|
|
|
| Wear Condition Recognition of Lathe Tool Based on Singular Value Decomposition and Grey Target Decision Methods |
| ZHU Jian-min,ZHAO Quan-long,HE Dan-dan |
| University of Shanghai for Science and Technology, Shanghai 200093, China |
|
|
|
|
Abstract In allusion to the problems that random noise interferes the time domain vibration signal extraction, and limited lathe tool wear condition recognition accuracy. This study proposed a time domain characteristics extraction method of tool wear signals which firstly extracts the time domain characteristics of the lathe tool vibration signal with wavelet packet transform and correlation coefficient methods, then denoises the time domain characteristics with singular value decomposition(SVD) method. The most relevant wear characteristics of lathe tool weariness are selected as reference characteristic sequence to calculate the similarity association degrees with other wear characteristic sequences. Then the weight of each time domain wear characteristics are gain through normalization process of similarity association degrees, and the comprehensive measurement of time domain characteristic of each wear signal are calculated with grey target decision method in order to determine the tool wear condition of the lathe tool. Experiment results indicate that the proposed method can filter the random noise effectively.
|
|
Received: 20 July 2016
Published: 28 February 2017
|
|
|
|
|
|
［1］李鹏阳,郝重阳,祝双武,等.基于脉冲耦合神经网络的刀具磨损检测［J］. 中国机械工程,2008,19(5):547-550.
［2］Niranjan P K,Ramamoorthy B. Tool wear evaluation by stereo vision and prediction by artificial neural network［J］ . Journal of Materials Proeessing Technology, 2001, 112(1): 43-52.
［3］李鹏阳,郝重阳,祝双武.基于图像连通区域数的刀具磨损状态特征提取实验研究［J］. 中国图像图形学报,2008,23(8):1476-1480.
［4］李国宾,关德林,李廷举.基于小波包变换和奇异值分解的柴油机振动信号特征提取研究［J］. 振动与冲击,2011,30(8):149-152.
［5］关山,彭昶.金属切削过程刀具磨损信号的混沌特征［J］. 振动与冲击,2015,34(10):28-33.
［6］孙勇,景博,覃征,等.基于小波分析的信噪分离方法研究［J］. 计量学报,2006, 27(2):153-155.
［7］朱坚民,战汉,张统超,等.基于切削声发射信号测量的刀具磨损状态判别［J］. 计量学报,2015, 36(3):268-272.
［8］张永祥,王孝霖,张帅,等.基于奇异值分解和相关峭度的滚动轴承故障诊断方法研究［J］. 振动与冲击,2014,33(11):167-171.
［9］孟宗,谷伟明,胡猛,等.基于改进奇异值分解和经验模式分解的滚动轴承早期微弱故障特征提取［J］. 计量学报,2016, 37(4):406-410.
［10］吕俊杰,王杰,王玫,等.基于SOM和HMM结合的刀具磨损状态监测研究［J］. 中国机械工程,2010, 21(13):1531-1535.
［11］Wang G F, Yang Y W, Zhang Y C. Vibration Sensor Based Tool Condition Monitoring Using v Support Vector Machine and Locality Preserving Projection ［J］. Sensors and Actuators A:Physical,2014, 209: 24-32. |
|
|
|
2017, Vol. 38 
