scholarly journals Estimation of Austenitizing and Multiple Tempering Temperatures from the Mechanical Properties of AISI 410 using Artificial Neural Network

2018 ◽  
Vol 7 (4.19) ◽  
pp. 778
Author(s):  
Abdul Kareem F. Hassan ◽  
Qahtan A. Jawad
Keyword(s):  
Neural Network ◽  
Mechanical Properties ◽  
Heat Treatment ◽  
Artificial Neural Network ◽  
Tensile Strength ◽  
Regression Analysis ◽  
Impact Energy ◽  
Ann Model ◽  
Artificial Neural ◽  
Quenching And Tempering

This research involved a study of the heat treatment conditions effect on the mechanical properties of martensitic stainless steel type AISI 410. Heat treatment process was hardening of the metal by quenching at different temperature 900°C, 950°C, 1000°C, 1050°C and 1100°C, followed by double tempering at 200°C, 250°C, 300°C, 350°C, 400°C, 450°C, 500°C, 550°C, 600°C, 650°C and 700°C, were evaluated and study of some mechanical properties such as hardness, impact energy and properties of tensile test such as yield and tensile strength is carried out. Multiple outputs Artificial Neural Network model was built with a Matlab package to predict the quenching and tempering temperatures. Also, linear and nonlinear regression analyses (using Data fit package) were used to estimate the mathematical relationship between quenching and tempering temperatures with hardness, impact energy, yield, and tensile strength. A comparison between experimental, regression analysis and ANN model show that the multiple outputs ANN model is more accurate and closer to the experimental results than the regression analysis results. 

scholarly journals Quantitative Relationship Analysis of Mechanical Properties with Mg Content and Heat Treatment Parameters in Al–7Si Alloys Using Artificial Neural Network

Materials ◽  
2019 ◽  
Vol 12 (5) ◽  
pp. 718 ◽  
Author(s):  
Xiaoyan Wu ◽  
Huarui Zhang ◽  
Haiyang Cui ◽  
Zhen Ma ◽  
Wei Song ◽  
...  
Keyword(s):  
Neural Network ◽  
Mechanical Properties ◽  
Heat Treatment ◽  
Artificial Neural Network ◽  
Quantitative Relationship ◽  
Ann Model ◽  
Relationship Analysis ◽  
Artificial Neural ◽  
Input Variables ◽  
Mg Content

In this paper, an artificial neural network (ANN) model with high accuracy and good generalization ability was developed to predict and optimize the mechanical properties of Al–7Si alloys. The quantitative correlation formulas of the mechanical properties with Mg content and heat treatment parameters were established based on the transfer function and weight values. The relative importance of the input variables, Mg content and heat treatment parameters, on the mechanical properties of Al–7Si alloys were identified through sensitivity analysis. The results indicated that the mechanical properties of Al–7Si alloys were sensitive to Mg content and aging temperature. Then the individual and the combined influences of these input variables on the properties of Al–7Si alloys were simulated and the process parameters were optimized using the artificial neural network model. Finally, the proposed model was validated to be a robust tool in predicting the mechanical properties of the Al–7Si alloy by conducting experiments.

Application of Artificial Neural Network for Prediction of Heat Treated Sintered Steels Properties

2008 ◽  
Vol 273-276 ◽  
pp. 323-328 ◽  
Author(s):  
H. Khorsand ◽  
M. Arjomandi ◽  
H. Abdoos ◽  
S.H. Sadati
Keyword(s):  
Neural Network ◽  
Mechanical Properties ◽  
Heat Treatment ◽  
Artificial Neural Network ◽  
Learning Algorithm ◽  
Initial Density ◽  
Back Propagation ◽  
Heat Treated ◽  
Algorithm Comparison ◽  
Artificial Neural

Heat treatment is an important method for improving the mechanical properties of industrial parts that are made through the powder metallurgy. Most PM steels are subjected to hardening and tempering, and it is due to this treatment that tempered martensite is formed. After heat treatment, these steel’s mechanical properties are affected by the heat treatment parameters and the initial density. In this paper, in order to make an evaluation of the effect of the above parameters, FN-0205 PM steel with various densities is heat treated in different austenite conditions and tempering time. Their mechanical properties are then evaluated and recorded. Afterwards, this data obtained by experimental procedure are predicted for various conditions. The method employed here is the well-known feedforward Artificial Neural Network (ANN) with the Back Propagation (BP) learning algorithm. Comparison between predicted values and experimental data, in the present study, indicate that the predicted results from this model are in good agreement with the experimental values.

Correlation of Mechanical Properties of Cast Al 3xx Alloys to Processing Variables and Alloy Chemistry Using Regression Analysis and Artificial Neural Network Techniques

2012 ◽  
Vol 463-464 ◽  
pp. 439-443
Author(s):  
Daryoush Emadi ◽  
Musbah Mahfoud
Keyword(s):  
Neural Network ◽  
Mechanical Properties ◽  
Artificial Neural Network ◽  
Nonlinear Regression ◽  
A356 Alloy ◽  
Ann Model ◽  
Alloy Chemistry ◽  
Processing Variables ◽  
Artificial Neural ◽  
Alloy Castings

The mechanical properties of aluminium alloy castings, such as EL%, YS and UTS, are controlled by the casting and heat treatment variables, alloy’s composition, and melt treatment. Despite the abundance of literature data, the large number of the controlling parameters has made it difficult to predict and model the mechanical properties by the conventional techniques. Another obstacle encountered when making such a prediction is the complex kinetics and interactions that exist among the many variables. The goal of this study was to develop Artificial Neural Network (ANN) and Multiple Regression models to predict the mechanical properties of A356 alloy from the processing variables. Several standard nonlinear regression and multi-layer ANN models were developed and trained using data from the literature and experimental results. Due to the complexity of A356’s solidification behaviour, the nonlinear regression produced results that were not as accurate as those produced by the ANN model. The results indicate that ANN is a suitable technique for predicting mechanical properties from alloy chemistry and processing variables.

scholarly journals Prediction of thermal conductivity of aqueous solution at high pressures by using artificial neural network

2014 ◽  
Vol 20 (4) ◽  
pp. 565-569
Author(s):  
Ali Amooey ◽  
Maryam Ahangarian ◽  
Farshad Rezazadeh
Keyword(s):  
Neural Network ◽  
Thermal Conductivity ◽  
Aqueous Solution ◽  
Artificial Neural Network ◽  
Regression Analysis ◽  
High Pressures ◽  
Ann Model ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Hidden Layer

The objective of this study is to predict thermal conductivity of aqueous solution with artificial neural network (ANN) model with three inputs (pressure, temperature and concentration). A feed forward artificial neural network with three neurons in its hidden layer is recommended to predict thermal conductivity and the accuracy of this method evaluated by regression analysis between the predicted and experimental value and it shows desired result.

Prediction of the Ultimate Tensile Strength in API X70 Line Pipe Steel Using an Artificial Neural Network Model

2019 ◽  
Vol 297 ◽  
pp. 71-81
Author(s):  
Adel Saoudi ◽  
Djahida Lerari ◽  
Farida Khamouli ◽  
L'Hadi Atoui ◽  
Khaldoun Bachari
Keyword(s):  
Neural Network ◽  
Mechanical Properties ◽  
Artificial Neural Network ◽  
Tensile Strength ◽  
Chemical Composition ◽  
Ultimate Tensile Strength ◽  
Yield Strength ◽  
High Strength ◽  
Ann Model ◽  
Mean Relative Error

An artificial neural network (ANN) model has been developed for the analysis and simulation of the correlation between the chemical composition and mechanical properties of high strength low alloy (HSLA) steel X70. The input parameters of the model consist of the base metal chemical composition (C, Si, Mn, the sum of Cr+Cu+Ni+Mo, the sum of Nb+Ti+V, carbon equivalent CEpcm) and the yield strength (YS). The outputs of the ANN model include the ultimate tensile strength (UTS) of the test material. Scatter plots, correlation coefficient (R) and mean relative error (MRE) were used to assess the performance of the developed neural network. Interestingly, the model output is efficient to calculate the mechanical properties of high strength low alloy steels, especially the ultimate tensile strength as a function of chemical composition and yield strength of the used material. The obtained results are in a good agreement with experimental ones, with high correlation coefficient and low mean relative error. The predictions accuracy of the developed model also conforms to the results of mean paired T-test.

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

2010 ◽  
Vol 658 ◽  
pp. 145-148 ◽  
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.

Application of Artificial Neural Network Based on GA-BP Algorithm to Predicting Mechanical Properties of TC4

2010 ◽  
Vol 146-147 ◽  
pp. 1698-1701
Author(s):  
Zhe Zhe Hou ◽  
Yan Liang Du
Keyword(s):  
Neural Network ◽  
Mechanical Properties ◽  
Heat Treatment ◽  
Genetic Algorithm ◽  
Artificial Neural Network ◽  
Back Propagation ◽  
Optimization Methods ◽  
Calculation Results ◽  
Tc4 Alloy ◽  
Artificial Neural

On the basis of numerous experimental results the effect of heat treatment on mechanical properties of TC4 alloy is studied. A computer model expressing the relationships between heat treatment and mechanical properties has been established with a back propagation feed forword artificial neural network method. The optimization methods based on artificial neural network and the genetic algorithm, using binary system, optimize the weight and threshold by the genetic algorithm. The calculation results show that the model has good learning precision and generalization and it can be used for predicting the mechanical properties of TC4 alloy.

Wear volume prediction of AISI H13 die steel using response surface methodology and artificial neural network

2020 ◽  
Vol 14 (2) ◽  
pp. 6789-6800
Author(s):  
Vishal Jagota ◽  
Rajesh Kumar Sharma
Keyword(s):  
Neural Network ◽  
Heat Treatment ◽  
Artificial Neural Network ◽  
Response Surface ◽  
Sliding Wear ◽  
Austenitizing Temperature ◽  
Tempering Temperature ◽  
Die Steel ◽  
Artificial Neural ◽  
Tempering Time

Resistance to wear of hot die steel is dependent on its mechanical properties governed by the microstructure. The required properties for given application of hot die steel can be obtained with control the microstructure by heat treatment parameters. In the present paper impact of different heat treatment parameters like austenitizing temperature, tempering time, tempering temperature is studied using response surface methodology (RSM) and artificial neural network (ANN) to predict sliding wear of H13 hot die steel. After heat treating samples at austenitizing temperature of 1020°C, 1040°C and 1060°C; tempering temperature 540°C, 560°C and 580°C; tempering time 1hour, 2hours and 3hours, experimentation on pin-on-disc tribo-tester is done to measure the sliding wear of H13 die steel. Box-Behnken design is used to develop a regression model and analysis of variance technique is used to verify the adequacy of developed model in case of RSM. Whereas, multi-layer feed-forward backpropagation architecture with input layer, single hidden layer and an output layer is used in ANN. It was found that ANN proves to be a better tool to predict sliding wear with more accuracy. Correlation coefficient R2 of the artificial neural network model is 0.986 compared to R2 of 0.957 for RSM. However, impact of input parameter interactions can only be analysed using response surface method. In addition, sensitivity analysis is done to determine the heat treatment parameter exerting most influence on the wear resistance of H13 hot die steel and it showed that tempering time has maximum influence on wear volume, followed by tempering temperature and austenitizing temperature. The prediction models will help to estimate the variation in die lifetime by finding the amount of wear that will occur during use of hot die steel, if the heat treatment parameters are varied to achieve different properties.

Sign in / Sign up

Export Citation Format

Share Document