Designing dual-phase steels with improved performance using ANN and GA in tandem

Dutta, Tanusree; Dey, Shobhana; Datta, Shubhabrata; Das, Debdulal

doi:10.1016/j.commatsci.2018.10.020

Cited by 52 publications

(19 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A feedforward neural network consists of input layer, hidden layer and output layer. Neuron is the basic unit of neural network [32]. Each neuron contains an activation function, which is used to process the data input into the neuron.…”

Section: A Deep Neural Networkmentioning

confidence: 99%

Elevating Prediction Performance for Mechanical Properties of Hot-Rolled Strips by Using Semi-Supervised Regression and Deep Learning

Yang

Cao

et al. 2020

IEEE Access

View full text Add to dashboard Cite

In the present work, to solve the problem of the lacking enough labeled training data for deep learning, a safe semi-supervised regression supporting Bayesian optimization deep neural network (SAFER-BODNN) model was proposed to establish mechanical property prediction model of hot-rolled strips. The Pearson correlation coefficient was applied to reduce the data dimension. The safe semi-supervised regression was implemented to add the pseudo labels to the unlabeled data for training dataset expansion. The deep neural network was trained with Bayesian optimization to determine the optimal hyper-parameters of the network. The results show that the SAFER-BODNN model achieves good accuracy for mechanical property prediction of hot-rolled strips with R of 0.9610 for yield strength, 0.9682 for tensile strength, and 0.8619 for elongation, respectively. Compared with the deep neural network trained on the labeled dataset, the SAFER-BODNN model obtains stable smaller predicted errors. Among all the variables, C content and Mn content have large influence on the yield strength and tensile strength, coiling temperature has the largest influence on the elongation. The investigation makes full use of unlabeled data to elevate the accuracy of the deep neural network, and also provides a way for deep learning modeling when the data are insufficient.

show abstract

Section: A Deep Neural Networkmentioning

confidence: 99%

Elevating Prediction Performance for Mechanical Properties of Hot-Rolled Strips by Using Semi-Supervised Regression and Deep Learning

Yang

Cao

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Low‐carbon dual‐phase (DP) steels have microstructures composed of a ferritic matrix and a hard phase (normally martensite), and thanks to their excellent mechanical properties, they are suitable materials for industrial applications, especially in the automotive industry . Accordingly, research on this subject is still under way to improve their strength–ductility balance.…”

Section: Introductionmentioning

confidence: 99%

Unraveling the Effect of Martensite Volume Fraction on the Mechanical and Corrosion Properties of Low‐Carbon Dual‐Phase Steel

Soleimani

Mirzadeh

Dehghanian

2019

steel research int.

View full text Add to dashboard Cite

The effect of martensite volume fraction on the mechanical and corrosion properties of low-carbon dual-phase steel is studied based on both step quenching (SQ) and intercritical annealing (IA) routes. For SQ samples, hardness and ultimate tensile strength decrease with increasing holding time at the intercritical temperature and reach a plateau, which is related to the decrease in the amount of martensite during annealing. Conversely, for the IA samples, hardness increases during holding at the intercritical temperature due to austenitization and reaches the same plateau. At a same martensite volume fraction, the work-hardening behavior of SQ samples is better than IA samples, which is related to both the finer grain size and smaller martensite islands in the former. At low martensite fractions, the corrosion properties are comparable with the asreceived ferritic-pearlitic sample. It is revealed that by decreasing the volume fraction of martensite in SQ samples, the corrosion current density (i corr ) decreases almost linearly, and at martensite content of zero, it reaches the i corr of the fully ferritic microstructure. The latter is found to be lower than the i corr of the as-received sample. Therefore, the real effect of martensite on corrosion properties is unraveled for the first time.

show abstract

“…In the network, each neuron implements a basic computation and produces the output [31]. The input data will be processed by the neurons of input layer, then the output can be obtained, which will be used as the input for the next layer.…”

Section: Brief Descriptions Of Modeling Techniques a Artificial Neural Networkmentioning

confidence: 99%

Prediction of Endpoint Sulfur Content in KR Desulfurization Based on the Hybrid Algorithm Combining Artificial Neural Network With SAPSO

Yang

Zhang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

In the present work, the endpoint sulfur content prediction model of Kambara Reactor (KR) desulfurization in the steelmaking process is investigated. For Artificial Neural Network (ANN), the effects of different structure parameters, including the number of hidden layer neurons, activation functions and training functions, on the performance of desulfurization model are studied. The initial weights and biases of the neural network is optimized to further elevated the prediction accuracy of the model. Three models established by using Multiple Linear Regression (MLR), ANN and a hybrid algorithm (artificial neural network optimized by SAPSO, named SAPSO-ANN) are compared by the Correlation Coefficient (R), Root Mean Square Error (RMSE) and Mean Absolute Relative Error (MARE). The results show that in the process of KR desulfurization, the nonlinear model of ANN and SAPSO-ANN has a higher accuracy than the linear model of MLR. Among the three models, the SAPSO-ANN model achieves the highest accuracy with R value of 0.54, RMSE of 2.61×10 −4 % and MAER of 0.47, which is selected to analyze the effect of process parameters on the desulfurization rate and design the amount of desulfurization flux in the KR desulfurization process. Experimental results show good agreements with the calculation results, indicating the practicability of the model. INDEX TERMS Artificial neural network, particle swarm optimization, multiple linear regression, prediction of endpoint sulfur content, KR desulfurization process.

show abstract

Designing dual-phase steels with improved performance using ANN and GA in tandem

Cited by 52 publications

References 58 publications

Elevating Prediction Performance for Mechanical Properties of Hot-Rolled Strips by Using Semi-Supervised Regression and Deep Learning

Elevating Prediction Performance for Mechanical Properties of Hot-Rolled Strips by Using Semi-Supervised Regression and Deep Learning

Unraveling the Effect of Martensite Volume Fraction on the Mechanical and Corrosion Properties of Low‐Carbon Dual‐Phase Steel

Prediction of Endpoint Sulfur Content in KR Desulfurization Based on the Hybrid Algorithm Combining Artificial Neural Network With SAPSO

Contact Info

Product

Resources

About