Neural network modelling of flow stress and mechanical properties for hot strip rolling of TRIP steel using efficient learning algorithm

2013 ◽  
Vol 40 (4) ◽  
pp. 298-304 ◽  
Author(s):  
S K Das
Keyword(s):  
Neural Network ◽  
Mechanical Properties ◽  
Flow Stress ◽  
Trip Steel ◽  
Learning Algorithm ◽  
Hot Strip Rolling ◽  
Strip Rolling ◽  
Network Modelling ◽  
Hot Strip ◽  
Efficient Learning

A Method of Establishing Temperature Schedule during ASP Hot Strip Rolling

2011 ◽  
Vol 704-705 ◽  
pp. 1298-1303
Author(s):  
Yan Feng Zhao ◽  
Dian Hua Zhang ◽  
Yun Bo Xu ◽  
Xiao Ying Hou ◽  
Guo Dong Wang
Keyword(s):  
Neural Network ◽  
Mechanical Properties ◽  
Bp Neural Network ◽  
Pipeline Steel ◽  
Rolling Temperature ◽  
Hot Strip Rolling ◽  
Strip Rolling ◽  
X70 Pipeline Steel ◽  
Temperature Schedule ◽  
Hot Strip

Based on the actual production data of ASP (Angang Strip Production) hot strip rolling line, mechanical properties of thin gauge X70 pipeline steel were simulated by BP neural network method. Recursive functions were used to verify the mechanical properties which calculated by BP neural network. Based on predicted mechanical properties with high precision, BP neural network and Genetic Algorithm (GA) were combined to establish the temperature schedule of X70 pipeline steel during ASP hot strip rolling. It is shown that there are four important temperatures during ASP hot strip rolling, such as rough rolling temperature, refine start rolling temperature, refine finish rolling temperature and coiling temperature. Temperature difference of adjacent stages and temperature of former stage is a linear function relationship. For a given mechanical properties, deviations between simulated temperature and actual temperature are within ±10°C. This method can be used to produce different strips with the same compositions but different strengths by regulating suitable temperature schedule, so it is effective to resolve conflicts during hot strip rolling.

Application of Deformation to Improve Hot Ductility in the Peritectic Steel

2005 ◽  
Vol 500-501 ◽  
pp. 203-210 ◽  
Author(s):  
Ahmad Rezaeian ◽  
Faramarz Zarandi ◽  
D.Q. Bai ◽  
Steve Yue
Keyword(s):  
Flow Stress ◽  
High Strength ◽  
Microalloyed Steels ◽  
Hot Strip Mill ◽  
Mean Flow ◽  
Hot Strip Rolling ◽  
Strip Rolling ◽  
Slip Ratio ◽  
Hot Strip ◽  
Mean Flow Stress

The hot strip rolling of advanced microalloyed high strength steels still represents a new task to many mills due to the lack of data on the hot deformation resistance. With the aid of processing data from the Ispat-Inland hot strip mill, the “measured mean flow stresses” are calculated from the mill force using the Sims analysis and taking into account roll flattening, slip ratio and the redundant strain. A modification of the Misaka mean flow stress equation is proposed for C – Mn – Si – Al steels microalloyed with up to 0.02 % Nb. The effects of alloying and microalloying are then estimated. A new fitting parameter shows excellent agreement with the mean flow stress data from industrial processing of advanced high strength microalloyed steels. However, during the second half of the rolling schedule (lower temperature region), indications of austeniteto- ferrite transformation were found.

Coiling Temperature Prediction and Application Based on Genetic-Neural Network on Hot Strip Mill

2013 ◽  
Vol 448-453 ◽  
pp. 3417-3420 ◽  
Author(s):  
Tie Jun Sun ◽  
Wei Dong Yang ◽  
Hai Gao ◽  
Hong Tao Mi
Keyword(s):  
Neural Network ◽  
Hot Strip Mill ◽  
Hot Strip Rolling ◽  
Coiling Temperature ◽  
Strip Rolling ◽  
Control Precision ◽  
Hot Strip ◽  
On Line ◽  
Genetic Neural Network ◽  
Coiling Temperature Control

Coiling temperature control (CTC) is very important to the quality of the strip steel in Hot Strip Rolling Mill. In the paper, genetic algorithm and neural network method to predict coiling temperature on hot strip mill were put forward. The genetic-neural network was trained and checked with actual production data. The result indicates that the method can real-time predict the strip coiling temperature. The on-line prediction model and step track method has been put into use. The result shows that the method can settle lag influence in feedback control and the CTC control precision is improved greatly.

scholarly journals Prediction of Mean Flow Stress during Hot Strip Rolling Using Genetic Algorithms

2014 ◽  
Vol 54 (1) ◽  
pp. 171-178 ◽  
Author(s):  
Antonella Dimatteo ◽  
Marco Vannucci ◽  
Valentina Colla
Keyword(s):  
Genetic Algorithms ◽  
Flow Stress ◽  
Mean Flow ◽  
Hot Strip Rolling ◽  
Strip Rolling ◽  
Hot Strip ◽  
Mean Flow Stress

Modeling of the Resistance to Hot Deformation and the Effects of Microalloying in High-Al Steels under Industrial Conditions

2005 ◽  
Vol 500-501 ◽  
pp. 195-202 ◽  
Author(s):  
Fulvio Siciliano ◽  
Evgueni I. Poliak
Keyword(s):  
Flow Stress ◽  
Hot Deformation ◽  
High Strength ◽  
Microalloyed Steels ◽  
Hot Strip Mill ◽  
Mean Flow ◽  
Hot Strip Rolling ◽  
Strip Rolling ◽  
Hot Strip ◽  
Mean Flow Stress

The hot strip rolling of advanced microalloyed high strength steels still represents a new task to many mills due to the lack of data on the hot deformation resistance. With the aid of processing data from the Ispat-Inland hot strip mill, the “measured mean flow stresses” are calculated from the mill force using the Sims analysis and taking into account roll flattening, slip ratio and the redundant strain. A modification of the Misaka mean flow stress equation is proposed for C – Mn – Si – Al steels microalloyed with up to 0.02 % Nb. The effects of alloying and microalloying are then estimated. A new fitting parameter shows excellent agreement with the mean flow stress data from industrial processing of advanced high strength microalloyed steels. However, during the second half of the rolling schedule (lower temperature region), indications of austeniteto- ferrite transformation were found.

Sign in / Sign up

Export Citation Format

Share Document