Hybrid intelligent modelling and simulation for cold tandem rolling process

Tie, Ming; Bi, Jing; Ding, Jinliang

doi:10.1049/iet-cta.2015.0842

Cited by 4 publications

(3 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A two-step CBR method using genetic algorithm to find the optimal attributes subset based on the evaluation method of Correlation-based Feature Selection was proposed for predicting the endpoint phosphorus content in BOF efficiently [15]. To be simulate dynamics of cold tandem rolling processes, a novel hybrid intelligent dynamic modelling approach is proposed based on the combination of a linearized state space model derived from various mechanism equations, a CBR algorithm for multi-state space models selection, a genetic algorithm for optimization of case attributes, an adaptive fractal filtering algorithm for the identification of state space model parameters, a neural network-based simulation error compensation model for the strip exit velocity [16]. CBR based on two-step retrieval approach and the correlation-based feature weighting method was proposed for predicting end temperature of molten steel in LF [17].…”

Section: Literature Reviewmentioning

confidence: 99%

Case-based reasoning method based on mechanistic model correction for predicting endpoint sulphur content of molten iron in KR desulphurization

Feng

et al. 2019

Ironmaking & Steelmaking

View full text Add to dashboard Cite

In order to improve the control on sulphur content at the endpoint of Kanbara Reactor (KR) desulphurization process, the case-based reasoning (CBR) method based on mechanistic model correction is used to predict the endpoint sulphur content of molten iron. First, the KR desulphurization process is analysed to determine its kinetic mechanistic model, and partial derivatives are obtained for different attributes. Then, according to the analysis ofthe attributes, the corrected model is determined by the method of selecting the attributes, determining the reasonable weights and fitting the calculation results. Finally, the CBR method, the Back Propagation Neural Network (BPNN) and the corrected model are used to predict the endpoint sulphur content at KR desulphurization. The experiment results indicate that the prediction accuracy of corrected model is significantly higher than that of BPNN and mechanistic model.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Case-based reasoning method based on mechanistic model correction for predicting endpoint sulphur content of molten iron in KR desulphurization

Feng

et al. 2019

Ironmaking & Steelmaking

View full text Add to dashboard Cite

show abstract

“…The traditional bending force preset is optimized for the minimum deviation of the roll gap crown (Liu and Lee, 2005; Yan et al , 2016; Li et al , 2015; Wang et al , 2007; Tie et al , 2016; Alaei et al , 2016; Wang et al , 2014; Yi, 2015; Zhang et al , 2014), and the objective function is established as follows: where, f B ( F FW , F FI ) is a traditional bending force preset objective function; i is the measure segment number in axial direction; n is the number of feature points, n = 20; δC r ( i ) is gap crown deviation; g FW ( i ) is working roll bending force efficacy coefficient; F FW is working roll bending force preset value; g FI ( i ) is an intermediate roll bending force efficacy coefficient; and F FI is an intermediate roll bending force preset value.…”

Section: Establishment Of Bending Force Preset Multi-objective Functionmentioning

confidence: 99%

Multi-objective optimization of bending force preset in cold rolling

Zhou

Yan

et al. 2019

View full text Add to dashboard Cite

Purpose In the process of cold rolled strip, there is tight coupling between flatness control and gauge control. The variation of the roll gap caused by the change of bending force will lead to the change of rolling force. Furthermore, it can cause a deep impact on the control accuracy of strip exit thickness and exit crown. The purpose of this paper is to improve the accuracy of the bending force preset value for cold rolled strip. Design/methodology/approach In this paper, the bending force preset control strategy with considering of rolling force was proposed for the first time and the preset objective function of bending force was established on the basis of the two-objective optimization of bending force and rolling force. Meanwhile, the multi-objective intelligent algorithm – INSGA-II – was used to solve the objective function. Findings The proposed bending force multi-objective preset model has been tested in a 1,450 mm tandem cold rolling line. The analyzed results of field data show that the deviations of strip exit thickness and exit crown are reduced effectively by using the improved model, and at the same time, more reasonable bending force preset values are obtained, which can enhance the accuracy of flatness preset control. Originality/value A preset model of bending force with considering flatness and gauge is proposed in this paper and the multi-objective function of bending force preset is established on the basis of the two-objective optimization of bending force and rolling force. The value lies in proposing a new decoupling method of rolling force and bending force.

show abstract

“…Due to intense complexity of MMFSS, it is difficult to derive a accurate mathematical model that can well describe the dynamic behaviour of the practical system. Most industrial processes including MMFSS can be controlled by using a simple model developed from first principles [5]. The uncertainty is usually described as the uncertainty of the model parameters.…”

Section: Introductionmentioning

confidence: 99%