基于主元分析和BP神经网络对刀具VB值预测

聂鹏; 谌鑫

基于主元分析和BP神经网络对刀具VB值预测

聂鹏,
谌鑫

沈阳航空航天大学机电工程学院, 沈阳 110136

基金项目: 沈阳市人才引进专项基金资助项目(07SYRC04)

详细信息

中图分类号: TP 183
计量
- 文章访问数: 3184
- HTML全文浏览量: 287
- PDF下载量: 816
- 被引次数: 0
出版历程
- 收稿日期: 2010-04-20
- 网络出版日期: 2011-03-31

Prediction of tool VB value based on PCA and BP neural network

Nie Peng,
Chen Xin

School of Mechanical Engineering, Shenyang University of Aeronautics and Aviation, Shenyang 110136, China

摘要

摘要: 对声发射信号进行5层小波分解提取6个频段的能量值,把它与切削速度、切削深度、进给量和切削时间一起作为刀具状态的特征向量.通过主元分析进行降维、消除特征向量间的相关性后,把得到的主元作为BP(Back Propagation)神经网络的输入向量.BP神经网络应用改进的LM(Levenberg-Marquart)算法进行学习,利用输入向量对网络进行训练后,实现对刀具后刀面磨损量VB的预测.实验结果显示:基于主元分析和LM算法改进的BP神经网络建立的预测系统,网络输出与实测VB值的误差0.03以内;根据预测VB值的范围可判别出刀具的不同状态.
- 主元分析 /
- LM算法 /
- BP神经网络 /
- VB值预测
Abstract: Five layers of wavelet decomposition was applied on acoustic emission signals for extracting the acoustic emission(AE) signals energy value of six bands. Energy value and cutting speed, cutting depth, feed rate, cutting time were turned into state feature vectors of tool wear. The principal component analysis was used to reduce dimension and eliminate the correlation between the feature vectors. The principal components were seen as back propagation(BP) neural network input vector. Improved Levenberg-Marquart (LM) algorithm was used to BP neural network for learning, input vectors were trained for BP neural network. Then, the BP neural network would realize the forecast of tool flank wear VB value. The results indicate that the VB value forecast system based on principal component analysis (PCA) and the improved BP neural network with LM algorithm can accurately predict the tool flank wear VB value within the error range 0.03. The different states of tool wear can be judged according to the VB value.
- principal component analysis (PCA) /
- Levenberg-Marquart(LM) algorithm /
- back propagation(BP) neural network /
- forecast VB value

HTML全文

参考文献(1)

[1] 康晶,冯长建,胡红英.刀具磨损监测及破损模式的识别[J].振动、测试与诊断,2009,29(1):5-9 Kang Jing,Feng Changjian,Hu Hongying.Tool wear monitoring and pattern recognition of tool failure[J].Journal of Vibration,Measurement & Diagnosis,2009,29(1):5-9(in Chinese) [2] Tamura M,Tsujita S.A study on the number of principal components and sensitivity of fault detection using PCA[J].Computers and Chemical Engineering,2007,31(9):1035-1046 [3] Balazinski M,Czogala E,Jemielniak K,et al.Tool condition monitoring using artificial intelligence methods[J].Engineering Applications of Artificial Intelligence ,2002,15:73-80 [4] 郑金兴,张铭钧,孟庆鑫.多传感器数据融合技术在刀具状态监测中的应用[J].传感器与微系统,2007,26(4):90-93 Zheng Jinxing,Zhang Mingjun,Meng Qingxin.Application of multi-sensor data fusion in tool wear monitoring[J].Transducer and Microsystem Technologies,2007,26(4):90-93(in Chinese) [5] Li R Y,Rong G.Fault isolation by partial dynamic principal component analysis in dynamic process[J].Chinese Journal of Chemical Engineering,2006,14(4):486-493 [6] 朱松青,史金飞.状态监测与故障诊断中的主元分析法[J].机床与液压,2007,35(1):241-243 Zhu Songqing,Shi Jinfei.PCA approach to condition monitoring and fault diagnosis[J].Machine Tool & Hydraulics,2007,35(1):241-243(in Chinese) [7] Ghosh N,Ravi Y B,Patra A,et al.Estimation of tool wear during CNC milling using neural network-based sensor fusion [J].Mechanical Systems and Signal Processing,2007,21(1):466-479 [8] 张德丰.MATLAB神经网络仿真与应用[M].北京:电子工业出版社,2009:168-174 Zhang Defeng.MATLAB neural network simulator and application [M].Beijing:Electronics Industry Press,2009:168-174(in Chinese)

施引文献

资源附件(0)

访问统计