Cutting chatter recognition based on generalized BP neural network

PDF(990 KB)

Journal of Vibration and Shock ›› 2018, Vol. 37 ›› Issue (5) : 65-70.

XIE Feng-yun JIANG Wei-wen CHEN Hong-nian XIE San-mao LI Xue-meng LIU Bo-wen

Author information +

History +

Abstract

Cutting chatter reduces quality and efficiency of machining, and it is an important study topic in cutting processing field. There are problems of measurement uncertainty and recognition model uncertainty in the traditional cutting chatter recognition method. Here, a generalized BP neural network cutting chatter recognition model based on the generalized interval theory was proposed. The quantities with measurement uncertainty were converted into generalized intervals with the generalized interval uncertainty analysis method, and a time-frequency feature extraction in generalized interval form was performed. Finally, the features in generalized interval form were substituted into the generalized BP neural network recognition model, the cutting states were indentified. The test results showed that the proposed generalized BP neural network recognition model has a higher recognition rate than the traditional BP neural network recognition model does.

Key words

generalized interval / neural network / chatter / recognition

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

XIE Feng-yun JIANG Wei-wen CHEN Hong-nian XIE San-mao LI Xue-meng LIU Bo-wen. Cutting chatter recognition based on generalized BP neural network[J]. Journal of Vibration and Shock, 2018, 37(5): 65-70

References

[1] 卢晓红, 王凤晨, 王华, 王鑫鑫, 司立坤 . 铣削过程颤振稳定性分析的研究进展[J]. 振动与冲击, 2016, 35(1): 74-82.
LU Xiao-hong, WANG Feng-chen, WANG Hua, WANG Xin-xin, SI Li-kun. Research Review of Chatter Stability Analysis in Milling Process[J]. Journal of vibration and shock, 2016, 35(1): 74-82.
[2]Tangjitsitcharoen S, Toshimichi M. Intelligent monitoring and identification of cutting states of chips and chatter on CNC turning machine [J]. Journal of Manufacturing Processes, 2008, 10:40-46.
[3] 张小龙, 张氢, 秦仙蓉,孙远韬. 基于ITD复杂度和PSO-SVM的滚动轴承故障诊断[J].振动与冲击,2016,35(24): 102-107.
Zhang Xiao-long, Zhang Qing, Qin Xian-rong, Sun Yuan-tao . Rolling bearing fault diagnosis based on ITD Lempel-Ziv complexity and PSO-SVM [J]. Journal of vibration and shock, 2016, 35(24): 102-107.
[4]吴石, 林连冬, 肖飞等. 基于多类超球支持向量机的铣削颤振预测方法[J].仪器仪表学报, 2012,33(11):2414-2421.
Wu Shi Lin Liandong,Xiao Fei , et al. Milling chatter rediction method based on multicalss hypersphere suppport vector machine [J]. Chinese journal of scientific instrument. 2012,33(11):2414-2421.
[5] E. Kuljanic, G. Totis, M. Sortino. Development of an intelligent multisensor chatter detection system in milling[J]. Mechanical Systems and Signal Processing, 2009, 23: 1704-1718.
[6] Zhang C L,Yue X, Jiang Y T, Zheng W. A hybrid approach of ANN and HMM for cutting chatter monitoring [J]. Advanced Materials Research,2010, 97:3225-3232.
[7] XIE Fengyun, HU Youmin, Wang Yan, Wu Bo. A generalized Markov chain model based on generalized interval probability[J]. Science China Technological Sciences. 2013, 56(9),
[8] Hu Youmin, XIE Fengyun, Wu Bo, et al. An uncertainty quantification method based on generalized interval, 2013 12th Mexican International Conference on Artificial Intelligence. Mexican, DOI 10.1109/MICAI.2013.25: 145-150
[9] Sainz M A, Armengol J,Calm R. Modal interval analysis: new tools for numerical information [M], Springer, 2014.
[10] 孙惠斌;牛伟龙;王俊阳. 基于希尔伯特黄变换的刀具磨损特征提取[J].振动与冲击, 2015, 34(4): 158-164.
Sun Hui-bin;Niu Wei-long; WANG Jun-yang. Tool Wear Feature Extraction Based on Hilbert-Huang Transform [J]. Journal of vibration and shock , 2015, 34(4): 158-164.
[11] Yao Z H, Mei D Q, Chen Z C. On-line chatter detection and I dentification based on wavelet and support vector machine [J]. Journal of Materials Processing Technology, 2010, 210: 713-719.
[12] 贾广飞，吴波，胡友民. 基于Hilbert-Huang变换的切削颤振识别[J]. 振动与冲击, 2014,33(22):188-192.
JIA Guang-fei, WU Bo, HU You-min. Cutting chatter recognition based on Hilbert-Huang transform [J]. Journal of vibration and shock, 2014,33(22):188-192.