Optimisation and Output Forecasting Using Taguchi-Neural Network Approach 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.
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, https://doi.org/10.4271/2006-01-1618. Download Citation
Author(s):
Rao V. Dukkipati, J. Srinivas, K. V. V. Chandra Mouli
Pages: 7
Event:
SAE 2006 World Congress & Exhibition
ISSN:
0148-7191
e-ISSN:
2688-3627
Also in:
Reliability and Robust Design in Automotive Engineering, 2006-SP-2032
Related Topics:
Neural networks
SAE MOBILUS
Subscribers can view annotate, and download all of SAE's content.
Learn More »
