skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Improved ferrite number prediction in stainless steel arc welds using artificial neural networks -- Part 1: Neural network development

Abstract

Neural network modeling is a powerful nonlinear regression analysis method that is extremely useful in identifying behavioral trends. This methodology was applied to the problem of predicting Ferrite Number in arc welds as a function of composition. This paper describes the details of the development of the neural network model, named FNN-1999, including the identification of the optimum network architecture and network parameters. The model was trained on the same data as the WRC-1992 constitution diagram and covers a range of Ferrite Numbers from 0 to 117, with a corresponding wide range in composition. Results of the model are presented in Part 2. It is shown that the accuracy of the FNN-1999 model in predicting Ferrite Number is superior to the accuracy of other models that are currently available, including the WRC-1992 diagram.

Authors:
; ;
Publication Date:
Research Org.:
Oak Ridge National Lab., TN (US)
Sponsoring Org.:
USDOE
OSTI Identifier:
20014306
DOE Contract Number:  
AC05-96OR22464
Resource Type:
Journal Article
Journal Name:
Welding Journal (Miami)
Additional Journal Information:
Journal Volume: 79; Journal Issue: 2; Other Information: PBD: Feb 2000; Journal ID: ISSN 0043-2296
Country of Publication:
United States
Language:
English
Subject:
36 MATERIALS SCIENCE; 99 MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE; STAINLESS STEELS; MICROSTRUCTURE; WELDED JOINTS; ARC WELDING; NEURAL NETWORKS; FERRITE; CHEMICAL COMPOSITION

Citation Formats

Vitek, J M, Iskander, Y S, and Oblow, E M. Improved ferrite number prediction in stainless steel arc welds using artificial neural networks -- Part 1: Neural network development. United States: N. p., 2000. Web.
Vitek, J M, Iskander, Y S, & Oblow, E M. Improved ferrite number prediction in stainless steel arc welds using artificial neural networks -- Part 1: Neural network development. United States.
Vitek, J M, Iskander, Y S, and Oblow, E M. Tue . "Improved ferrite number prediction in stainless steel arc welds using artificial neural networks -- Part 1: Neural network development". United States.
@article{osti_20014306,
title = {Improved ferrite number prediction in stainless steel arc welds using artificial neural networks -- Part 1: Neural network development},
author = {Vitek, J M and Iskander, Y S and Oblow, E M},
abstractNote = {Neural network modeling is a powerful nonlinear regression analysis method that is extremely useful in identifying behavioral trends. This methodology was applied to the problem of predicting Ferrite Number in arc welds as a function of composition. This paper describes the details of the development of the neural network model, named FNN-1999, including the identification of the optimum network architecture and network parameters. The model was trained on the same data as the WRC-1992 constitution diagram and covers a range of Ferrite Numbers from 0 to 117, with a corresponding wide range in composition. Results of the model are presented in Part 2. It is shown that the accuracy of the FNN-1999 model in predicting Ferrite Number is superior to the accuracy of other models that are currently available, including the WRC-1992 diagram.},
doi = {},
journal = {Welding Journal (Miami)},
issn = {0043-2296},
number = 2,
volume = 79,
place = {United States},
year = {2000},
month = {2}
}