Application of the gradient boosting decision tree in the online prediction of rolling force in hot rolling

Wang, Qiuna; Song, Lin; Zhao, Jianwei; Li, Ang; Dong, Lijie; Wang, Xiaochen; Yang, Quan

doi:10.1007/s00170-022-10716-z

Cited by 14 publications

(2 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Roll separating force (RSF) prediction is crucial for new mill design, schedule optimization, and online process management in rolling mills. [3,4].…”

Section: Introductionmentioning

confidence: 99%

Analytical Approximation and Evaluation of Roll Separating Force in Bar Rolling Process.

Mistry,

Judal

2024

Preprint

View full text Add to dashboard Cite

Designing the roller and determining the required passes to manufacture the bar depend on the estimation of the pressure value during the bar rolling operation. Numerous researchers have proposed a mean unit pressure formula based on the flat rolling process formula. However, it is challenging to predict the pressure accurately using these formulas. Hence, the principle of sticking and slipping friction as well as weak plane strain is applied to derive the analytical formula based on slab analysis. To apply the proposed formula for different types of passes, the given pass shape is converted into an equivalent rectangular bar and assumed that it is pressed between two flat plates. Prediction of metal flow stress value is calculated by using Shida’s formula with the proposed equation for the correction in input temperature of the hot metal. The constitutive formula of the roll separating force (RSF) is proposed based on these parameters. A comparison is made between the suggested formula and the experimental values which is available in the literature. The findings reveal that the RSF values obtained by applying the suggested method offer a reliable approximation for different kinds of passes.

show abstract

“…Roll separating force (RSF) prediction is crucial for new mill design, schedule optimization, and online process management in rolling mills. [3,4].…”

Section: Introductionmentioning

confidence: 99%

Analytical Approximation and Evaluation of Roll Separating Force in Bar Rolling Process.

Mistry,

Judal

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Flatness defects that may occur between the two stands have a detrimental effect on the stability of rolling and may even cause serious accidents such as breaking and piling-up of the steel strip during hot tandem rolling [2,3]. Affected by the roll deformation caused by the rolling force, the roll thermal contour, the roll wear contour and the strip entry crown, the crown of the strip often cannot reach the target value at the exit of the stand [4][5][6].…”

Section: Introductionmentioning

confidence: 99%

Numerical Study on Metal Transverse Flow Law and Model of Rolled Strip under Variable Specification in Hot Rolling

Chai,

Li,

Shang

2023

Metals

View full text Add to dashboard Cite

The research on metal transverse flow under variable specification is of great significance for shape calculation and control in hot strip rolling. The finite element software ABAQUS 2016 is used to establish the elastic–plastic deformation model of a hot rolled strip to study the metal transverse flow. The edge transverse strain εe and center transverse strain εc are introduced to characterize metal transverse flow and calculate the strip flatness. The effect on εe, εc and the flatness increment of similarity of profile under different widths, thicknesses and reduction rates is simulated and calculated. The results show that the change in similarity of profile has a linear influence on εe and εc. The strip has the ability of flatness self-correction due to the metal transverse flow. The ksc of the strip with B = 700 mm is 0.87, which is significantly greater than the 0.45 ksc value of the strip with B = 2100 mm. Priority can be given to ensure the crown requirements during narrow strip rolling. The ksc of the strip with H = 50 mm is 0.45, which is higher than the 0.22 ksc value of the strip with H = 6 mm, and the ksc of the strip with ε = 50% is 0.52, which is higher than 0.30 ksc value of the strip with ε = 10%. It is more reasonable to adjust the crown to a greater extent in the upstream stand to meet the requirement of both flatness and crown for the large entry thickness reduction rate and self-correction ability. A metal transverse flow prediction model based on the full test simulation results is established, which can meet the requirement of crown setting at the exit of each stand and the rapid calculation of online flatness control, and can further make the crown and flatness reach the target values at the finishing exit.

show abstract

Chatter detection in simulated machining data: a simple refined approach to vibration data

Alberts,

St. John,

Jared

et al. 2024

Int J Adv Manuf Technol

View full text Add to dashboard Cite

Vibration monitoring is a critical aspect of assessing the health and performance of machinery and industrial processes. This study explores the application of machine learning techniques, specifically the Random Forest (RF) classification model, to predict and classify chatter—a detrimental self-excited vibration phenomenon—during machining operations. While sophisticated methods have been employed to address chatter, this research investigates the efficacy of a novel approach to an RF model. The study leverages simulated vibration data, bypassing resource-intensive real-world data collection, to develop a versatile chatter detection model applicable across diverse machining configurations. The feature extraction process combines time-series features and Fast Fourier Transform (FFT) data features, streamlining the model while addressing challenges posed by feature selection. By focusing on the RF model’s simplicity and efficiency, this research advances chatter detection techniques, offering a practical tool with improved generalizability, computational efficiency, and ease of interpretation. The study demonstrates that innovation can reside in simplicity, opening avenues for wider applicability and accelerated progress in the machining industry.

show abstract

Application of the gradient boosting decision tree in the online prediction of rolling force in hot rolling

Cited by 14 publications

References 28 publications

Analytical Approximation and Evaluation of Roll Separating Force in Bar Rolling Process.

Analytical Approximation and Evaluation of Roll Separating Force in Bar Rolling Process.

Numerical Study on Metal Transverse Flow Law and Model of Rolled Strip under Variable Specification in Hot Rolling

Chatter detection in simulated machining data: a simple refined approach to vibration data

Contact Info

Product

Resources

About