Mapping the input–output relationship in HSLA steels through expert neural network

Modification of the architecture of the artificial neural network is done to accommodate the information available from the knowledge base in the field of materials science for thermomechanically processed HSLA steel. The complicated architectures of these networks are made to satisfy the well-under...

Full description

Saved in:
Bibliographic Details
Published in:Materials science & engineering. A, Structural materials : properties, microstructure and processing Structural materials : properties, microstructure and processing, 2006-03, Vol.420 (1-2), p.254-264
Main Authors: Datta, S., Banerjee, M.K.
Format: Article
Language:English
Subjects:
Applied sciences
Artificial neural network
Automation. Data processing
Composition
Cross-disciplinary physics: materials science
rheology
Engineering techniques in metallurgy. Applications. Other aspects
Exact sciences and technology
Heat treatment
HSLA steel
Management. Ergonomics. Economics. Business administration
Materials science
Metals. Metallurgy
Other heat and thermomechanical treatments
Physics
Process parameters
Production techniques
Thermomechanical treatment
Thermomechanical-controlled processing
Treatment of materials and its effects on microstructure and properties
Yield strength
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Modification of the architecture of the artificial neural network is done to accommodate the information available from the knowledge base in the field of materials science for thermomechanically processed HSLA steel. The complicated architectures of these networks are made to satisfy the well-understood physical metallurgy principles, which administer the property response to the combined actions of the compositional and process parameters. The networks developed have been found to give very good convergence during training. The number of epochs required to reach the targeted error was found less for these networks than the conventional networks.
ISSN:0921-5093
1873-4936
DOI:10.1016/j.msea.2006.01.037