基于小波包分析和Elman网络的切削表面粗糙度预测方法

中国机械工程 ›› 2010, Vol. 21 ›› Issue (7): 822-826.

基于小波包分析和Elman网络的切削表面粗糙度预测方法

迟军;陈廉清;杨超珍

宁波工程学院,宁波,315016

出版日期:2010-04-10 发布日期:2010-04-16
基金资助:
宁波市自然科学基金资助项目(2006A610035)
Natural Science Foundation of Ningbo（No. 2006A610035）

Reasearch on Prediction of Cutting Surface Roughness Based on Wavelet Packet Analysis and Elman Network

Chi Jun;Chen Lianqing;Yang Chaozhen

Ningbo University of Technology,Ningbo, 315016

Online:2010-04-10 Published:2010-04-16
Supported by:
Natural Science Foundation of Ningbo（No. 2006A610035）

摘要/Abstract

摘要：

提出了一种基于松散型小波网络的切削表面粗糙度预测方法。结合切削参数和切削振动理论,建立了预测网络结构,为避免频域混叠,采用小波包改进算法来实现振动信号去噪。根据振动加速度及切削参数,利用Elman网络的非线性映射和学习机制,实现切削表面粗糙度的实时在线预测。为减少训练时间,用遗传算法对网络权重进行预先优化。实验表明,该方法的预测误差小于3%。



关键词:

遗传算法, 切削振动, 小波网络, 表面粗糙度

Abstract:

A forecast method based on relax-type wavelet network for cutting surface toughness was indicated. The forecasting network structure was established by considering the influence of cutting parameters and vibration. The noise in cutting vibration signals was filtered with the reformed wavelet pack algorithm to avoid aliasing in frequency domain. The real-time forecast was achieved by the nonlinear mapping and learning mechanism in Elman network according to the vibration acceleration and cutting parameters. The weights in network were optimized with genetic algorithm in advance to reduce learning time. The forecasting error of this method is less than 3% in experiments.

Key words: genetic algorithm, cutting vibration, wavelet network, surface roughness

中图分类号:

TP183

迟军, 陈廉清, 杨超珍.

基于小波包分析和Elman网络的切削表面粗糙度预测方法

[J]. 中国机械工程, 2010, 21(7): 822-826.

CHI Jun, CHEN Lian-Qing, YANG Chao-Zhen.

Reasearch on Prediction of Cutting Surface Roughness Based on Wavelet Packet Analysis and Elman Network

[J]. China Mechanical Engineering, 2010, 21(7): 822-826.

参考文献

[1]王洪祥,董申.通过切削参数的优选控制振动对超精密加工表面质量影响[J].中国机械工程,2000,11(4):452-455.
[2]林岗[1],毛伟[1],马莉[2],徐向明[3].基于振动传感器的车削加工表面粗糙度预测[J].组合机床与自动化加工技术,2007(9):51-53.
[3]Lin S Y, Cheng S H. Construction of a Surface Roughness Prediction Model for High Speed Machining[J]. Mechanical Science and Technology, 2007, 10(21) : 1622-1629.
[4]Othman M O, Elkholy A H. Surface Roughness Measurement Using Dry Friction Noise[J] . Experimental Mechanics,1990,30(9) :309-311.
[5]唐英,陈克兴.基于神经网络的表面粗糙度智能预测系统[J].机床与液压,1996(4):37-38.
[6]Singh D, Rao P V. A Surface Roughness Prediction Model for Hard Turning Process [J]. Advanced Manufacturing Technology, 2007,32 ( 11 / 12 ) : 1115 - 1124.
[7]Salgado D R, Alonso F J. Inprocess Surface Roughness Prediction System Using Cutting Vibrations in Turning[J]. Advanced Manufacturing Technology, 2009,7 (43) : 40-51.
[8]李加种编著.金属切削动力学[M],1993:287.
[9]赵惠英[1],蒋庄德[1],田世杰[1].纳米级超精密切削表面粗糙度若干影响因素分析[J].机械工程学报,2004,40(4):190-194.
[10]Chern G L, Lee H J. Using Workpiece Vibration Cutting for Micro--drilling[J]. Advanced Manufacturing Technology, 2006,27 (1) : 688-692.
[11]Ekici S,Yildirim S,Poyraz M. Energy and Entropy --based Feature Extraction for Locating Fault on Transmission Lines by Using Neural Network and Wavelet Packet Decomposition[J]. Science Direct, 2008,34:2937-2944.
[12]张臣[1],周儒荣[1],庄海军[1],周来水[1].基于BP神经网络的球头铣刀铣削力建模与仿真[J].中国机械工程,2005,16(20):1791-1794.
[13]Zhang J Z,Chen J C. The Development of an Innprocess Surface Roughness Adaptive Control System in Turning Operations[J]. Intellectual Manufacturing, 2007,18(6): 301-311.
[14]Pal S K, Chakraborty D. Surface Roughness Prediction in Turning Using Artificial Neural Network[J]. Neural Computation, 2005,14(12) : 319 -326.
[15]Quintana G, Garcia--Romeu M L. Surface Roughness Monitoring Application Based on Artificial Neural Networks for Ball--end Milling Operations [J]. Intellectual Manufacturing, 2009, 16: 219- 240.
[16]Pendharkar P C. Genetic Algorithm Based Neural Network Approaches for Predicting Churn in Cellular Wireless Network Services[J]. Expert Systems with Applications, 2009,36 : 6714-6720.