Laminae-based feature recognition

IEEE, 2020

The computer aided design and manufacturing CAD/CAM integration systems were focused on product representation techniques or product modeling. In product design process trends are currently tend to use freeform surface that modeling by using (Non-Uniform Rational B-Spline Surface (NURBS), B-spline, Bezier) technique to suit aesthetic, functional and manufacturability requirements. Set of problem are faced difficulties in recognizing freeform feature such polishing process after the finishing machining process by multi-axis CNC machine, sheet metal forming, and freeform surface machining. In this research, a new developed methodology has been introduced for automatic recognition of the depression and protrusion features. The 3D CAD solid model is designed by freeform surfaces of non-uniform B-spline technique and then extracts their parameter by IGES standard format file. The developed methodology has four major steps: Subdivision of Non-uniform B-spline surface, surface analysis, primitives shape detection, and recognition of geometric features.

2009

The detailed development phase in modern engineering project lifecycles is characterised by the iterative use of a number of engineering software tools. Inefficient integration between these tools often results in a high volume of manual data manipulation, for example the derivation of analysis and manufacturing models from detailed design models.

2001

Computer aided design (CAD) and computer aided manufacturing (CAM) systems are now indispensable tools for all stages of product development. The¯exibility and ease of use of these systems has dramatically increased productivity and quality of product while reducing lead times. These advances have been largely achieved by automating individual tasks. At present, these islands of automation are poorly linked. One reason for this is that current computer systems are unable to extract geometric and topological information automatically from solid models that is relevant to the downstream application. In other words, feature information. The objective of the research reported in this paper was to develop a more generic methodology than heretofore, in order to ®nd the generic protrusion and depression features of a CAD model. The approach taken is one relying on a more human type of analysis, one that is``viewer-centered'' as opposed to the object-centered approach of most previous research in this area. The viewer-centered approach to feature recognition described is based on a novel geometric probing or tomographic methodology. A ®ve-step algorithm is described and then applied to a number of components by way of illustration.

Mathematics

Feature Recognition (FR) in Computer-aided Design (CAD) models is central for Design and Manufacturing. FR is a problem whose computational burden is intractable (NP-hard), given that its underlying task is the detection of graph isomorphism. Until now, compromises have been reached by only using FACE-based geometric information of prismatic CAD models to prune the search domain. Responding to such shortcomings, this manuscript presents an interactive FR method that more aggressively prunes the search space with reconfigurable geometric tests. Unlike previous approaches, our reconfigurable FR addresses curved EDGEs and FACEs. This reconfigurable approach allows enforcing arbitrary confluent topologic and geometric filters, thus handling an expanded scope. The test sequence is itself a graph (i.e., not a linear or total-order sequence). Unlike the existing methods that are FACE-based, the present one permits combinations of topologies whose dimensions are two (SHELL or FACE), one (LO...

2000

In this paper we report on our work on a CAD model-based object recognition system for industrial parts. We present a novel approach which uses information derived from the CAD model in the early process of range image segmentation. This approach gives an exact classification of the range image enabling the development of a CAD based object recognition system. We describe the feature extraction from CAD data and its use in the curvature based range image classification. We carried out experiments with data from multiple sources. The results obtained are presented and discussed.

Automatic punch shape recognition is an important task in the design automation of progressive dies. Many researchers have proposed and used different techniques to solve this problem by extracting shape information of 2D objects. To recognize the punch shape, the overall shapes of two-dimensional profiles are automatically recognized using a shape recognition technology in a computer aided system. When a profile is input from a CAD system for shape recognition, its CAD data is translated into shape data and input to the pattern recognition device. Upon successful recognition of a shape, the shape code will be composed and its dimension values will be extracted. Traditional linear, angular, diametric, radial, fillet, and chamfer dimensions are automatically created for the profile with the linear factor and dimension distance being parameters controlled by the end user given in a configuration module. As an application of the technology, an application is developed to create auto-di...

Product Modeling for Computer Integrated Design and Manufacture, 1997

Fax+ 39 106475660 Feature technology is now becoming popular in most advanced CAD systems. However, feature recognition processes are still necessary both to derive design feature-based description from traditional geometric representations for redesign purposes and to create feature-based description for driving downstream applications. One of the main limitations in existing automatic feature recognition systems is the inability of identifying simple features when feature faces and edges have been split or destroyed as a consequence of the interaction with other features. In this paper, a method for identifying such situations by means of geometric reasoning is presented. The proposed system is able to recognize not only generic features but also specific instances of application features with their defining parameter relations and values.

Product Modeling for Computer Integrated Design and Manufacture, 1997

This paper describes the results from a research project into Feature Recognition, carried out at the University of Liverpool, Department of Industrial Studies between April 1994 and July 1996, which was funded by the Engineering and Physical Sciences Research Council of the United Kingdom under grant GR/J/97458. After a brief exposition of the ongoing need for feature recognition, even within a designby-features context, the paper identifies previous work most influential in this project, and then presents the project objective of building a programmable feature recogniser in which the input feature descriptions do not need either to pander to the specific data structures of the solid {or other) modeller holding the domain, or to express a recognition algorithm. The characterisation of features is then discussed and the range of domains in which recognition might need to take place. This leads on to the presentation of a basic, correct but inefficient algorithm for generic recognition, and a substantial section on how the inefficiency can be rectified while retaining correctness. 1 WHY FEATURE RECOGNITION ? When feature recognition research started, solid models were solid models, representing geometry, but nothing else. Any application which needed to access that geometry intelligently had problems, because the structures giving explicit meaning to the shape were absent. Now, however, we have feature-based modellers and they are used in design-by-features CAD systems. The argument is therefore that it should be unnecessary to recognise features; they should already be explicit in the CAD-system's database. This is largely true. Although various kinds of hole are excellent examples for feature recognisers to use in demonstrations, they are totally unrealistic as examples of typical usage, because they will almost certainly have been designed as such.

Computer Vision and Image Understanding, 1997

samy and Langrana . Like the other vectorizing methods published in the literature , the line extraction algo-Algorithms to identify 2-D geometric features from the vectorized form of a scanned engineering drawing have been develrithms (such as line tracking and curve fitting) used in oped. These are based on a pattern matching process where RENDER are based on low level local processing which the entities present in the vectorized drawing are checked for introduces errors in the recognized entities. The vectorizaspecific pattern primitives. The pattern primitives present in tion algorithm uses a number of parameters to alleviate an entity are compared with the overall direction of the entity this problem; however, these problems have not been comto arrive at the 2-D features that are present. A library of pletely solved 5]. A post-processing system called P- RENDER [11] was developed to correct the errors intropurposes. For 3-D reconstruction and feature recognition a duced during vectorization. P-RENDER re-creates the separation reference point is first found in order to group the output obtained from RENDER. It includes procedures entities into their respective views, i.e., top, front, and right side for attribute assignment, re-creation of arcs, recognition view. This separation reference point is then used to transfer the points belonging to the three orthographic views, expressed in of dashed lines, and global alignment of the points in the 2-D coordinate system, to a 3-D coordinate system. The 2the drawing.

Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture, 2007

Automatic Feature Recognition (AFR) techniques applied to 3D solid models are an important tool for achieving a true integration of Computer-Aided Design (CAD) and

Computers in Industry, 1984

Applied Mechanics and Materials, 2012

Manufacturing is one of the main source of income for a developing country, like Malaysia. Start from the beginning of need in the market, a new concept of product is created. From the initial idea based on a need, this idea is hard to be understood if not presented in any form of drawing or prototype. So, computer-aided design (CAD) has the greatest role in helping to visualise the initial concept of a design with presenting the idea in a graphical view. However, this type of data cannot be used directly for the manufacturing process and normally intervention of human effort is needed to define all the manufacturing features from the component drawing again. This work is laborious if not assisted by computer technology. As a result, this paper aims to design a system and database which has the ability to extract geometrical features from drawings and identify all the manufacturing features which is useful for manufacturing process. This project takes a neutral drawing format, ISO 1...

The paper points out how the recognition activity is a useful tool to realize the integration of design activities with manufacturing, handling, assembling etc…The concept on which the system is based is the possibility to utilize, in processes from the design to the manufacturing of a mechanical part, a common model for solid model representation and a set of tools which permits in different contexts, the extraction of information useful to carry out the activities within the considered context. The goal of the paper is to present a prototype of an expert system for the automatic recognition of form features. The system is founded on a rule-based architecture that allows a great flexibility and an easy adaptation to different contexts. The objects are described by using a boundary representation. The recognitions rules are formalized using a particular rewriting system called CAIL (Conditional Attributed Interactive Lindenmayer system).

Journal of Materials Processing Technology, 2006

In the last years more and more people have been having access to the Internet, which has reduced or even eliminated the distances among people and/or groups located physically distant among them. The Internet has also enabled the development of applications for the support to the design and manufacturing activities of industrial parts. In this work, a system will be presented for the recognition of features in cylindrical parts created with the ACIS solid modeling kernel through the Internet. In the part design stage, the user inputs in the browser the elements that compose the part. These data are analyzed, and if there is no inconsistency, they are sent via Common Gateway Interface (CGI) to the software that is in the server. To visualize the part, the file with the solid in the Standard ACIS Text (SAT) format is transformed into the Virtual Reality Markup Language (VRML) format, and soon afterwards it is sent to browser of the remote user. The part may contain cylinders, cones and chamfers. The user can slice the part along the rotation axis, and he can also obtain the file in the SAT format from the server, in case he wants to handle the part in his own CAD software. After finishing the design of the part, the software recognizes the features in the part, which it is accomplished through the automatic analysis of half of the profile of the part in 2D. These features can be used in the process of generating the NC program for the CNC machine.

Computers in Industry, 2010

This paper presents a new hybrid (graph + rule based) approach for recognizing the interacting features from B-Rep CAD models of prismatic machined parts. The developed algorithm considers variable topology features and handles both adjacent and volumetric feature interactions to provide a single interpretation for the latter. The input CAD part model in B-Rep format is preprocessed to create the adjacency graphs for faces and features of associated topological entities and compute their attributes. The developed FR system initially recognizes all varieties of the simple and stepped holes with flat and conical bottoms from the feature graphs. A new concept of Base Explicit Feature Graphs and No-base Explicit Feature Graphs has been proposed which essentially delineates between features having planar base face like pockets, blind slots, etc. and those without planar base faces like passages, 3D features, conical bottom features, etc. Based on the structure of the explicit feature graphs, geometric reasoning rules are formulated to recognize the interacting feature types. Extracted data has been post-processed to compute the feature attributes and their parent-child relationships which are written into a STEP like native feature file format. The FR system was extensively tested with several standard benchmark components and was found to be robust and consistent. The extracted feature file can be used for integration with various downstream applications like CAPP.