Prediction and analysis of cold rolling mill vibration based on a data-driven method

Lü, Xing; Sun, Jie; Song, Zhixin; Li, Guangtao; Wang, Zhenhua; Hu, Yunjian; Wang, Qinglong; Zhang, Dianhua

doi:10.1016/j.asoc.2020.106706

Cited by 35 publications

(14 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to investigate the chatter problem in cold rolling mill, ensuring of a high-speed and stable rolling process is required. Neuralnetwork-based method and extreme gradient boosting method as a rapid technique was accomplished by Lu et al [18] to detect chatter mill. Results show that an effective way to eliminate the chatter mill was control the rolling speed, cumulative rolling strip length, tension and roll radius.…”

Section: Introductionmentioning

confidence: 99%

Using feed-forward perceptron Artificial Neural Network (ANN) model to determine the rolling force, power and slip of the tandem cold rolling

et al. 2023

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

Using feed-forward perceptron Artificial Neural Network (ANN) model to determine the rolling force, power and slip of the tandem cold rolling

et al. 2023

View full text Add to dashboard Cite

“…Theoretical and experimental research have been pointed out that , the remaining life prediction method of the rolling bearing mainly uses data-driven method. A data-driven vibration signal amplitude prediction method has been proposed [4]. Feature data has been extracted based on wavelet transform and VMD algorithm in time-frequency domain [5].…”

Section: Introductionmentioning

confidence: 99%

Deep learning method for remaining useful life prediction of the rolling bearing of high-speed train

Wang

Liang

2023

International Conference on Cyber Security, Artificial Intelligence, and Digital Economy (CSAIDE 2023)

View full text Add to dashboard Cite

In this paper, an optimized long short-term memory (LSTM) network is proposed for the remaining useful life (RUL) prediction of the rolling bearings based on whale optimized algorithm (WOA). The multi-domain features are extracted to construct the feature dataset as the single domain features are difficult to characterize the performance degeneration of the rolling bearing. Considering the possible gradient explosion by training of the rolling bearing lifetime data and the difficulties in selecting the key network parameters, an optimized LSTM network, namely, WOA-LSTM network is proposed. Experiment results show that, compared with the LSTM network, the RUL prediction accuracy of the rolling bearing are improved by the proposed WOA-LSTM network.

show abstract

“…Chatter has a serious impact on the operating state of the rolling mill, and occurs often in different working environments, especially in high‐speed, high‐strength rolling and variable gauge switching. The presence of vibration severely limits the quality and performance of plate and strip, and also results in manufacturing failures such as strip breaking, piling, or damaged rolling equipment 2 . As a result, rolling mill vibration has received a great deal of attention as a primary rolling mill operation index, and it is necessary and significant to research the chatter mechanism, as well as eliminate and suppress undesirable vibration occurring in the rolling process.…”

Section: Introductionmentioning

confidence: 99%

Modeling and vertical torsional coupling vibration control of the rolling mill with full state constraints

Qian

Chen

et al. 2022

Intl J Robust & Nonlinear

View full text Add to dashboard Cite

This article establishes a mechanical-electrical-hydraulic vertical torsional coupling vibration mathematical model, and investigates its vibration suppression control strategy with time varying full state constraints for the rolling mill vertical torsional coupling vibration system. Firstly, the mechanical-electrical-hydraulic vertical torsional coupling vibration nonlinear model is developed using dynamic theory, which takes into account nonlinear damping, nonlinear rolling force and the coupling relationship between the vertical vibration system and the torsional vibration system. Then, nonlinear constraint transformation functions and coordinate transformations are implemented to remove the feasibility condition in handling the full state constraints problem, and neural networks are used to approximate unknown nonlinear functions. Furthermore, the vibration suppression control algorithm of the mechanical-electrical-hydraulic vertical torsional coupling system is designed with the specific sequence backstepping method and dynamic surface control technique, which can resolve the problem of nesting in the controller design process. Finally, the effective of the proposed method on vibration suppression is verified by the simulation.

show abstract

Prediction and analysis of cold rolling mill vibration based on a data-driven method

Cited by 35 publications

References 41 publications

Using feed-forward perceptron Artificial Neural Network (ANN) model to determine the rolling force, power and slip of the tandem cold rolling

Using feed-forward perceptron Artificial Neural Network (ANN) model to determine the rolling force, power and slip of the tandem cold rolling

Deep learning method for remaining useful life prediction of the rolling bearing of high-speed train

Modeling and vertical torsional coupling vibration control of the rolling mill with full state constraints

Contact Info

Product

Resources

About