Optimisation and Output Forecasting Using Taguchi-Neural Network Approach
Date Published: 2006-04-03
Paper Number:2006-01-1618
DOI: 10.4271/2006-01-1618
Citation:
Dukkipati, R., Srinivas, J., and Chandra Mouli, K., "Optimisation and Output Forecasting Using Taguchi-Neural Network Approach," SAE Technical Paper 2006-01-1618, 2006, doi:10.4271/2006-01-1618.
The paper proposes an approach based on Taguchi’s method to predict the optimum process parameters and forecasts the outputs at these parameters using neural networks. The predicted data from Taguchi’s Design of Experiments (DOE) is quite useful in obtaining optimised output parameters, using some regression models. In multiple input (MI) systems, with no cost function defined explicitly in terms of system variables, Taguchi’s solution provides best accurate alternative. Neural networks on the other hand provide the output corresponding to the optimum process parameters obtained in Taguchi method. A case study demonstrates the approach. Results are presented in the form of graphs and tables.
Purchase more technical papers and save! With TechSelect,
you decide what SAE Technical Papers you need, when you need them, and how much you want to pay.
Learn more >
