OPTIMIZATION WELDING PROCESS PARAMETERS TROUGH RESPONSE SURFACE, NEURAL NETWORK AND GENETIC ALGORITHMS

被引：4

作者：

Praga-Alejo, R. J. ^{[1
]}

Torres-Trevino, L. M. ^{[1
]}

Pina-Monarrez, M. R. ^{[1
]}

机构：

[1] COMIMSA, Saltillo 25290, Coahuila, Mexico

来源：

CERMA 2008: ELECTRONICS, ROBOTICS AND AUTOMOTIVE MECHANICS CONFERENCE, PROCEEDINGS | 2008年

关键词：

Artificial Intelligence; Neural Networks; Regression; Global Optimization; Genetic algorithms;

D O I：

10.1109/CERMA.2008.70

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

Since the Neural Network (NN) with a Genetic Algorithm (GA) as a complement; are good optimization tools, we compare its performance with the Response Surface Methodology (RSM) that is generally used in the optimization of the process, in this case welding process. For the data used in the comparison, the results show that NN plus GA and RSM have a good results and very well performance, for identify the optimal set of parameters to obtain a maximum response of the process.

引用

页码：393 / 399

页数：7

共 23 条

[1] Using genetic algorithm and artificial neural network analyses to design an Al-Si casting alloy of minimum porosity [J].