A Comparative Study on Arrhenius Equations and BP Neural Network Models to Predict Hot Deformation Behaviors of a Hypereutectoid Steel

Qiao, Lei; Deng, Yong; Wang, Yuan; Zhu, Jingchuan

doi:10.1109/access.2020.2986389

Cited by 15 publications

(3 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, it is particularly suitable for modeling using artificial neural networks. Qiao et al [26] used Arrhenius model and BP neural network model to predict the high temperature deformation behavior of hypereutectoid steel and found that the model constructed by BP neural network has more accurate prediction results with higher correlation coefficient(R) and mean absolute relative error (AARE). In their investigation of the superplastic forming of Ti-2.5Al-1.8Mn, Mosleh A et al [27] used an Arrhenius-type model and an artificial neural network model to describe the behavior at high temperatures.…”

Section: Introductionmentioning

confidence: 99%

Constitutive Model of TNM Alloy Using Arrhenius-Type Model and Artificial Neural Network Model

Zhou

Yang

et al. 2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

TNM alloys are frequently employed in automotive and aeronautical applications. Hot compression experiments on a Gleeble-3800 testing apparatus were conducted at a range of temperatures (1150°C–1250°C) and strain rates (0.001s-1 - 1s-1) to investigate the high temperature deformation behavior of TNM alloys. The complex deformation mechanisms of TNM alloys at various temperatures and strain rates were studied using the experimentally discovered true stress-true strain curves. The constitutive relationships between deformation parameters and flow stresses were constructed using two methods, Arrhenius model and neural network model respectively. The results demonstrated that the correlation coefficient R and root mean square error (RSME) achieved by BPNN are, respectively, 0.9982 and 4.7784, and are notably better than those anticipated by the Arrhenius-type model. In terms of the distribution of relative errors, the BPNN findings are similarly more concentrated, and the bulk of them fall inside the 10% range. Therefore, the BP neural network is a useful tool for forecasting the elevated temperature flow behavior of TNM alloys.

show abstract

Section: Introductionmentioning

confidence: 99%

Constitutive Model of TNM Alloy Using Arrhenius-Type Model and Artificial Neural Network Model

Zhou

Yang

et al. 2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

show abstract

“…In addition, the artificial neural network model has a large parallel processing structure, which can be used to depict the complex flow behavior of materials through a variety of nonlinear relationships. [ 36–42 ]…”

Section: Introductionmentioning

confidence: 99%

Dynamic Softening Mechanism and an Improved Unified Constitutive Model for an Al–Cu–Mn–Fe–Zr Alloy during Warm Deformation

et al. 2021

View full text Add to dashboard Cite

Deformation behavior of an Al–Cu–Mn–Fe–Zr alloy is investigated by plane strain compression tests at a warm deformation region. The flow stress first increases and then keeps steady, and the flow stress increases with reducing temperature or raising strain rate. However, the influence of strain rate on flow stress is weak at 100 and 150 °C. The dynamic recovery (DRV) mechanism is the dominant mechanism to balance the work hardening, and a larger number of dislocations are consumed at low strain rates. So, the deformed grains are difficult to reach the critical strain for dynamic recrystallization (DRX). When the strain rate is relatively high, the critical strain can be reached in a short time, which promotes the process of DRX. In addition, an improved unified constitutive model is built based on the evolution of dislocation density. The predicted flow stresses are in a close agreement with the measured results, proving that the built model can nicely reproduce the flow behavior.

show abstract

“…[1][2][3][4] Due to its prominent performance in antiwearing and high strength, eutectoid or hypereutectoid steels with nearly fully pearlitic microstructure have been viewed as candidate materials for heavy-haul railway applications. [5] However, the heavier transport conditions tend to significantly increase the risk of damage and failure of rail steels. [6][7][8][9][10] Serving in complicated conditions, it is generally acceptable that the rails life is strongly related to the wear behavior, including the abrasive, adhesive, and wear mechanisms.…”

Section: Introductionmentioning

confidence: 99%

Machine Learning‐Guided Design of Pearlitic Steel with Promising Mechanical and Tribological Properties

Qiao

Zhu

2021

Adv Eng Mater

Self Cite

View full text Add to dashboard Cite

Herein, attempts have been made to design and develop pearlitic steels for application in heavy‐haul rails. The hardness plays a vital role in studying the mechanical and tribological properties, which is theoretically related to the alloying composition of steel. With aid of machine learning (ML) method, the particle swarm optimization (PSO) improved generalized regression neural network (GRNN) is utilized to model the relationship between composition and hardness of pearlitic steel. The results show that the designed steel exhibits superior hardness and mechanical properties with fine pearlite lamellar microstructure. In addition, the wear behavior of the steel and its wear mechanism are systematically studied by tribological testing and electron probe microanalysis (EPMA) observations of worn surface and wear particles. With composition optimization, the wear resistance has further improved as evidenced by the lower friction coefficient and reduction of wear volume. The pearlitic steels exhibit a combined wear mechanism including adhesive wear, abrasion, delamination, and plastic deformation. As a result, the designed steels offer high hardness with very good mechanical and tribological properties which are far superior to previously reported pearlitic steels. This work may assist in developing the appropriate composition to create the desired hardness, mechanical, and tribological properties.

show abstract

A Comparative Study on Arrhenius Equations and BP Neural Network Models to Predict Hot Deformation Behaviors of a Hypereutectoid Steel

Cited by 15 publications

References 36 publications

Constitutive Model of TNM Alloy Using Arrhenius-Type Model and Artificial Neural Network Model

Constitutive Model of TNM Alloy Using Arrhenius-Type Model and Artificial Neural Network Model

Dynamic Softening Mechanism and an Improved Unified Constitutive Model for an Al–Cu–Mn–Fe–Zr Alloy during Warm Deformation

Machine Learning‐Guided Design of Pearlitic Steel with Promising Mechanical and Tribological Properties

Contact Info

Product

Resources

About