Prediction of the Flow Stress of a High Alloyed Austenitic Stainless Steel Using Artificial Neural Network

The high temperature flow behavior of as-cast 904L austenitic stainless steel was studied using artificial neural network (ANN). Isothermal compression tests were carried out at the temperature range of 1000°C to 1200°C and strain rate range of 0.01 to 10s1. Based on the experimental flow stress data, an ANN model for the constitutive relationship between flow stress and strain, strain rate and deformation temperature was constructed by back-propagation (BP) method. Three layer structured network with one hidden layer and nine hidden neurons was trained and the normalization method was employed in training process to avoid over fitting. Modeling results show that the developed ANN model exhibits good performance for predicting the flow stresses of the 904L steel. Therefore, it can be used to reflect the hot deformation behavior in a wide working window.

Download Full-text

Capability of a Feed-Forward Artificial Neural Network to Predict the Constitutive Flow Behavior of As Cast 304 Stainless Steel Under Hot Deformation

Journal of Engineering Materials and Technology ◽

10.1115/1.2400276 ◽

2006 ◽

Vol 129 (2) ◽

pp. 242-247 ◽

Cited By ~ 25

Author(s):

Sumantra Mandal ◽

P. V. Sivaprasad ◽

S. Venugopal

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Stainless Steel ◽

Strain Rate ◽

Hot Deformation ◽

Flow Behavior ◽

304 Stainless Steel ◽

Compression Tests ◽

Feed Forward ◽

Artificial Neural

A model is developed to predict the constitutive flow behavior of as cast 304 stainless steel during hot deformation using artificial neural network (ANN). The inputs of the neural network are strain, strain rate, and temperature, whereas flow stress is the output. Experimental data obtained from hot compression tests in the temperature range 1023-1523K, strain range 0.1-0.5, and strain rate range 10−3-102s−1 are employed to develop the model. A three-layer feed-forward ANN is trained with standard back propagation and some upgraded algorithms like resilient propagation (Rprop) and superSAB. The performances of these algorithms are evaluated using a wide variety of standard statistical indices. The results of this study show that Rprop algorithm performs better as compared to others and thereby considered as the most efficient algorithm for the present study. It has been shown that the developed ANN model can efficiently and accurately predict the hot deformation behavior of as cast 304 stainless steel. Finally, an attempt has been made to quantify the extrapolation ability of the developed network.

Download Full-text

Artificial Neural Network for Predicting the Flow Behaviors of Hot Compressed 2124-T851 Aluminum Alloy

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.146-147.720 ◽

2010 ◽

Vol 146-147 ◽

pp. 720-723

Author(s):

Yong Cheng Lin ◽

Xiao Min Chen ◽

Yu Chi Xia

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Aluminum Alloy ◽

Flow Stress ◽

Strain Rate ◽

Learning Algorithm ◽

Ann Model ◽

Wide Range ◽

Feed Forward Network ◽

Artificial Neural

The compressive deformation experiments of 2124-T851 aluminum alloy were carried out over a wide range of temperature and strain rate. An artificial neural network (ANN) model is developed for the analysis and simulation of the correlation between the flow behaviors of hot compressed 2124-T851 aluminum alloy and working conditions. The input parameters of the model consist of strain rate, forming temperature and deformation degree whereas flow stress is the output. A three layer feed-forward network with 15 neurons in a single hidden layer and back propagation (BP) learning algorithm has been employed. Good performance of the ANN model is achieved. The predicted results are consistent with what is expected from fundamental theory of hot compression deformation, which indicates that the excellent capability of the developed ANN model to predict the flow stress level, the strain hardening and flow softening stages is well evidenced.

Download Full-text

Artificial Neural Network to Predict the Hot Deformation Behavior of Super 13Cr Martensitic Stainless Steel

Materials Science Forum ◽

10.4028/www.scientific.net/msf.695.361 ◽

2011 ◽

Vol 695 ◽

pp. 361-364 ◽

Cited By ~ 3

Author(s):

Ying Han ◽

Guan Jun Qiao ◽

Dong Na Yan ◽

De Ning Zou

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Stainless Steel ◽

Flow Stress ◽

Strain Rate ◽

Hot Deformation ◽

Deformation Behavior ◽

Martensitic Stainless Steel ◽

Ann Model ◽

Hot Deformation Behavior

The hot deformation behavior of super 13Cr martensitic stainless steel was investigated using artificial neural network (ANN). Hot compression tests were carried out at the temperature range of 950°C to 1200°C and strain rate range of 0.1–50s–1at an interval of an order of magnitude. Based on the limited experimental data, the ANN model for the constitutive relationship existed between flow stress and strain, strain rate and deformation temperature was developed by back-propagation (BP) neural network method. A three layer structured network with one hidden layer and ten hidden neurons was trained and the normalization method was employed in training for avoiding over fitting. Modeling results show that the developed ANN model can efficiently predict the flow stress of the steel and reflect the hot deformation behavior in the whole deforming process.

Download Full-text

Artificial Neural Network Approach to Predict Mechanical Properties of 301 Austenitic Stainless Steel

Materials Science Forum ◽

10.4028/www.scientific.net/msf.658.145 ◽

2010 ◽

Vol 658 ◽

pp. 145-148 ◽

Cited By ~ 1

Author(s):

Zhi Yu Chen ◽

De Ning Zou ◽

Jun Hui Yu ◽

Ying Han

Keyword(s):

Neural Network ◽

Experimental Data ◽

Mechanical Properties ◽

Artificial Neural Network ◽

Stainless Steel ◽

Austenitic Stainless Steel ◽

Rolling Reduction ◽

Ann Model ◽

Neural Network Approach ◽

Artificial Neural

In this study, the effect of original thicknesses of plate, the thicknesses of plate after rolling and rolling reduction on the strength in 301 stainless steel was modeled by means of artificial neural network (ANN). The experimental data were collected to obtain training set and testing set. The normalization method was employed for avoiding over-fitting. The optimal ANN method architecture was determined by according to the trial and error procedure. The results of the ANN model were in good agreement with experimental data. As can be seen from the result, we believe that the neural network model can efficiently predict the relationship between mechanical properties and rolling reduction in 301 austenitic stainless steel.

Download Full-text

Prediction and Analysis of Tensile Properties of Austenitic Stainless Steel Using Artificial Neural Network

Metals ◽

10.3390/met10020234 ◽

2020 ◽

Vol 10 (2) ◽

pp. 234 ◽

Cited By ~ 3

Author(s):

Yuxuan Wang ◽

Xuebang Wu ◽

Xiangyan Li ◽

Zhuoming Xie ◽

Rui Liu ◽

...

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Stainless Steel ◽

Austenitic Stainless Steel ◽

Tensile Properties ◽

Prediction Performance ◽

Good Prediction ◽

Relative Significance ◽

Value Analysis ◽

Artificial Neural

Predicting mechanical properties of metals from big data is of great importance to materials engineering. The present work aims at applying artificial neural network (ANN) models to predict the tensile properties including yield strength (YS) and ultimate tensile strength (UTS) on austenitic stainless steel as a function of chemical composition, heat treatment and test temperature. The developed models have good prediction performance for YS and UTS, with R values over 0.93. The models were also tested to verify the reliability and accuracy in the context of metallurgical principles and other data published in the literature. In addition, the mean impact value analysis was conducted to quantitatively examine the relative significance of each input variable for the improvement of prediction performance. The trained models can be used as a guideline for the preparation and development of new austenitic stainless steels with the required tensile properties.

Download Full-text