scholarly journals Prediction of Bending Force in the Hot Strip Rolling Process Using Multilayer Extreme Learning Machine

2021 ◽  
Vol 2021 ◽  
pp. 1-13
Author(s):  
Yan Wu ◽  
Hongchao Ni ◽  
Xu Li ◽  
Feng Luan ◽  
Yaodong He
Keyword(s):  
Extreme Learning Machine ◽  
Hot Rolling ◽  
Absolute Error ◽  
Rolling Process ◽  
Hot Strip Rolling ◽  
Strip Rolling ◽  
Bending Force ◽  
Hot Strip ◽  
Learning Machine ◽  
Hidden Layer

In the hot strip rolling process, accurate prediction of bending force can improve the control accuracy of the strip flatness and further improve the quality of the strip. In this paper, based on the production data of 1300 pieces of strip collected from a hot rolling factory, a series of bending force prediction models based on an extreme learning machine (ELM) are proposed. To acquire the optimal model, the parameter settings of the models were investigated, including hidden layer nodes, activation function, population size, crossover probability, and hidden layer structure. Four models are established, one hidden layer ELM model, an optimized ELM model (GAELM) by genetic algorithm (GA), an optimized ELM model (SGELM) by hybrid simulated annealing (SA) and GA, and two-hidden layer optimized ELM model (SGITELM) optimized by SA and GA. The prediction performance is evaluated from the mean absolute error (MAE), root-mean-squared error (RMSE), and mean absolute percentage error (MAPE). The results show that the SGITELM has the highest prediction accuracy in the four models. The RMSE of the proposed SGITELM is 11.2678 kN, and 98.72% of the prediction data have an absolute error of less than 25 kN. This indicates that the proposed SGITELM with strong learning ability and generalization performance can be well applied to hot rolling production.

scholarly journals On the Evolution of Temperature and Combined Stress in a Work Roll under Cyclic Thermo-Mechanical Loadings during Hot Strip Rolling and Idling

Materials ◽  
2020 ◽  
Vol 13 (21) ◽  
pp. 5054
Author(s):  
Kejun Hu ◽  
Qinghe Shi ◽  
Wenqin Han ◽  
Fuxian Zhu ◽  
Jufang Chen
Keyword(s):  
Thermal Stress ◽  
Hot Rolling ◽  
Work Roll ◽  
Rolling Process ◽  
Roll Surface ◽  
Hot Strip Rolling ◽  
Strip Rolling ◽  
Hot Strip ◽  
Calculation Results ◽  
Work Rolls

An accurate prediction of temperature and stress evolution in work rolls is crucial to assess the service life of the work roll. In this paper, a finite element method (FEM) model with a deformable work roll and a meshed, rigid body considering complex thermal boundary conditions over the roll surface is proposed to assess the temperature and the thermal stress in work rolls during hot rolling and subsequent idling. After that, work rolls affected by the combined action of temperature gradient and rolling pressure are investigated by taking account of the hot strip. The accuracy of the proposed model is verified through comparison with the calculation results obtained from the mathematical model. The results show that thermal stress is dominant in the bite region of work rolls during hot rolling. Afterwards, the heat treatment residual stresses which are related to thermal fatigue are simulated and introduced into the work roll as the initial stress to evaluate the redistribution under the thermal cyclic loads during the hot rolling process. Results show that the residual stress significantly changed near the roll surface.

Simulation of Thermal Phenomena in Reverse Strip-Rolling Process

2018 ◽  
Vol 941 ◽  
pp. 1424-1430
Author(s):  
Alexander Nam ◽  
Uwe Prüfert ◽  
Marciej Pietrzyk ◽  
Rudolf Kawalla ◽  
Ulrich Prahl
Keyword(s):  
Hot Rolling ◽  
Rolling Process ◽  
Temperature Model ◽  
Hot Strip Rolling ◽  
Forming Process ◽  
Strip Rolling ◽  
Unknown Parameters ◽  
Hot Strip ◽  
Thermal Phenomena ◽  
Good Agreement

In the reverse hot strip rolling, the coiling and uncoiling of the strip leads to unstable conditions during the forming process. Both the temperature of the strip and the dwell time in the coil vary and influence the microstructure evolution passing in the coil during reverse rolling. It makes the design of this process difficult. Therefore, development of the temperature model for the reverse hot rolling including coiling and uncoiling was the main objective of the paper. The identification of the unknown parameters of the boundary conditions is proposed. Methods for their determination are discussed. The analysis is performed on example of the reverse hot rolling of the magnesium alloy AZ31. The resulting temperature model reveals good agreement with thermocouple and pyrometer measurements.

Determining the No-Recrystallization Conditions for Industrial Hot Strip Rolling of Steels Using Laboratory Simulations

2012 ◽  
Vol 706-709 ◽  
pp. 1409-1414 ◽  
Author(s):  
Gwenola Herman ◽  
Evgueni I. Poliak
Keyword(s):  
Hot Rolling ◽  
Incubation Time ◽  
Rolling Process ◽  
Critical Conditions ◽  
Recrystallization Temperature ◽  
Static Case ◽  
Hot Strip Rolling ◽  
Strip Rolling ◽  
Hot Strip ◽  
Cold Rolling And Annealing

Avoiding recrystallization of austenite in hot strip rolling of steels is highly important for enhancing mechanical properties of hot rolled products, as well as for the products undergoing cold rolling and annealing or coating. Recrystallization can only be avoided if its incubation time is longer that the time intervals characteristic for a particular hot rolling process. The present work focuses on computation of incubation time tinc for static recrystallization using laboratory hot deformation data and on extrapolation the results to industrial conditions. The computations are done based on application of critical conditions for initiation of dynamic recrystallization to the static case. No-recrystallization temperature in hot strip rolling is determined by setting tinc equal to interpass time. Simulations allow for prediction of the onset of austenite static or metadynamic recrystallization after individual rolling passes during industrial hot rolling and evaluation of the effects of strip thickness, rolling speeds, etc.

Mathematical modelling of roll wear in a tandem mill hot strip rolling process

2013 ◽  
Vol 4 (1) ◽  
pp. 56
Author(s):  
Carlos Arturo Vega Lebrún ◽  
Rumualdo Servin Castañeda ◽  
Genoveva Rosano Ortega ◽  
Juan Manuel Lopez ◽  
José Luis Cendejas Valdéz ◽  
...  
Keyword(s):  
Mathematical Modelling ◽  
Rolling Process ◽  
Hot Strip Rolling ◽  
Strip Rolling ◽  
Hot Strip ◽  
Roll Wear

scholarly journals A Comparative Assessment of Six Machine Learning Models for Prediction of Bending Force in Hot Strip Rolling Process

Metals ◽  
2020 ◽  
Vol 10 (5) ◽  
pp. 685 ◽  
Author(s):  
Xu Li ◽  
Feng Luan ◽  
Yan Wu
Keyword(s):  
Prediction Accuracy ◽  
Computational Cost ◽  
Regression Tree ◽  
Prediction Performance ◽  
Learning Models ◽  
Hot Strip Rolling ◽  
Strip Rolling ◽  
Bending Force ◽  
Hot Strip ◽  
Machine Learning Models

In the hot strip rolling (HSR) process, accurate prediction of bending force can improve the control accuracy of the strip crown and flatness, and further improve the strip shape quality. In this paper, six machine learning models, including Artificial Neural Network (ANN), Support Vector Machine (SVR), Classification and Regression Tree (CART), Bagging Regression Tree (BRT), Least Absolute Shrinkage and Selection operator (LASSO), and Gaussian Process Regression (GPR), were applied to predict the bending force in the HSR process. A comparative experiment was carried out based on a real-life dataset, and the prediction performance of the six models was analyzed from prediction accuracy, stability, and computational cost. The prediction performance of the six models was assessed using three evaluation metrics of root mean square error (RMSE), mean absolute error (MAE), and coefficient of determination (R2). The results show that the GPR model is considered as the optimal model for bending force prediction with the best prediction accuracy, better stability, and acceptable computational cost. The prediction accuracy and stability of CART and ANN are slightly lower than that of GPR. Although BRT also shows a good combination of prediction accuracy and computational cost, the stability of BRT is the worst in the six models. SVM not only has poor prediction accuracy, but also has the highest computational cost while LASSO showed the worst prediction accuracy.

Looper Lifter Movement Simulation for Continuous Hot Rolling

2010 ◽  
Vol 44-47 ◽  
pp. 494-498
Author(s):  
Shen Bai Zheng ◽  
Yue Long ◽  
Li Rong Gao ◽  
Li Wei Duan ◽  
Li Sheng Zhang
Keyword(s):  
Hot Rolling ◽  
Simulation System ◽  
Hot Strip Rolling ◽  
Strip Rolling ◽  
Hot Strip ◽  
Two Stages ◽  
Movement Simulation ◽  
Transfer Models

In the hot strip rolling simulation system, the movement of looper lifter is divided into two stages. First the lifter rises freely, then it is collided with strip bar. For the dynamic simulating, the transfer models and parameters for two serial moment motors or hydraulic looper lifters are built. On the base of a new tension formula, the tension with looper lifter is got by folding.

Sign in / Sign up

Export Citation Format

Share Document