Neural-Taguchi, a new engineering analysis method that combines the neural-network and the Taguchi techniques for better improvement of engineering design is proposed in this paper. Explicit system model that allows precise prediction and easy optimizing is constructed in terms of a multilayer feedforward neural network. Advantages and good performances of the proposed Neural-Taguchi method are well illustrated by a die cast component analysis problem.

This content is only available via PDF.
You do not currently have access to this content.