstrate the feasibility of the proposed method, and the results were compared with those from commercial software.

KW - B-rep model

KW - Feature classification

KW - Feature recognition

KW - Hole recognition

KW - Injection mold

UR - http://www.scopus.com/inward/record.url?scp=85088867347&partnerID=8YFLogxK

U2 - 10.18178/ijmerr.9.8.1189-1197

DO - 10.18178/ijmerr.9.8.1189-1197

M3 - 期刊論文

AN - SCOPUS:85088867347

SN - 2278-0149

VL - 9

SP - 1189

EP - 1197

JO - International Journal of Mechanical Engineering and Robotics Research

JF - International Journal of Mechanical Engineering and Robotics Research

IS - 8

ER -

Automatic hole recognition and classification for a set of B-rep models representing an injection mold

Abstract

Keywords

Access to Document

Fingerprint

Cite this