Tool wear condition monitoring based on principal component analysis and C-support vector machine

被引：0
|
作者：
Xie N. [1 ]
Ma F. [2 ]
Duan M. [2 ]
Li A. [2 ]
机构：
[1] Sino-German College of Applied Science, Tongji University, Shanghai
[2] College of Mechanical Engineering, Tongji University, Shanghai
来源：
Tongji Daxue Xuebao/Journal of Tongji University | 2016年 / 44卷 / 03期
关键词：
C-support vector machine; Monitoring; Principal component analysis; Tool wear;
D O I：
10.11908/j.issn.0253-374x.2016.03.015
中图分类号：
学科分类号：
摘要：
In order to monitor tool wear condition (TWC), the power-sensor-based monitoring system on the state of machining tool wear was designed. The monitoring model of TWC was proposed based on principal component analysis (PCA) and C-support vector machine (C-SVM). Current and power signals were obtained from power sensor during cutting process. After that, the features of these signals were extracted using PCA. The principal components, mainly affecting TWC, were chosen as the input samples of C-SVM to carry out monitoring the tool condition with accuracy. The results of computerized numerical control (CNC) turning machine tool show that the model is effective even in the case of a small samples. Moreover, a comparison about the monitoring and prognostics capability between the presented method and back propagation (BP) neural network has been made. © 2016, Science Press. All right reserved.
引用
收藏
页码：434 / 439
页数：5
相关论文
共 17 条
  • [1] Zhu H., Mei W., Analysis and research of tool wear identification methods, Equipment Manufacturing Technology, 2, (2012)
  • [2] Chen J., Wang W., Mao L., State recognition of tool wear based on differential evolution wavelet neural networks, Machinery Design & Manufacture, 7, (2012)
  • [3] Zhang K., Yuan H., Nie P., Tool wear condition monitoring based on generalized fractal dimensions, Journal of Vibration and Shock, 1, 33, (2014)
  • [4] Guan J., Li G., Chen Z., Current signal based failure analysis on lathe tool fault, Journal of Ning Bo University: Natural Science and Engineering Edition, 26, 1, (2013)
  • [5] Bhattacharyya P., Sengupta D., Mukhopadhyay S., Et al., Online tool condition monitoring in face milling using current and power signals, International Journal of Production Research, 46, 4, (2008)
  • [6] Qiu Y., Xie F., Tool wear monitoring based on wavelet packet coefficient and hidden Markov model, Hydromechatronics Engineering, 42, 12, (2014)
  • [7] Guan S., Study on identification method of tool wear based on singular value decomposition and least squares support vector machine, Journal of Northeast Dianli University, 33, 3, (2013)
  • [8] Elangovan M., Devasenapati S.B., Sakthivel N.R., Et al., Evaluation of expert system for condition monitoring of a single point cutting tool using principle component analysis and decision tree algorithm, Expert Systems with Application, 38, (2011)
  • [9] Malhi A., Gao R.X., PCA-Based feature selection scheme for machine defect classification, IEEE Transactions on Instrumentation and Measurement, 53, 6, (2004)
  • [10] Guan S., Nie P., The review and perspective of the research of on-line and indirect metal cutting tool condition monitoring III: pattern recognition methods, Machine Tool & Hydraulics, 40, 3, (2012)
12