Computer recognition and extraction of form features

A CAD/CAM link

Mark Henderson, David C. Anderson

Research output: Contribution to journalArticle

136 Citations (Scopus)

Abstract

The future success of CAD and CAM depends on the ability of these two processes to communicate with each other and with the intermediate manufacturing database. CAD-generated objects can be defined and stored as complete geometric and topologic solids. The elements of CAM, however, cannot make full use of the CAD part description because it exists in terms of low-level faces, edges and vertices or primitive volumes usually unrelated to manufacturing processes. Consequently, manufacturing planning continues to depend upon human interpretation of the part definition according to manufacturing needs. The automatic linking of CAD and CAM involves a computer interpretation of the part database to extract manufacturing-specific semantic knowledg about the part. This knowledge can enable process planning and other CAM operations to proceed automatically without human guidance or intervention. A method has been developed to automatically extract manufacturing information in the form of part features. The procedure consists of searching the part description, recognizing cavity features, extracting those features as solid volumes of material to be removed and arranging them in a feature graph, a high level data structure appropriate for manufacturing process planning. The feature recognition step uses logic programming implemented in PROLOG. Using rules of logic, definitions have been formulated to describe some common features of a part, such as holes and slots. The part is represented as a set of facts in a boundary representation format and these facts are searched to satisfy the feature rules. Multiple feature cavities can be separated into their component feature parts. This work has relevance in the areas of CAD/CAm linking, automated process planning, expert systems and, in fact, the interpretation of any 3-D data.

Original languageEnglish (US)
Pages (from-to)329-339
Number of pages11
JournalComputers in Industry
Volume5
Issue number4
DOIs
StatePublished - 1984
Externally publishedYes

Fingerprint

Computer aided manufacturing
Computer aided design
Process planning
PROLOG (programming language)
Logic programming
Manufacturing
Expert systems
Data structures
Semantics
Planning
Data base
Manufacturing process

Keywords

  • CAD
  • CAD database
  • CAD/CAM integration
  • CAM
  • expert systems
  • feature graph
  • form features
  • logic programming
  • process planning
  • PROLOG
  • solid modeling

ASJC Scopus subject areas

  • Computer Science Applications
  • Management Science and Operations Research
  • Industrial and Manufacturing Engineering

Cite this

Computer recognition and extraction of form features : A CAD/CAM link. / Henderson, Mark; Anderson, David C.

In: Computers in Industry, Vol. 5, No. 4, 1984, p. 329-339.

Research output: Contribution to journalArticle

Henderson, Mark ; Anderson, David C. / Computer recognition and extraction of form features : A CAD/CAM link. In: Computers in Industry. 1984 ; Vol. 5, No. 4. pp. 329-339.
@article{4a895f1d977b44c1a2ca3b3878d81f99,
title = "Computer recognition and extraction of form features: A CAD/CAM link",
abstract = "The future success of CAD and CAM depends on the ability of these two processes to communicate with each other and with the intermediate manufacturing database. CAD-generated objects can be defined and stored as complete geometric and topologic solids. The elements of CAM, however, cannot make full use of the CAD part description because it exists in terms of low-level faces, edges and vertices or primitive volumes usually unrelated to manufacturing processes. Consequently, manufacturing planning continues to depend upon human interpretation of the part definition according to manufacturing needs. The automatic linking of CAD and CAM involves a computer interpretation of the part database to extract manufacturing-specific semantic knowledg about the part. This knowledge can enable process planning and other CAM operations to proceed automatically without human guidance or intervention. A method has been developed to automatically extract manufacturing information in the form of part features. The procedure consists of searching the part description, recognizing cavity features, extracting those features as solid volumes of material to be removed and arranging them in a feature graph, a high level data structure appropriate for manufacturing process planning. The feature recognition step uses logic programming implemented in PROLOG. Using rules of logic, definitions have been formulated to describe some common features of a part, such as holes and slots. The part is represented as a set of facts in a boundary representation format and these facts are searched to satisfy the feature rules. Multiple feature cavities can be separated into their component feature parts. This work has relevance in the areas of CAD/CAm linking, automated process planning, expert systems and, in fact, the interpretation of any 3-D data.",
keywords = "CAD, CAD database, CAD/CAM integration, CAM, expert systems, feature graph, form features, logic programming, process planning, PROLOG, solid modeling",
author = "Mark Henderson and Anderson, {David C.}",
year = "1984",
doi = "10.1016/0166-3615(84)90056-3",
language = "English (US)",
volume = "5",
pages = "329--339",
journal = "Computers in Industry",
issn = "0166-3615",
publisher = "Elsevier",
number = "4",

}

TY - JOUR

T1 - Computer recognition and extraction of form features

T2 - A CAD/CAM link

AU - Henderson, Mark

AU - Anderson, David C.

PY - 1984

Y1 - 1984

N2 - The future success of CAD and CAM depends on the ability of these two processes to communicate with each other and with the intermediate manufacturing database. CAD-generated objects can be defined and stored as complete geometric and topologic solids. The elements of CAM, however, cannot make full use of the CAD part description because it exists in terms of low-level faces, edges and vertices or primitive volumes usually unrelated to manufacturing processes. Consequently, manufacturing planning continues to depend upon human interpretation of the part definition according to manufacturing needs. The automatic linking of CAD and CAM involves a computer interpretation of the part database to extract manufacturing-specific semantic knowledg about the part. This knowledge can enable process planning and other CAM operations to proceed automatically without human guidance or intervention. A method has been developed to automatically extract manufacturing information in the form of part features. The procedure consists of searching the part description, recognizing cavity features, extracting those features as solid volumes of material to be removed and arranging them in a feature graph, a high level data structure appropriate for manufacturing process planning. The feature recognition step uses logic programming implemented in PROLOG. Using rules of logic, definitions have been formulated to describe some common features of a part, such as holes and slots. The part is represented as a set of facts in a boundary representation format and these facts are searched to satisfy the feature rules. Multiple feature cavities can be separated into their component feature parts. This work has relevance in the areas of CAD/CAm linking, automated process planning, expert systems and, in fact, the interpretation of any 3-D data.

AB - The future success of CAD and CAM depends on the ability of these two processes to communicate with each other and with the intermediate manufacturing database. CAD-generated objects can be defined and stored as complete geometric and topologic solids. The elements of CAM, however, cannot make full use of the CAD part description because it exists in terms of low-level faces, edges and vertices or primitive volumes usually unrelated to manufacturing processes. Consequently, manufacturing planning continues to depend upon human interpretation of the part definition according to manufacturing needs. The automatic linking of CAD and CAM involves a computer interpretation of the part database to extract manufacturing-specific semantic knowledg about the part. This knowledge can enable process planning and other CAM operations to proceed automatically without human guidance or intervention. A method has been developed to automatically extract manufacturing information in the form of part features. The procedure consists of searching the part description, recognizing cavity features, extracting those features as solid volumes of material to be removed and arranging them in a feature graph, a high level data structure appropriate for manufacturing process planning. The feature recognition step uses logic programming implemented in PROLOG. Using rules of logic, definitions have been formulated to describe some common features of a part, such as holes and slots. The part is represented as a set of facts in a boundary representation format and these facts are searched to satisfy the feature rules. Multiple feature cavities can be separated into their component feature parts. This work has relevance in the areas of CAD/CAm linking, automated process planning, expert systems and, in fact, the interpretation of any 3-D data.

KW - CAD

KW - CAD database

KW - CAD/CAM integration

KW - CAM

KW - expert systems

KW - feature graph

KW - form features

KW - logic programming

KW - process planning

KW - PROLOG

KW - solid modeling

UR - http://www.scopus.com/inward/record.url?scp=0021661703&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0021661703&partnerID=8YFLogxK

U2 - 10.1016/0166-3615(84)90056-3

DO - 10.1016/0166-3615(84)90056-3

M3 - Article

VL - 5

SP - 329

EP - 339

JO - Computers in Industry

JF - Computers in Industry

SN - 0166-3615

IS - 4

ER -