A Neural Network Approach To Tolerance Synthesis And Cost Optimization In Assembly

JFET_V5_N2_RP2 A Neural Network Approach To Tolerance Synthesis And Cost Optimization In Assembly K. Jayaram J.K. Sankaranarayanasamy S. Arunachalam Tom Page Journal on Future Engineering and Technology 2230 – 7184 5 2 9 16 Multi Layer Perceptron, Artificial Neural Networks, Tolerance Synthesis, Cost-Tolerance Relationship, Regression Analysis Tolerance synthesis directly influences the functionality of products and their related production costs. The problem of synthesis is to discretise tolerances without affecting overall product functionality. A promising method of tolerance synthesis is to assign component tolerances that minimize the cost of production of an assembly. In this paper, a neural network is applied to fit the cost-tolerance relationship. The neural network has been reported to be an effective tool for determining the relationship between input factor and output responses. The accompanying case studies are used to investigate the efficiency and effectiveness of the proposed methodology. November 2009 - January 2010 Copyright © 2010 i-manager publications. All rights reserved. i-manager Publications http://www.imanagerpublications.com/Article.aspx?ArticleId=1090