Automotive
Technical Paper

A Comparison of Neural Networks and Wavelets Networks for Predicting Creep and Rupture Resistance of Ferritic Steels

2007-01-2827

11/28/2007

Event
SAE Brasil 2007 Congress and Exhibit
Authors
Renata Neves Penha Universidade de São Paulo, São Carlos, SP, Brazil
Lauralice C. Franceschini Canale Universidade de São Paulo, São Carlos, SP, Brazil
Abstract
Content
This work is based in a model of neural and wavelets networks using published experimental data. The objective is to compare a neural and a wavelet network estimating the creep rupture strength based on chemical composition of Fe-2.25Cr-Mo and Fe-(9-12)Cr steels, and on its heat treatment temperature and life time. It will be determined the configuration that provides the best fit of the data.
Meta Tags
Topics
Neural networks
Heat treatment
Drag
Chemicals
Affiliated or Co-Author
Universidade de São Paulo, São Carlos, SP, Brazil
Details
DOI
https://doi.org/10.4271/2007-01-2827
Pages
8
Citation
Penha, R., and Franceschini Canale, L., "A Comparison of Neural Networks and Wavelets Networks for Predicting Creep and Rupture Resistance of Ferritic Steels," SAE Technical Paper 2007-01-2827, 2007, https://doi.org/10.4271/2007-01-2827.
Additional Details
Publisher
SAE International
Published
Nov 28, 2007
Product Code
2007-01-2827
Content Type
Technical Paper
Language
English