Chinese Journal of Mechanical Engineering >

2019 , Vol. 32 >Issue 1: 1 - 1

DOI: https://doi.org/10.1186/s10033-018-0313-7

Intelligent Manufacturing Technology

Grinding Chatter Detection and Identifcation Based on BEMD and LSSVM

  • Huan-Guo Chen ,
  • Jian-Yang Shen ,
  • Wen-Hua Chen ,
  • Chun-Shao Huang ,
  • Yong-Yu Yi ,
  • Jia-Cheng Qian
展开
  • 1. Zhejiang Provinceos Key Laboratory of Reliability Technology for Mechanical and Electrical Product, Hangzhou 310018, China;
    2. Zhejiang Jiali Technology Co., Ltd., Hangzhou 311241, China;
    3. Hangzhou Hangji Machine Tool Co., Ltd., Hangzhou 310018, China

收稿日期: 2017-01-16

  网络出版日期: 2019-07-19

基金资助

Supported by National Natural Science Foundation of China (Grant Nos. 51675361, 51135007), Shanxi Scholarship Council of China (Grant Nos. 2015-086, 2016-096), and Shanxi Provincial Key Research and Development Program of China (Grant No. 03012015004)

收起

Grinding Chatter Detection and Identifcation Based on BEMD and LSSVM

  • Huan-Guo Chen ,
  • Jian-Yang Shen ,
  • Wen-Hua Chen ,
  • Chun-Shao Huang ,
  • Yong-Yu Yi ,
  • Jia-Cheng Qian
Expand
  • 1. Zhejiang Provinceos Key Laboratory of Reliability Technology for Mechanical and Electrical Product, Hangzhou 310018, China;
    2. Zhejiang Jiali Technology Co., Ltd., Hangzhou 311241, China;
    3. Hangzhou Hangji Machine Tool Co., Ltd., Hangzhou 310018, China

Received date: 2017-01-16

  Online published: 2019-07-19

Supported by

Supported by National Natural Science Foundation of China (Grant Nos. 51675361, 51135007), Shanxi Scholarship Council of China (Grant Nos. 2015-086, 2016-096), and Shanxi Provincial Key Research and Development Program of China (Grant No. 03012015004)

Fold

摘要

Grinding chatter is a self-induced vibration which is unfavorable to precision machining processes. This paper proposes a forecasting method for grinding state identification based on bivarition empirical mode decomposition (BEMD) and least squares support vector machine (LSSVM), which allows the monitoring of grinding chatter over time. BEMD is a promising technique in signal processing research which involves the decomposition of two-dimensional signals into a series of bivarition intrinsic mode functions (BIMFs). BEMD and the extraction criterion of its true BIMFs are investigated by processing a complex-value simulation chatter signal. Then the feature vectors which are employed as an amplification for the chatter premonition are discussed. Furthermore, the methodology is tested and validated by experimental data collected from a CNC guideway grinder KD4020X16 in Hangzhou Hangji Machine Tool Co., Ltd. The results illustrate that the BEMD is a superior method in terms of processing non-stationary and nonlinear signals. Meanwhile, the peak to peak, real-time standard deviation and instantaneous energy are proven to be effective feature vectors which reflect the different grinding states. Finally, a LSSVM model is established for grinding status classification based on feature vectors, giving a prediction accuracy rate of 96%.

关键词： Grinding chatter; BEMD and LSSVM; Complex-value chatter signal; Feature vector; Grinding status classifcation

本文引用格式

Huan-Guo Chen , Jian-Yang Shen , Wen-Hua Chen , Chun-Shao Huang , Yong-Yu Yi , Jia-Cheng Qian . Grinding Chatter Detection and Identifcation Based on BEMD and LSSVM[J]. Chinese Journal of Mechanical Engineering, 2019 , 32(1) : 1 -1 . DOI: 10.1186/s10033-018-0313-7

Abstract

Grinding chatter is a self-induced vibration which is unfavorable to precision machining processes. This paper proposes a forecasting method for grinding state identification based on bivarition empirical mode decomposition (BEMD) and least squares support vector machine (LSSVM), which allows the monitoring of grinding chatter over time. BEMD is a promising technique in signal processing research which involves the decomposition of two-dimensional signals into a series of bivarition intrinsic mode functions (BIMFs). BEMD and the extraction criterion of its true BIMFs are investigated by processing a complex-value simulation chatter signal. Then the feature vectors which are employed as an amplification for the chatter premonition are discussed. Furthermore, the methodology is tested and validated by experimental data collected from a CNC guideway grinder KD4020X16 in Hangzhou Hangji Machine Tool Co., Ltd. The results illustrate that the BEMD is a superior method in terms of processing non-stationary and nonlinear signals. Meanwhile, the peak to peak, real-time standard deviation and instantaneous energy are proven to be effective feature vectors which reflect the different grinding states. Finally, a LSSVM model is established for grinding status classification based on feature vectors, giving a prediction accuracy rate of 96%.

Key words： Grinding chatter; BEMD and LSSVM; Complex-value chatter signal; Feature vector; Grinding status classifcation

参考文献

[1] M Ahrens, R Fischer, M Dagen, et al. Abrasion monitoring and automatic chatter detection in cylindrical plunge grinding. Procedia CIRP, 2013(8): 374-378.
[2] L G Wang, X J Liu, Q F Jia. Studies and developments about grinding chatter of machine tools. Tianjin: Machine Tool & Hydraulics, 2004.
[3] Wenfeng Ding, Barbara Linke, Yejun Zhu, et al. Review on monolayer CBN superabrasive wheels for grinding metallic materials. Chinese Journal of Aeronautics, 2017, 30(1): 109-134.
[4] Wenzhong Li, Yujing Hu. Simulation analysis of ultrasonic vibration grinding of hard alloy. Journal of Qingdao University (Natural Science Edition), 2015, 28 (4): 66-71. (in Chinese)
[5] N H M Rozalli, N L Chin, Y A Yusof. Grinding characteristics of Asian originated peanuts (Arachishypogaea L.) and specific energy consumption during ultra-high speed grinding for natural peanut butter production. Journal of Food Engineering, 2015, 152(2): 1-7.
[6] X C Liu, F Chen, M S Fen, et al. Research of GCr15 bearing steel's surface roughness and grinding burn in ultra-high speed grinding. Modular Machine Tool & Automatic Manufacturing Technique, 2016(9): 32-34. (in Chinese)
[7] H G Chen, J Y Shen, W H Chen, et al. The bivariate empirical mode decomposition and its contribution to grinding chatter detection. Applied Sciences, 2017, 7(2): 145-163.
[8] Yao Liu, Xiufeng Wang, Jing Lin, et al. Early chatter detection in gear grinding process using servo feed motor current. The International Journal of Advanced Manufacturing Technology, 2016, 83(12): 1801-1810.
[9] Z L Yao, M Wang, T Zan, et al. Prediction method of grinding chatter based on ARIMA. Advanced Materials Research, 2014, 971-973 (9): 1288-1291.
[10] A Messaoud, C Weihs. Monitoring a deep hole drilling process by nonlinear time series modeling. Journal of Sound and Vibration, 2009, 321(3-5): 620-630.
[11] E Kondo, H Ota, T Kawai. A new method to detect regenerative chatter using spectral analysis. Part 1. Basic study on criteria for detection of chatter. Journal of Manufacturing Science & Engineering, 1997, 119(4A): 461-466.
[12] M C Yoon, D H Chin. Time series modeling and spectrum analysis for chatter mode in endmilling dynamics. The International Journal of Advanced Manufacturing Technology, 2006, 29(11): 1125-1133.
[13] I N Tansel, X Wang, P Chen, et al. Transformation in machining, Part 2. Evaluation of machining quality and Trans detection of chatter in turning by using s-transformation. International Journal of Machine Tools & Manufacture, 2014, 46(a): 43-50.
[14] Zhehe Yao, Deqing Mei, Zichen Chen. On-line chatter detection and detection based on wavelet and support vector machine. Journal of Materials Processing Technology, 2010, 210(5): 713-719.
[15] J Gradisek, E Govekar, I Grabec. Using coarse-grained entropy rate to detect chatter in turning. Journal of Sound and Vibration, 1998, 214(5): 941-952.
[16] Gabriel Rilling, Partick Flandrin. Bivariate empirical mode decomposition. IEEE Signal Processing Letters, 2007, 14(12): 936-939.
[17] Wenxian Yang, Richard Court, Peter J Tavner. Bivariate empirical mode decomposition and its contribution to wind turbine condition monitoring. Journal of Sound and Vibration, 2011, 330(15): 3766-3782.
[18] Long Li, Jing Wei, Canbing Li. Prediction of load model based on artificial neural network. Transactions of China Electrotechnical Society, 2015, 30(8): 225-230. (in Chinese)
[19] Yuan Ren, Guangchen Bai. New neural network response surface methods for reliability analysis. Chinese Journal of Aeronautics, 2011, 24(1): 25-31.
[20] X Q Li, Y S Wong, A Y C Nee. A comprehensive identification of tool failure and chatter using a parallel multi-ART2 neural network. Journal of Manufacturing Science and Engineering, 1998, 120(2): 433-442.
[21] I Bediaga, J Muñoa, J Hernández, et al. An automatic spindle speed selection strategy to obtain stability in high-speed milling. International Journal of Machine Tools and Manufacture, 2009, 49(5): 384-394.
[22] Y T Jiang, C L Zhang. Hybrid HMM/SVM method for predicting of cutting chatter. Proceedings of the SPIE-The International Society for Optical Engineering, 2006, 6280: 404-411.
[23] Qing Wang, Weiqi Qian, Kaifeng He. Unsteady aerodynamic modeling at high angles of attack using support vector machines. Chinese Journal of Aeronautics, 2015, 28(3): 659-668.
[24] Jianyang Shen. An online BEMD and LSSVM-based grinding chatter detection method for large grinding machine. Zhejiang: Zhejiang Sci-Tech University, 2017. (in Chinese)
[25] C W Hsu, C J Lin. A comparison of methods formulticlass support vector support vector machines. IEEE Transactions on Neural Networks, 2002, 13(2): 415-425.
[26] N E Huang, Z Shen, S R Long, et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. Proceedings Mathematical Physical & Engineering Sciences, 1998, 454(1971): 903-995.zbMATHGoogle Scholar
[27] Changfu Liu, Lida Zhu, Chenbing Ni. The chatter identification in end milling based on combining EMD and WPD. The International Journal of Advanced Manufacturing Technology, 2017, 91(9-12): 3339-3348.
[28] H G Chen, Y J Yan, W H Chen, et al. Early damage detection in composite wingbox structures using Hilbert-Huang Transform and Genetic Algorithm. International Journal of Structural Health Monitoring, 2007, 6(4): 281-297.
[29] Z H Zhu, Y L Sun, J I Yu. Short-term load forecasting research based on EMD and SVM. High Voltage Engineering, 2007, 33(5): 118-122.
[30] S J Rong, L Pan, X X Huang, et al. The influence of training step on price forecasting based on least squares support vector machine. Applied Mechanics & Materials, 2014, 530-531: 621-624.
[31] Xin Ma. Power transformer fault diagnosis based on least squares support vector machine and particle swarm optimization. Applied Mechanics & Materials, 2011, 50-51: 624-628.
[32] Q Wu. Monthly run off forecasting research based on wavelet transform and LSSVM. Xinjiang: Xinjiang University, 2015. (in Chinese)
[33] Zhang Fei, Xinfeng Ge, Luoping Pan, et al. Shaft run-outs' peak to peak value calculation method for a hydraulic power unit under stable conditions. Journal of Vibration and Shock, 2015, 34(21): 170-174.
[34] Bai Yu, Huang Zhigang, Li Rui. Analyze of algorithm based on estimating navigation satellite measurement noise. Annual Conference on Ship Communication and Navigation, 2008, 12(4): 11-16. (in Chinese)
[35] Yafu Yao, Zhang Xing. Fault diagnosis approach for roller bearing based on EMD momentary energy entropy and SVM. Journal of Electronic Measurement and Instrumentation, 2013, 27(10): 957-962.
[36] Xuelong Li, Zhonghui Li, Enyuan Wang, et al. Analysis of natural mineral earthquake and blast based on Hilbert-Huang transform (HHT). Journal of Applied Geophysics, 2016, 128: 79-86.
[37] Wang Ming, Fen Meng, Yao Ziliang, et al. Prediction of grinding chatter based on the ARIMA. Journal of Beijing University of Technology, 2016, 42: 609-613.
[38] Yingxia Luo, Ma Jun, Qingsong Zhu. A method for phase difference measurement with correlation function based on Matlab. Sci/Tech Information Development & Economy, 2003, 13(7): 1-2.
[39] Hanguang Han, Congzhong Cai. Comparison study of normalization of feature vector. Engineer and Application, 2009, 45(22): 117-119.
[40] Rui LIN. An improved fast algorithm for the fractional Fourier transform based on the method of the dimensional normalization. Journal of Jiangxi Normal University (Natural Sciences Edition), 2016, 40 (01): 71-76. (in Chinese)zbMATHGoogle Scholar
[41] Wang Nan, Jinsong Du. Application of wavelet de-noising in unsteady vibration signal processing. Chinese Journal of Scientific Instrument, 2001.
[42] J H CAI, J Li. Suppression of power line interference on MT signals based on the frequency domain wavelet method. Geology and Exploration, 2015, 51(02): 353-359.
Options
文章导航

/

〈 〉

版权所有 © 《Chinese Journal of Mechanical Engineering》编辑部

技术支持：北京玛格泰克科技发展有限公司