A contemporary study into the application of neural network techniques employed to automate CAD/CAM integration for die manufacture

Ding, Lian; Matthews, Jason

Abstract

In recent years, collaborative research between academia and industry has intensified in finding a successful approach to take the information from a computer generated drawings of products such as casting dies, and produce optimal manufacturing process plans. Core to this process is feature recognition. Artificial neural networks have a proven track record in pattern recognition and there ability to learn seems to offer an approach to aid both feature recognition and process planning tasks. This paper presents an up-to-date critical study of the implementation of artificial neural networks (ANN) applied to feature recognition and computer aided process planning. In providing this comprehensive survey, the authors consider the factors which define the function of a neural network specifically: the net topology, the input node characteristic, the learning rules and the output node characteristics. In additions the authors have considered ANN hybrid approaches to computer aided process planning, where the specific capabilities of ANN's have been used to enhance the employed approaches. © 2009 Elsevier Ltd. All rights reserved.

Citation

Ding, L., & Matthews, J. (2009). A contemporary study into the application of neural network techniques employed to automate CAD/CAM integration for die manufacture. Computers and Industrial Engineering, 57(4), 1457-1471. https://doi.org/10.1016/j.cie.2009.01.006

• Journal Article Type: Short Survey
• Publication Date: Nov 1, 2009
• Journal: Computers and Industrial Engineering
• Print ISSN: 0360-8352
• Publisher: Elsevier
• Peer Reviewed: Peer Reviewed
• Volume: 57
• Issue: 4
• Pages: 1457-1471
• DOI: https://doi.org/10.1016/j.cie.2009.01.006
• Keywords: computer aided process planning, feature recognition, artificial neural networks, casting die machining
• Public URL: https://uwe-repository.worktribe.com/output/990888
• Publisher URL: http://dx.doi.org/10.1016/j.cie.2009.01.006