应用特征识别的神经网络模增强塑料部件.docVIP

Application of neural networks in feature recognition of mould reinforced plastic parts HYPERLINK /search/results/quick.url?CID=quickSearchCitationFormatsearchWord1={Marquez,+M.}section1=AUdatabase=1yearselect=yearrangesort=yrMarquez, M.1, 3, 4, 5; HYPERLINK /search/results/quick.url?CID=quickSearchCitationFormatsearchWord1={Gill,+R.}section1=AUdatabase=1yearselect=yearrangesort=yrGill, R.2, 6, 7; HYPERLINK /search/results/quick.url?CID=quickSearchCitationFormatsearchWord1={White,+A.}section1=AUdatabase=1yearselect=yearrangesort=yrWhite, A.2, 6 Source: Concurrent Engineering Research and Applications, v 7, n 2, p 115-122, June 1999; ISSN: 1063293X; Publisher: Technomic Publ Co Inc Author affiliations: 1 Universidad Nacional Experimental del Tachira (UNET), San Cristobal, Venezuela 2 School of Engineering Systems, Middlesex University, London, United Kingdom 3 Middlesex University, School of Engineering Systems, Bounds Green Road, N11 2NQ, London, United Kingdom 4 Universidad Nacional Experimental del Tachira (UNET, Venezuela) 5 Middlesex University, London, United Kingdom 6 School of Engineering Systems, Middlesex University 7 Cambridge University Manufacturing Group Abstract: Feature recognition is an application dependant task, which has been mostly focused in production planning of machining process. It plays a fundamental role and usually is the first step in downstream activities concerning product development process such as design for manufacturing, design for assembly and process planning. This report presents a methodology to carry out recognition of design for manufacturing features of reinforced plastic components. A three-layer neural network system was created and trained using back-propagation-supervised learning to recognise nine of the most important design features related to this manufacturing process. Also, a methodology for pre-processing 3-D solid models such that geometrical and topological information of the part could be suitable as network