WIT Press


On The Limitations Of Neural Network Techniques For Analysing Cause And Effect Relationships In Manufacturing Processes – A Case Study

Price

Free (open access)

Paper DOI

10.2495/DATA030491

Volume

29

Pages

10

Published

2003

Size

476 kb

Author(s)

R. S. Ransing, M. R. Ransing & R. W. Lewis

Abstract

On the limitations of neural network techniques for analysing cause and effect relationships in manufacturing processes - a case study R. S. Ransing, M. R. Ransing & R. W. Lewis Civil and Computational Engineering Research Centre, School of Engineering, University of Wales Swansea, SA2 8PP, UK Abstract The cause and effect relationship is complex for many manufacturing processes. The ability to learn causal relationships from diagnostic examples is extremely useful. This learning ability can help not only to quantify the influence of causes on defects for existing components but also to set up new process, material and design parameters to manufacture new components. A neural network approach that can adapt and learn from past examples, was explored for analysing and quantifying cause and effect relationships. Neural networks use the data to extract any pre-existing relationships between the input and output variables. However, in many real situations very few good quality training examples ar

Keywords