The Optimization of Roll Force Model in Hot Strip Mill

2014 ◽  
Vol 926-930 ◽  
pp. 3705-3708
Author(s):  
Geng Sheng Ma ◽  
Fang Chen Yin ◽  
Zhu Wen Yan ◽  
He Nan Bu ◽  
Wen Peng ◽  
...  
Keyword(s):  
Prediction Accuracy ◽  
Rolling Force ◽  
Strip Thickness ◽  
Deformation Resistance ◽  
Hot Strip Mill ◽  
Force Model ◽  
Roll Force ◽  
Adaptive Model ◽  
Hot Strip ◽  
High Prediction

The accuracy of roll force model and the rationality of roll fore adaptive model play a key role in obtaining the thickness of strip with high precision. The roll force model has been established. It includes the elastic flattened roller model and deformation resistance model considering the chemical composition of strip. A deformation resistance-based fitting curve is proposed in rolling force adaption, it can be inherited to any other thick range class. Application results show that the rolling force model and its adaptation are with high prediction accuracy and it has improved the strip thickness accuracy.

Applying Deformation Resistance Estimation Method to Predict Nine Stand Hot Strip Mill Rolling Force

2012 ◽  
Vol 472-475 ◽  
pp. 451-455
Author(s):  
Yan Bing He ◽  
Yu Hua Pang ◽  
Jin Zhi Zhang ◽  
Li Peng Zhu
Keyword(s):  
High Speed ◽  
Rolling Force ◽  
Estimation Method ◽  
Deformation Resistance ◽  
Forecasting Model ◽  
Hot Strip Mill ◽  
Continuous Rolling ◽  
Hot Strip ◽  
Hot Continuous Rolling ◽  
Rolling Production

The rolling force of the nine stand hot continuous rolling production line is predicted on the base of the deformation resistance estimation method. The predicted error is turned out to be about 10% through the comparing analysis of the predicted rolling force and actual rolling force, which proves the feasibility of the forecasting model. One can get the deformation resistance without experiments by using this method, besides, this method works in a high speed.

scholarly journals Modelling of Deformation Resistance with Big Data and Its Application in the Prediction of Rolling Force of Thick Plate

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Shun Hu Zhang ◽  
Li Zhi Che ◽  
Xin Ying Liu
Keyword(s):  
Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
Bp Neural Network ◽  
Prediction Accuracy ◽  
Rolling Force ◽  
Deformation Resistance ◽  
Force Model ◽  
The Neural Network ◽  
Bp Neural Network Model

The precision of traditional deformation resistance model is limited, which leads to the inaccuracy of the existing rolling force model. In this paper, the back propagation (BP) neural network model was established according to the industrial big data to accurately predict the deformation resistance. Then, a new rolling force model was established by using the BP neural network model. During the establishment of the neural network model, the data set of deformation resistance was established, which was calculated back from the actual rolling force data. Based on the data set after normalization, the BP neural network model of deformation resistance was established through the optimization of algorithm and network structure. It is shown that both the prediction accuracy of the neural network model on the training set and the test set are high, indicating that the generalization ability of the model is strong. The neural network model of the deformation resistance is compared with the theoretical one, and the maximum error is only 3.96%. Furthermore, by comparison with the traditional rolling force model, it is found that the prediction accuracy of the rolling force model imbedding with the present neural network model is improved obviously. The maximum error of the present rolling force model is just 3.86%. The research in this paper provides a new way to improve the prediction accuracy of rolling force model.

Application of Probabilistic Neural Network in the Rolling Rhythm Evaluation of Hot Strip Mill

2012 ◽  
Vol 572 ◽  
pp. 67-71
Author(s):  
Chao Chao Chen ◽  
An Rui He ◽  
Jian Shao ◽  
Jian Hua Liu ◽  
Jie Zhou
Keyword(s):  
Neural Network ◽  
Hot Rolling ◽  
Prediction Accuracy ◽  
Simple Structure ◽  
Probabilistic Neural Network ◽  
Evaluation Model ◽  
Hot Strip Mill ◽  
Fast Calculation ◽  
Hot Strip ◽  
High Prediction

In this paper, the probabilistic neural network and prediction thought are combined to evaluate hot rolling rhythm. An evaluation model of hot rolling rhythm based on PNN network is established. To verify the validity of the model and predicted results, the PNN network model is applied to practical production of a hot strip mill and proves to be a model of simple structure, fast calculation, high prediction accuracy and strong generalization ability, which is able to substitute for the conventional evaluation model based on the empirical formula and empirical data.

Data Fusion Based Quality Monitoring and Control of Strip Thickness

2011 ◽  
Vol 230-232 ◽  
pp. 266-273
Author(s):  
Kai Xiang Peng ◽  
Dong Hua Zhou
Keyword(s):  
Data Fusion ◽  
Rolling Force ◽  
Strip Thickness ◽  
Hot Strip Mill ◽  
Monitoring And Control ◽  
Hot Strip Rolling ◽  
Fusion Algorithm ◽  
Thickness Control ◽  
Hot Strip ◽  
Plasticity Coefficient

This paper first introduces the principle of AGC and conventional AGC in Hot Strip Mill (HSM). A linearized and discretized state-space model used for rolling force and thickness control is obtained by using recursive squares method. A data fusion algorithm based on Kalman filter is presented. For hot strip systems with complex multi-variables, an asynchronous fusion estimation algorithm is built and applied to the thickness prediction of the hot strip mill and the plasticity coefficient Q of strip prediction. Finally, real-time prediction on thickness and plasticity coefficient of the coming strip is synthetically utilized in hot strip rolling thickness control system, to improve the quality of final coming strip thickness.

The Optimization of Thickness Model Adaption in Hot Strip Mill

2014 ◽  
Vol 941-944 ◽  
pp. 1700-1703
Author(s):  
Geng Sheng Ma ◽  
Fang Chen Yin ◽  
Wen Peng ◽  
Yuan Ming Liu ◽  
Jing Guo Ding ◽  
...  
Keyword(s):  
Adaptive System ◽  
Rolling Force ◽  
Specific Model ◽  
Hot Strip Mill ◽  
Force Model ◽  
Convection Coefficient ◽  
Temperature Model ◽  
Quadratic Curve ◽  
Hot Strip ◽  
Model Temperature

Thickness model adaption plays a important role in obtaining strip with high thickness precision. In order to improve the thickness precision, a complete thickness model adaption system has been designed for every specific model used in the setup system including gap position model, temperature model, rolling force model. Snapshot data and stretch equation are used to adapt gap position. Forced convection coefficient is selected as adaption parameter. A deformation resistance-based fitting quadratic curve is proposed in rolling force adaption, it can be inherited to any other thick range class and a quick thickness adaption method is introduced. Application results show that this adaptive system is with high accuracy, quick adaption and high stability.

A 3-D Differential Method for Solving Rolling Force of PC Hot Strip Mill

2010 ◽  
Vol 17 (9) ◽  
pp. 36-39 ◽  
Author(s):  
Xue-song Wang ◽  
Yan Peng ◽  
Li-pu Xu ◽  
Hong-min Liu
Keyword(s):  
Rolling Force ◽  
Differential Method ◽  
Hot Strip Mill ◽  
Hot Strip

Research on Online Model of Vertical Rolling Force in Hot Strip Roughing Trains

2010 ◽  
Vol 145 ◽  
pp. 198-203 ◽  
Author(s):  
Guo Ming Yuan ◽  
Jian Wang ◽  
Hong Xiao ◽  
Ming Lei Li
Keyword(s):  
Rolling Force ◽  
Fem Simulation ◽  
Simulation Software ◽  
External Stress ◽  
New Method ◽  
Hot Strip Mill ◽  
Deformation Degree ◽  
Hot Strip ◽  
New Formula ◽  
Force Calculation

For low prediction precision of online model for vertical rolling force in roughing trains of hot strip mill, the process of hot strip roughing trains was simulated by the FEM simulation software DEFORM. The cause of low prediction precision of rolling force during vertical rolling was analyzed. Then the new method for calculating deformation degree when edge rolling was presented by analysis of the FEM simulated results. The formula of external stress status modulus, which is fit for the vertical rolling force calculation, was obtained by analytic regression. Furthermore, a new formula about rolling force calculation was gained. It was approved that the prediction precision was obviously enhanced compared with the practical data for vertical rolling force.

Sign in / Sign up

Export Citation Format

Share Document