Multi-dimension and multi-modal rolling mill vibration prediction model based on multi-level network fusion

Abstract

Mill vibration is a common problem in rolling production, which directly affects the thickness accuracy of the strip and may even lead to strip fracture accidents in serious cases. The existing vibration prediction models do not consider the features contained in the data, resulting in limited improvement of model accuracy. To address these challenges, this paper proposes a multi-dimensional multi-modal cold rolling vibration time series prediction model (MDMMVPM) based on the deep fusion of multi-level networks. In the model, the long-term and short-term modal features of multi-dimensional data are considered, and the appropriate prediction algorithms are selected for different data features. Based on the established prediction model, the effects of tension and rolling force on mill vibration are analyzed. Taking the 5th stand of a cold mill in a steel mill as the research object, the innovative model is applied to predict the mill vibration for the first time. The experimental results show that the correlation coefficient (R ²) of the model proposed in this paper is 92.5%, and the root-mean-square error (RMSE) is 0.0011, which significantly improves the modeling accuracy compared with the existing models. The proposed model is also suitable for the hot rolling process, which provides a new method for the prediction of strip rolling vibration.

Keywords

rolling mill vibration / multi-dimension data / multi-modal data / convolutional neural network / time series prediction

References

[1] Liu Y-j, Wang S, Qi J-b, et al. Vibrations of tandem cold rolling mill: Coupled excitation of rolling force and variable stiffness of fault-free back-up roll bearing [J]. Journal of Iron and Steel Research International, 2023, 30(9): 1792-1802

[2] Fujita N, Kimura Y, Kobayashi K, et al. Dynamic control of lubrication characteristics in high speed tandem cold rolling [J]. Journal of Materials Processing Technology, 2016, 229: 407-416

[3] Cao L, Li X, Wang Q-l, et al. Vibration analysis and numerical simulation of rolling interface during cold rolling with unsteady lubrication [J]. Tribology International, 2021, 153: 106604

[4] Wang M, Xu H-d, He D-p, et al. Design of a damped vibration absorber to control the resonant vibration of roll [J]. Mechanical Systems and Signal Processing, 2022, 178: 109262

[5] Ji Y-f, Song L-b, Sun J, et al. Application of SVM and PCA-CS algorithms for prediction of strip crown in hot strip rolling [J]. Journal of Central South University, 2021, 28(8): 2333-2344

[6] Liu Z-l, Li P, Jiang J-h, et al. Research on vibration characteristics of mill rolls based on nonlinear stiffness of the hydraulic cylinder [J]. Journal of Manufacturing Processes, 2021, 64: 1322-1328

[7] Qi J-b, Wang X-x, Yan X-qiang. Influence of mill modulus control gain on vibration in hot rolling Mills [J]. Journal of Iron and Steel Research International, 2020, 27(5): 528-536

[8] Yan X-q, Qi J-b, Wang X-xin. An active method suppressing rolling mill vibration: Disturbance estimation and compensation algorithm [J]. Journal of Iron and Steel Research International, 2019, 26(7): 697-703

[9] Lu X, Sun J, Wei Z, et al. Effect of minimum friction coefficient on vibration stability in cold rolling mill [J]. Tribology International, 2021, 159: 106958

[10] Liu X-c, Zang Y, Gao Z-y, et al. Time delay effect on regenerative chatter in tandem rolling Mills [J]. Shock and Vibration, 2016, 2016: 4025650

[11] Lu X, Sun J, Li G-t, et al. Stability analysis of a nonlinear coupled vibration model in a tandem cold rolling mill [J]. Shock and Vibration, 2019, 20191: 4358631

[12] Cao L, Li X, Zhang D-hua. Research into the effect of flatness control actuators on vibration stability in cold rolling using the finite element method [J]. The International Journal of Advanced Manufacturing Technology, 2023, 125(1): 245-266

[13] Hejazi S A M, Feyzpour A, Khaje Khabaz M, et al. Numerical investigation of rigidity and flexibility parameters effect on superstructure foundation behavior using threedimensional finite element method [J]. Case Studies in Construction Materials, 2023, 18: e01867

[14] Mosayebi M, Zarrinkolah F, Farmanesh K. Calculation of stiffness parameters and vibration analysis of a cold rolling mill stand [J]. The International Journal of Advanced Manufacturing Technology, 2017, 91(9): 4359-4369

[15] Hemmat Esfe M, Hajian M, Toghraie D, et al. Prediction the dynamic viscosity of MWCNT-Al₂O₃ (30: 70)/oil 5W50 hybrid nano-lubricant using principal component analysis (PCA) with artificial neural network (ANN) [J]. Egyptian Informatics Journal, 2022, 23(3): 427-436

[16] Ding C-y, Sun J, Li X-j, et al. A high-precision and transparent step-wise diagnostic framework for hot-rolled strip crown [J]. Journal of Manufacturing Systems, 2023, 71: 144-157

[17] Ma K, Shen Q-q, Sun X-y, et al. Rockburst prediction model using machine learning based on microseismic parameters of Qinling water conveyance tunnel [J]. Journal of Central South University, 2023, 30(1): 289-305

[18] Liu H, Zhang X-y, Yang Y-x, et al. Hourly traffic flow forecasting using a new hybrid modelling method [J]. Journal of Central South University, 2022, 294: 1389-1402

[19] Xia J S, Khaje Khabaz M, Patra I, et al. Using feed-forward perceptron Artificial Neural Network (ANN) model to determine the rolling force, power and slip of the tandem cold rolling [J]. ISA Transactions, 2023, 132: 353-363

[20] Esfe M H, Esmaily R, Khabaz M K, et al. A novel integrated model to improve the dynamic viscosity of MWCNT-Al₂O₃ (40: 60)/oil 5W50 hybrid nano-lubricant using artificial neural networks (ANNs) [J]. Tribology International, 2023, 178: 108086

[21] Babajamali Z, Khabaz M K, Aghadavoudi F, et al. Pareto multi-objective optimization of tandem cold rolling settings for reductions and inter stand tensions using NSGAII [J]. ISA Transactions, 2022, 130: 399-408

[22] Zhang Y, Wang W-z, Zhang H, et al. Vibration monitoring and analysis of strip rolling mill based on the digital twin model [J]. The International Journal of Advanced Manufacturing Technology, 2022, 122(9): 3667-3681

[23] Lu X, Sun J, Song Z-x, et al. Prediction and analysis of cold rolling mill vibration based on a data-driven method [J]. Applied Soft Computing, 2020, 96: 106706

[24] Pan J, Chen J-l, Zi Y-y, et al. Monocomponent feature extraction for mechanical fault diagnosis using modified empirical wavelet transform via data-driven adaptive Fourier spectrum segment [J]. Mechanical Systems and Signal Processing, 2016, 72: 160-183

[25] Pan J, Chen J-l, Zi Y-y, et al. Data-driven mono-component feature identification via modified nonlocal means and MEWT for mechanical drivetrain fault diagnosis [J]. Mechanical Systems and Signal Processing, 2016, 80: 533-552

[26] Lu X, Sun J, Li G-t, et al. Dynamic analysis of vibration stability in tandem cold rolling mill [J]. Journal of Materials Processing Technology, 2019, 272: 47-57

[27] Chen J-l, Wan Z-g, Pan J, et al. Customized maximal-overlap multiwavelet denoising with data-driven group threshold for condition monitoring of rolling mill drivetrain [J]. Mechanical Systems and Signal Processing, 2016, 68: 44-67

[28] Ma L, Dong J, Peng K-x, et al. A novel databased quality-related fault diagnosis scheme for fault detection and root cause diagnosis with application to hot strip mill process [J]. Control Engineering Practice, 2017, 67: 43-51

[29] Zhang Y, Lin R-m, Zhang H, et al. Vibration prediction and analysis of strip rolling mill based on XGBoost and Bayesian optimization [J]. Complex & Intelligent Systems, 2023, 91: 133-145

[30] Zhao H-m, Liu H-d, Jin Y, et al. Feature extraction for data-driven remaining useful life prediction of rolling bearings [J]. IEEE Transactions on Instrumentation and Measurement, 2021, 70: 3511910

[31] Ding C-y, Sun J, Li X-j, et al. Intelligent diagnosis for hot-rolled strip crown with unbalanced data using a hybrid multi-stage ensemble model [J]. Journal of Central South University, 2024, 313: 762-782

[32] Brauwers G, Frasincar F. A general survey on attention mechanisms in deep learning [J]. IEEE Transactions on Knowledge and Data Engineering, 2023, 35(4): 3279-3298