Some speculations on feature recognition

Woodwark, John

doi:10.1016/0010-4485(88)90276-x

Cited by 72 publications

(12 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most of the feature recognition systems developed up to today are solid modeller dependent, and are either CSG-based or B-rep-based systems. The systems developed by Woo (1982), Woodwark (1988), Perng et al (1990), Sakurai and Chin (1993), Kim (1994), and Parry- Barwick and Bowyer (1995) are examples of the ® rst category, whereas systems developed by Kyprianou (1980), Henderson (1984), Joshi and Chang (1988), Sakurai and Gossard (1988), Vandenbrande and Requicha (1990), Hwang (1991), Prabhakar and Henderson (1992), Tseng and Joshi (1994), Chan (1994), Sakurai (1995), Gu et al (1995), and Nezis and Vosniakos (1997) are based on B-rep models.…”

Section: Literature Reviewmentioning

confidence: 98%

Feature patterns in recognizing non-interacting and interacting primitive, circular and slanting features using a neural network

Zulkifli

1999

International Journal of Production Research

View full text Add to dashboard Cite

Many varied techniques have long been suggested for the recognition of features from solid modellers, and the systems which have incorporated these techniques have achieved a moderate success. However the problem of recognition of the wide variety of features, e.g. interacting and non-interacting primitive, circular and slanting features, that any real life component may have, requires complex systems which are in¯exible and hence limited in their use. Here, we present a simple and¯exible system in which the features are de® ned as patterns of edges and vertices to deal with all the above types of features. The system starts by searching a B-rep solid model, using a cross-sectional layer method, for volumes which can be considered to represent features. Once the volumes are detected, their edges and vertices are processed and arranged into feature patterns which are used as input for a neural network to recognize the features. Simple conventions used in this work enable the creation of feature patterns for primitive, circular and slanting features. Learning, generalizing and tolerating incomplete data are some of the neural network's attributes exploited in this work to deal with interacting and non-interacting features.

show abstract

Section: Literature Reviewmentioning

confidence: 98%

Feature patterns in recognizing non-interacting and interacting primitive, circular and slanting features using a neural network

Zulkifli

1999

International Journal of Production Research

View full text Add to dashboard Cite

show abstract

“…The process of identifying features is callcd feature recognition or feature extraction. There are Wei and Egbelu five techniques that are most commonly reported for feature recognition: (1) syntactic pattern recognition [20][21][22][23][24][25]; (2) set theoretic approach [ 15,16,18,26,27]; (3) expert system/logic approach [ 10, 20,28]; (4) graph-based approach [29,12,14], and (5) geometric pattern recognition [I 7,30-…”

Section: Review Of Previous Relevant Workmentioning

confidence: 99%

Process alternative generation from product geometric design data

Wei¹,

Egbelu²

2000

IIE Transactions

View full text Add to dashboard Cite

A fundamental element in operating a competitive manufacturing system is the ability to control material, cost, and other production resources required to transform the raw material to a finished product. To successfully control cost, it is essential that a reliable assessment of the tasks required to manufacture the product be made. This involves identifying the operations and the machine tools required. In this research, a method of decomposing polyhedral components to generate all possible ways to process the part is presented. The technique takes as input the geometric design data of the product, analyzes and interprets the design to identify the volume of material to be machined out from the raw material block to obtain the finished product. The volume of material to be removed are characterized to generate various approach directions from which the material can be machined out.The alternate tool approach directions are used to construct an AND/OR graph that captures the process alternatives. Using this graphical representation, a model is proposed for selecting the best process plan based on some user defined criterion. The developed procedure can be integrated into a CAD/CAM system to provide the required linkage between design and manufacturing and thus, automate a critical link in manufacturing.

show abstract

“…According to Woodwark (1988) feature recognition is 'the recognition of expected patterns of geometry, corresponding to particular engineering functionality'. He goes on to say that 'shapes should "look different" when being considered for different processes', a sentiment widely held as a goal of feature recognition research.…”

Section: Other Areas Of Applicationmentioning

confidence: 99%

Feature recognition within a truth maintained process planning system

Herbert

Hinde

Bray

et al. 1990

International Journal of Computer Integrated Manufacturing

View full text Add to dashboard Cite

A major problem for computer aided process planning (CAPP) is the difference in data representation between the design and planning stages. Computer aided design (CAD) uses a data representation which is suited to solid modelling but is impractical for process planning. A partial solution to the non-unique nature of the set-theoretic solid model is detailed.A method of feature recognition for the set-theoretic solid model, together with its implementation in a process planning system is described. It is essentially a rule-based conversion of the CSG string into a set of manufacturing features. One or more alternative ways of viewing the component in terms of features are produced, and user interaction may be required to determine the best set of features to process plan with.

show abstract

Some speculations on feature recognition

Cited by 72 publications

References 22 publications

Feature patterns in recognizing non-interacting and interacting primitive, circular and slanting features using a neural network

Feature patterns in recognizing non-interacting and interacting primitive, circular and slanting features using a neural network

Process alternative generation from product geometric design data

Feature recognition within a truth maintained process planning system

Contact Info

Product

Resources

About