基于FDA-LSTM的冷轧过程多源异构时序数据处理及颤振预测

赵潇雅,郜志英,周晓敏,宋寅虎

振动与冲击 ›› 2022, Vol. 41 ›› Issue (22) : 202-210.

PDF(4211 KB)
PDF(4211 KB)
振动与冲击 ›› 2022, Vol. 41 ›› Issue (22) : 202-210.
论文

基于FDA-LSTM的冷轧过程多源异构时序数据处理及颤振预测

  • 赵潇雅,郜志英,周晓敏,宋寅虎
作者信息 +

Multi-source heterogeneous time series data processing and chatter prediction based on the method of FDA-LSTM in cold rolling processes

  • ZHAO Xiaoya,GAO Zhiying,ZHOU Xiaomin,SONG Yinhu
Author information +
文章历史 +

摘要

冷连轧颤振诱发机理复杂多变,颤振问题的解决需要通过大数据驱动的信息挖掘对机理模型进行补充。该研究针对某冷连轧机现场采集的工艺参数及振动数据,通过函数型数据分析 (functional data analysis ,FDA) 方法进行预处理,实现多源异构时序数据的频率协同;采用SelectKBest算法对影响颤振的多种工艺参数进行特征选择,筛选出与振动相关性较强的因素,构造样本空间;基于长短时记忆 (long short-term memory ,LSTM) 神经网络建立振动能量值的预测模型,并与径向基函数 (radial basis function ,RBF) 神经网络、循环神经网络 (recurrent neural network ,RNN) 模型进行比较。结果表明,LSTM模型具有较高的预测精度,同时采用阈值法验证该模型能有效地预测颤振的发生。
关键词:冷连轧颤振;多源异构时序数据;函数型数据分析(FDA);长短时记忆 (LSTM) 神经网络

Abstract

The induced mechanism of cold tandem rolling chatter is complex and changeable, and the solution of chatter problem needs to supplement the mechanism model through big data-driven information mining. In this paper, based on the process parameters and vibration data collected on-site in cold tandem rolling mills, preprocessed by the functional data analysis (FDA) method to achieve frequency coordination of multi-source heterogeneous time series data, thereby improving the accuracy of sample expansion. Making a feature selection for kinds of process parameters that strongly affected chatter with SelectKBest algorithm, and to construct a sample space. The prediction model of vibration energy value was established based on long short-term memory (LSTM) neural network, and compared with the radial basis function (RBF) neural network and the recurrent neural network (RNN) models, the results showed that the LSTM model had higher prediction accuracy. And the threshold method was used to verify that the model can effectively predict the occurrence of chatter.
Keywords: cold tandem rolling chatter; multi-source heterogeneous time series data; functional data analysis (FDA); long short-term memory  (LSTM) neural network

关键词

冷连轧颤振 / 多源异构时序数据 / 函数型数据分析(FDA) / 长短时记忆 (LSTM) 神经网络

Key words

cold tandem rolling chatter / multi-source heterogeneous time series data / functional data analysis (FDA) / long short-term memory  / (LSTM) neural network

引用本文

导出引用
赵潇雅,郜志英,周晓敏,宋寅虎. 基于FDA-LSTM的冷轧过程多源异构时序数据处理及颤振预测[J]. 振动与冲击, 2022, 41(22): 202-210
ZHAO Xiaoya,GAO Zhiying,ZHOU Xiaomin,SONG Yinhu . Multi-source heterogeneous time series data processing and chatter prediction based on the method of FDA-LSTM in cold rolling processes[J]. Journal of Vibration and Shock, 2022, 41(22): 202-210

参考文献

[1] 工业和信息化部信息电信研究院. 工信部电信研究院大数据白皮书 [EB/OL]. [2014-05-12].?获取访问路径.
[2] LEI Y G, JIA F, LIN J, et al. An intelligent fault diagnosis method using unsupervised feature learning towards mechanical big data[J]. IEEE Transactions on Industrial Electronics, 2016, 63(5): 3137-3147.
[3] OLALERE I O, OLANREWAJU O A. Optimising production through Intelligent manufacturing[J]. E3S Web of Conferences, 2020, 152(5): 03012.
[4] XU K, LI Y G, LIU C Q, et al. Advanced data collection and analysis in data-driven manufacturing process[J]. Chinese Journal of Mechanical Engineering, 2020, 33(3): 40-60.
[5] RAMSAY J O. When the data are functions[J]. Psychometrika, 1982, 47(4): 379-396.
[6] RAMSAY J O,  DALZELL C J . Some tools for functional data analysis[J]. Journal of the Royal Statistical Society. Series B (Methodological), 1991, 53(3): 539-561.
[7] RAMSAY J O,  WANG X,  FLANAGAN R. A functional data analysis of the pinch force of human fingers[J]. Journal of the Royal Statistical Society. Series C (Applied Statistics), 1995, 44(1): 17-30.
[8] 黎敏,谢玄,陈泽等. 基于函数型数据分析的半导体生产过程监控[J]. 机械工程学报, 2018, 54(16): 62-69.
LI Min, XIE Xuan, CHEN Ze, et al. Monitoring of semiconductor manufacturing process based on functional data analysis[J]. Journal of Mechanical Engineering, 2018, 54(16): 62-69.
[9] 徐钢, 黎敏, 徐金梧, 等. 基于函数型数字孪生模型的转炉炼钢终点碳控制技术[J]. 工程科学学报, 2019, 41(4): 521-527.
XU Gang, LI Min, XU Jinwu, et al. Control technology of end-point carbon in converter steelmaking based on functional digital twin model[J]. Chinese Journal of Engineering, 2019, 41(4): 521-527.
[10] TLUSTY J, CRITCHLEY S, PATON D. Chatter in cold rolling[J]. Annals of the CIRP, 1982, 31(1): 195-199.
[11] YUN I S, WILSON W R D, EHMANN K F. Chatter in the strip rolling process[J]. Journal of Manufacturing Science and Engineering, 1998, 120(5): 330-348.
[12] 郜志英, 白露露, 李强. 薄板冷连轧自激振动的临界轧制速度研究[J]. 机械工程学报, 2017, 53(12): 118-132.
 GAO Zhiying, BAI Lulu, LI Qiang. Research on critical rolling speed of self-excited vibration in the tandem rolling process of thin strip[J]. Journal of Mechanical Engineering, 2017, 53(11): 118-132.
[13] 郜志英, 臧勇, 曾令强. 轧机颤振建模及理论研究进展[J]. 机械工程学报, 2015, 51(16): 87-105.
GAO Zhiying, ZANG Yong, ZENG Lingqiang. Review of modeling and theoretical studies on chatter in the rolling mills[J]. Journal of Mechanical Engineering, 2015, 51(16): 87-105.
[14] 李郅琴, 杜建强, 聂斌, 等. 特征选择方法综述[J]. 计算机工程与应用, 2019, 55(24): 10-19.
 LI Zhiqin, DU Jianqiang, NIE Bin, et al. Summary of feature selection methods[J]. Computer Engineering and Applications, 2019, 55(24): 10-19.
[15] LIU J , HU Y M, WU B ,et al. A hybrid health condition monitoring method in milling operations[J]. International Journal of Advanced Manufacturing Technology, 2017, 92: 2069-2080.
[16] 谢锋云, 江炜文, 陈红年, 等. 基于广义BP神经网络的切削颤振识别研究[J]. 振动与冲击, 2018, 37(5): 65-70.
XIE Fengyun, JIANG Weiwen, CHEN Hongnian,  et al. Cutting chatter recognition based on generalized BP neural network[J]. Journal of Vibration and Shock, 2018, 37(5): 65-70.
[17] KUMAR S, SINGH B. Chatter prediction using merged wavelet denoising and ANFIS[J]. Methodologies and Application, 2019, 23: 4439-4458.
[18] 刘阳, 郜志英, 周晓敏, 等. 工业数据驱动下薄板冷轧颤振的LSTM智能预报[J]. 机械工程学报, 2020, 56(11): 121-131.
LIU Yang, GAO Zhiying, ZHOU Xiaomin, et al. Industrial data-driven intelligent forecast for chatter of cold rolling of thin strip with LSTM recurrent neural network [J]. Journal of Mechanical Engineering,2020, 56(11): 121-131.
[19] CORRALES D C, LASSO E, LEDEZMA A, et al. Feature selection for classification tasks: expert knowledge or traditional methods[J]. Journal of Intelligent & Fuzzy Systems, 2018, 34(5): 2825.
[20] ZHANG Y, SUN C, GAO L, et al. Determination of minor metal elements in steel using laser-induced breakdown spectroscopy combined with machine learning algorithms[J]. Spectrochimica Acta Part B: Atomic Spectroscopy, 2020, 166: 105802.

PDF(4211 KB)

Accesses

Citation

Detail

段落导航
相关文章

/