Development of an Integrated Flow Stress and Roll Force Models for Plate Rolling of Microalloyed Steel

Thakur, Suman Kant; Das, Alok Kumar; Jha, B. K.

doi:10.1002/srin.202100479

Cited by 8 publications

(5 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since variation in strain rate is very high, the logarithm of strain rate was taken as an input variable in place of strain rate. A two hidden layer feed-forward back-propagation DNN flow stress model was developed in R software to characterize the hot deformation behavior of experimental steel [26]. Strain, deformation temperature and strain rate were used as input variable in flow stress model.…”

Section: Fig1 the Layout Of Plate Millmentioning

confidence: 99%

Application of Machine Learning Methods for the Prediction of Roll Force and Torque during Plate Rolling of Micro-alloyed Steel

Thakur¹,

Das

Jha³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

Machine learning technique is extensively used to establish the relationship between non-linear data sets which cannot be described mathematically and thus an exact analytic model is either intractable or too time-consuming to develop. During hot rolling, the effect of process parameters that cannot be captured in mathematical models, such as roll dimensions and its wear, the inter-pass time between rolling passes, temperature variation has been incorporated using multivariate supervised machine learning technique for accurate prediction of roll force and torque during plate rolling of micro-alloyed steel. An ensemble method was used to combine various machine learning techniques and average them to develop one final predictive model. K-cross validation of the model was carried out to validate the results and ensure the model gets the correct pattern of data. Root mean square error of ensemble roll force model was compared with roll force calculation using Sims theory. It was found that the machine learning model can predict the roll force and torque accurately as it takes care of various non-linear process variables which cannot be accounted for mathematically. The R-value of the machine learning model was > 98%, whereas it was 92.2% for roll force calculation using Sims theory.

show abstract

Section: Fig1 the Layout Of Plate Millmentioning

confidence: 99%

Application of Machine Learning Methods for the Prediction of Roll Force and Torque during Plate Rolling of Micro-alloyed Steel

Thakur¹,

Das

Jha³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Xiao et al [26] conducted a comparative study about the Arrhenius-type constitutive equation and BP-ANN model in a prediction of 12Cr3WV steel deformation behavior and discussed that 12Cr3WV steel flow behavior can be more accurately captured by the optimized BP-ANN model than the Arrhenius-type constitutive model. Likewise, the constitutive relationships were proposed for various materials using the BP-ANN models by researchers Li et al [27], Stendal et al [28], WD et al [29], Thakur et al [30], and Murugesan et al [31] and stated that the neural network model could be an impressive tool to examine the deformation behavior and to suggest the constitutive equation of test materials. However, the BP-ANN model can yield different results at each run due to random outcomes of weights and bias in the neural network and is often termed a multi-restart problem [31].…”

Section: Introductionmentioning

confidence: 99%

Hybrid Artificial Neural Network-Based Models to Investigate Deformation Behavior of AZ31B Magnesium Alloy at Warm Tensile Deformation

Murugesan

Chung

et al. 2023

Materials

View full text Add to dashboard Cite

The uniaxial warm tensile experiments were carried out in deformation temperatures (50–250 °C) and strain rates (0.005 to 0.0167 s−1) to investigate the material workability and to predict flow stress of AZ31B magnesium alloy. The back–propagation artificial neural network (BP–ANN) model, a hybrid models with a genetic algorithm (GABP–ANN), and a constrained nonlinear function (CFBP–ANN) were investigated. In order to train the exploited machine learning models, the process parameters such as strain, strain rate, and temperature were accounted as inputs and flow stress was considered as output; moreover, the experimental flow stress values were also normalized to constructively run the neural networks and to achieve better generalization and stabilization in the trained network. Additionally, the proposed model’s closeness and validness were quantified by coefficient of determination (R2), relative mean square error (RMSE), and average absolute relative error (AARE) metrics. The computed statistical outcomes disclose that the flow stress predicted by both GABP–ANN and CFBP–ANN models exhibited better closeness with the experimental data. Moreover, compared with the GABP–ANN model outcomes, the CFBP–ANN model has a relatively higher predictability. Thus, the outcomes confirm that the proposed CFBP–ANN model can result in the accurate description of AZ31 magnesium alloy deformation behavior, showing potential for the purpose of practicing finite element analysis.

show abstract

“…Comprehensive predictions may be made about the hot deformation behavior and microstructural development of V–Ti microalloyed steels. Recently, Thakur et al [ 11 ] constructed the deep neural network flow stress model to predict flow stress. The results show that the model had a higher prediction accuracy at high strain rates.…”

Section: Introductionmentioning

confidence: 99%

Constitutive Modeling for Flow Stress and Processing Maps of a 0.2C–2.0Mn–0.5Cr Microalloyed Steel

Feng,

Zhang,

Zhang

et al. 2023

steel research int.

View full text Add to dashboard Cite

Low‐carbon microalloyed steel with the microstructure of bainite is frequently utilized to produce automotive parts. The systematic investigation of the hot deformation behavior can serve as a reference for the optimization of deformation process parameters. The hot deformation of 0.2C–2.0Mn–0.5Cr microalloyed steel is studied. Based on the stress–strain curve, an Arrhenius model with strain compensation is established. The correlation coefficient R2 and the average absolute relative error calculated according to this model are 0.962 and 4.871%. The microstructure evolution at the strain of 0.90 is studied. In the stable region with substantial power dissipation, the microstructure is uniformly fine. The strain rate is high in the stable region with low‐power dissipation, and the room‐temperature microstructure after deformation retains a large amount of deformation storage energy and fine substructures. During deformation, the banded structures are formed in the instable region. The difference in dislocation density between the band structure and the nearby regions promotes the formation of necklace microstructures. Therefore, the 0.2C–2.0Mn–0.5Cr microalloyed steel has an ideal deformation process window in the range of a hot deformation temperature of 880–920 °C and a strain rate of 0.1–0.3 s−1.

show abstract

Development of an Integrated Flow Stress and Roll Force Models for Plate Rolling of Microalloyed Steel

Abstract: The ORCID identification number(s) for the author(s) of this article can be found under https://doi.org/10.1002/srin.202100479.

Cited by 8 publications

References 31 publications

Application of Machine Learning Methods for the Prediction of Roll Force and Torque during Plate Rolling of Micro-alloyed Steel

Application of Machine Learning Methods for the Prediction of Roll Force and Torque during Plate Rolling of Micro-alloyed Steel

Hybrid Artificial Neural Network-Based Models to Investigate Deformation Behavior of AZ31B Magnesium Alloy at Warm Tensile Deformation

Constitutive Modeling for Flow Stress and Processing Maps of a 0.2C–2.0Mn–0.5Cr Microalloyed Steel

Contact Info

Product

Resources

About