基于支持向量机与粒子滤波的刀具磨损状态识别

程灿1,李建勇1,2,徐文胜1,聂蒙1,2

振动与冲击 ›› 2018, Vol. 37 ›› Issue (17) : 48-55.

PDF(1685 KB)
PDF(1685 KB)
振动与冲击 ›› 2018, Vol. 37 ›› Issue (17) : 48-55.
论文

基于支持向量机与粒子滤波的刀具磨损状态识别

  • 程灿1,李建勇1,2,徐文胜1,聂蒙1,2
作者信息 +

Tools’wear state recognition based on support vector machine and particle filtering#br#

  •   CHENG Can 1   LI Jianyong 1,2  XU Wensheng 1,2  NIE Meng 1,2
Author information +
文章历史 +

摘要

为了提高小样本情况下刀具磨损量识别的精度,提出一种基于支持向量机和粒子滤波的刀具磨损量识别方法。针对支持向量机的输入特征选择和参数选择难题,建立支持向量机输入特征与参数优化双层规划模型,并组合遗传算法和人工蜂群算法进行求解。之后,利用粒子滤波方法对支持向量机回归得到的结果进行修正。实验结果表明,在小样本情况下,基于支持向量机和粒子滤波的刀具磨损量识别方法具备良好的学习能力,能够精确地识别刀具的磨损量。

Abstract

To improve the accuracy of tools’wear recognition under the case of small samples,a tools’wear recognition method based on support vector machine (SVM) and particle filtering was proposed. Aiming at difficult problems of SVM’s feature selecting and parametric selecting,a bi-level programming model for SVM’s input features and parametric optimization was developed and solved using the genetic algorithm and the artificial bee colony algorithm. Then,the particle filtering method was used to modify tools’wear recognition results obtained using the regression algorithm of SVM. Test results showed that under the case of small samples,the tools’wear recognition method based on SVM and particle filtering has a good learning capability and can recognize tools’wear precisely.

关键词

刀具磨损 / 支持向量机 / 双层规划 / 遗传算法 / 人工蜂群 / 粒子滤波

Key words

 tools&rsquo / wear / support vector machine (SVM) / bi-level programming / genetic algorithm / artificial bee colony algorithm / particle filtering

引用本文

导出引用
程灿1,李建勇1,2,徐文胜1,聂蒙1,2. 基于支持向量机与粒子滤波的刀具磨损状态识别[J]. 振动与冲击, 2018, 37(17): 48-55
CHENG Can 1 LI Jianyong 1,2 XU Wensheng 1,2 NIE Meng 1,2. Tools’wear state recognition based on support vector machine and particle filtering#br#[J]. Journal of Vibration and Shock, 2018, 37(17): 48-55

参考文献

[1]  Yeo SH, Khoo LP, Neo SS. Tool condition monitoring using reflectance of chip surface and neural network[J]. Journal of Intelligent Manufacturing, 2000, 11(6): 507-514.
[2]  Kurada S, Bradley C. A review of machine vision sensors for tool condition monitoring[J]. Computers in Industry, 1997, 34(1): 55-72.
[3] 李宏坤, 汪寅虎, 杨树华, 等. 基于声发射信号的铣刀运行可靠性评估[J]. 大连理工大学学报, 2014, (4): 418-423.
LI Hongkun, WANG Yinhu, YANG Shuhua, et al. Tool reliability evaluation based acoustic emission [J]. Journal of Dalin University of Technology, 2014, (4): 418-423.
[4] 张世昌, 李旦, 张冠伟. 机械制造技术基础[M]. 3版. 北京: 高等教育出版社, 2014.
Zhang Shichang, LI Dan, ZHANG Guan Wei. Fundamentals of mechanical manufacturing technology[M]. 3th edition. Beijing: Higher Education Press,2014.
[5] Vapnik, Vladimir N. The nature of statistical learning theory[M]. New York:Springer, 1995.
[6] Vapnik V, Golowich S E, Smola A. Support vector method for function approximation, regression estimation, and signal processing[J]. Advances in neural information processing systems, 1997: 281-287.
[7] Salgado D R, Alonso F J. An approach based on current and sound signals for in-process tool wear monitoring[J]. International Journal of Machine Tools & Manufacture, 2007, 47(14): 2140-2152.
[8] Benkedjouh T, Medjaher K, Zerhouni N, et al. Health assessment and life prediction of cutting tools based on support vector regression[J]. Journal of Intelligent Manufacturing, 2015, 26(2): 213-223.
[9] 张栋梁, 莫蓉, 孙惠斌,等. 基于混沌时序分析方法与支持向量机的刀具磨损状态识别[J]. 计算机集成制造系统, 2015, 21(8): 2138-2146.
ZHANG Dongliang, MO Rong, SUN Huibin, et al. Tool wear state recognition based on chaotic time series analysis and support vector machine[J]. Computer Integrated Manufacturing Systems, 2015, 21(8): 2138-2146.
[10] 袁敏, 王玫, 潘玉霞,等. 基于改进果蝇优化算法的铣削力信号特征选择方法[J]. 振动与冲击, 2016, 35(24):196-200.
 YUAN Min, WANG Mei, PAN Yuxia, et al. A feature selection method for the milling force signal based on the improved Fruit Fly Optimization Algorithm[J]. JOURNAL OF VIBRATION AND SHOCK, 2016, 35(24):196-200.
[11] 于明, 艾月乔. 基于人工蜂群算法的支持向量机参数优化及应用[J]. 光电子•激光, 2012, (2):374-378.
YU Ming, AI Yueqiao. SVM parameter optimization and application based on artificial bee colony algorithm[J]. Journal of Optoelectronics•Lase, 2012, (2):374-378.
[12] 刘路, 王太勇. 基于人工蜂群算法的支持向量机优化[J]. 天津大学学报, 2011, 44(9): 803-809.
LIU Lu, WANG Taiyong. Support vector machine optimization based on artificial bee colony algorithm[J]. Journal of Tianjin University, 2011, 44(9): 803-809(in Chinese).
[13] Peel L. Data driven prognostics using a Kalman filter ensemble of neural network models[C]//Prognostics and Health Management, 2008. PHM 2008. International Conference on. IEEE, 2008: 1-6.
[14] 李威霖, 傅攀, 曹伟青. 卡尔曼滤波修正LS-SVM的刀具磨损识别技术研究[J]. 机械科学与技术, 2015, 34(1): 81-85.
LI Weilin, FU Pan, CAO Weiqing. Study on the technology of tool wear monitoring by modifying least square support vector machine via kalman filter[J]. Mechanical Science and Technology for Aerospace Engineering, 2015, 34(1): 81-85.
[15] Li X, Lim B S, Zhou J H, et al. Fuzzy neural network modelling for tool wear estimation in dry milling operation[C]//Annual conference of the prognostics and health management society. 2009: 1-11.
[16] PHM Society. (2010). PHM data chalelnge 2010. https://www.phmsociety.org/competition/phm/10.
[17] Karaboga D. An idea based on honey bee swarm for numerical optimization[R]. Technical report-tr06, Erciyes university, engineering faculty, computer engineering department, 2005.
[18] Karaboga D, Basturk B. A powerful and efficient algorithm for numerical function optimization: artificial bee colony (ABC) algorithm[J]. Journal of Global Optimization, 2007, 39(3): 459-471.
[19] Gordon N J, Salmond D J, Smith A F M. Novel approach to nonlinear/non-Gaussian Bayesian state estimation[C]//IEE Proceedings F-Radar and Signal Processing. IET, 1993, 140(2): 107-113.

PDF(1685 KB)

Accesses

Citation

Detail

段落导航
相关文章

/