A New Data-driven Roll Force and Roll Torque Model Based on FEM and Hybrid PSO-ELM for Hot Strip Rolling

Wang, Zhenhua; Zhang, Dianhua; Gong, Dunwei; Wen, Peng

doi:10.2355/isijinternational.isijint-2018-846

Cited by 20 publications

(8 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As shown in Table 1, the maximum error is 12.5%. Therefore, both the two maximum errors are within the engineering allowable value of 15% (Wang et al, 2019). It should be noted here that it is better to further give the comparison between the present results based on the present yield criterion and those based on the other yield criteria, which can further reflect the superiority of the present yield criterion.…”

Section: Experimental Validation Of Rolling Force and Thickness Predictionsupporting

confidence: 51%

Modeling of Rolling Force for Thick Plate of Multicomponent Alloys and Its Application on Thickness Prediction

2021

View full text Add to dashboard Cite

During the rolling process of thick plate, the nonlinear specific plastic power that derived from the non-linear Mises yield criterion is difficult to be integrated, which has restricted the establishment of a rolling force model. To solve this problem, a new yield criterion is firstly established, and then used to derive a linear specific plastic power. Meanwhile, a kinematically admissible velocity field whose horizontal velocity component obeys the Logistic function is proposed to describe the metal flow of the deformed plate. On these bases, the rolling energy items including the internal deformation power of the deformed body, friction power on the contact surface, and shear power on the entry and exit sections are integrated successively, and the rolling force model is established. It is proved that the model can predict the rolling force well when compared with the actual data of multicomponent alloys. Besides, the formula for predicting the outlet thickness is ultimately given upon this derived model, and a good agreement is also found between the predicted values and the actual ones, since the absolute errors between them are within 0.50 mm.

show abstract

Section: Experimental Validation Of Rolling Force and Thickness Predictionsupporting

confidence: 51%

Modeling of Rolling Force for Thick Plate of Multicomponent Alloys and Its Application on Thickness Prediction

2021

View full text Add to dashboard Cite

show abstract

“…Rolling is easier to realize intelligent optimization and control than forging and stamping due to its incremental deformation nature. Wang et al [ 58 ] established a regression model between rolling process parameters and rolling force using a data-driven extreme learning machine (ELM), and the PSO algorithm was used to optimize the model. They compared the prediction results of PSO-ELM with ELM and PSO-SVM.…”

Section: The State Of the Art Of Intelligent Optimization In The Plas...mentioning

confidence: 99%

A Review of the Intelligent Optimization and Decision in Plastic Forming

Tang

Wang²,

Deng³

et al. 2022

Materials

View full text Add to dashboard Cite

The plastic forming process involves many influencing factors and has some inevitable disturbance factors, rendering the multi-objective collaborative optimization difficult. With the rapid development of big data and artificial intelligence (AI) technology, intelligent process optimization has become one of the critical technologies for plastic forming. This paper elaborated on the research progress on the intelligent optimization of plastic forming and the data-driven process planning and decision-making system in plastic forming process optimization. The development trend in intelligent optimization of the plastic forming process was researched. This review showed that the intelligent optimization algorithm has great potential in controlling forming quality, microstructure, and performance in plastic forming. It is a general trend to develop an intelligent optimization model of the plastic forming process with high integration, versatility, and high performance. Future research will take the data-driven expert system and digital twin system as the carrier, integrate the optimization algorithm and model, and realize the multi-scale, high-precision, high-efficiency, and real-time optimization of the plastic forming process.

show abstract

“…By analyzing fracture toughness measurements, Liu et al [ 12 ] proposed a model based on ML to overcome the limitations and improve the reliability of engineering solutions. Wang et al [ 13 ] combined ML with an optimization algorithm, and successfully established a regression model of the rolling force and rolling torque of a strip in hot rolling. Thus, they provided a new research concept for profile and flatness control and optimization in hot rolling.…”

Section: Introductionmentioning

confidence: 99%

Strip Thickness and Profile–Flatness Prediction in Tandem Hot Rolling Process Using Mechanism Model‐Guided Machine Learning

Liu

Wang

Sun

et al. 2022

steel research int.

View full text Add to dashboard Cite

This study is focused on the multivariable, nonlinear, strong‐coupling, and time‐varying characteristics of the quality control process of hot strip rolling. Using the rolling process data from a continuously variable crown (CVC) mill of a 1580 mm hot tandem rolling line, a new prediction model of the strip thickness, profile, and flatness in hot rolling based on rolling mechanism model‐guided machine learning (ML) is developed. The weighted processing (WP) method is used to fuse the rolling mechanism and process data, to improve the relationship between the strong correlation features and the model. Combined with nondominated sorting genetic algorithm III (NSGA‐III), multiple parameters of multioutput support vector regression (M‐SVR) are optimized. The results show that the root mean square error (RMSE), mean square correlation coefficient (R 2), and mean absolute error (MAE) of the strip thickness, crown, and flatness are 2.0159, 1.3191, and 0.9355; 0.9854, 0.9895, and 0.9873; and 16.601, 1.126, and 0.604, respectively. Moreover, the established method of data fusion rolling mechanism shows strong capability to improve the model prediction accuracy, increasing it by 60%. Thus, it can offer theoretical guidance for realizing accurate control of the quality of strips and improving the quality of hot‐rolled products.

show abstract

A New Data-driven Roll Force and Roll Torque Model Based on FEM and Hybrid PSO-ELM for Hot Strip Rolling

Cited by 20 publications

References 19 publications

Modeling of Rolling Force for Thick Plate of Multicomponent Alloys and Its Application on Thickness Prediction

Modeling of Rolling Force for Thick Plate of Multicomponent Alloys and Its Application on Thickness Prediction

A Review of the Intelligent Optimization and Decision in Plastic Forming

Strip Thickness and Profile–Flatness Prediction in Tandem Hot Rolling Process Using Mechanism Model‐Guided Machine Learning

Contact Info

Product

Resources

About