基于谐波小波包和BSA优化LS-SVM的铣刀磨损状态识别研究

中国机械工程

基于谐波小波包和BSA优化LS-SVM的铣刀磨损状态识别研究

董彩云1;张超勇1;孟磊磊1;肖鹏飞1;罗敏2;林文文3

1.华中科技大学机械学院数字制造装备与技术国家重点实验室，武汉,430074
2.湖北汽车工业学院电气与信息工程学院,十堰,442002
3.宁波大学机械工程与力学学院,宁波,315211

出版日期:2017-09-10 发布日期:2017-09-07
基金资助:
国家自然科学基金资助项目（51575211,51421062）;
国家自然科学基金国际（地区）合作与交流项目（51561125002）；
湖北省自然科学基金资助项目（2014CFB348）；
高等学校学科创新引智计划资助项目（B16019）
National Natural Science Foundation of China （No. 51575211,51421062）
Projects of International Cooperation and Exchanges NSFC（No. 51561125002）
Hubei Provincial Natural Science Foundation of China （No. 2014CFB348）

State Recognition of Milling Tool Wears Based on Harmonic Wavelet Packet and BSA Optimization LS-SVM

DONG Caiyun1;ZHANG Chaoyong1;MENG Leilei1;XIAO Pengfei1;LUO Min2;LIN Wenwen3

1.State Key Lab of Digital Manufacturing Equipment & Technology,Huazhong University of Science and Technology,Wuhan，430074
2.School of Electrical and Information Engineering,Hubei Automotive Industries Institute,Shiyan,Hubei,442002
3.School of Mechanical Engineering and Mechanics,Ningbo University,Ningbo,Zhejiang,315211

Online:2017-09-10 Published:2017-09-07
Supported by:
National Natural Science Foundation of China （No. 51575211,51421062）
Projects of International Cooperation and Exchanges NSFC（No. 51561125002）
Hubei Provincial Natural Science Foundation of China （No. 2014CFB348）

摘要/Abstract

摘要： 针对铣削刀具磨损状态识别问题,提出谐波小波包和最小二乘支持向量机（LS-SVM）的状态识别方法。为克服传统小波包分解的频带交叠问题，采用谐波小波包提取不同磨损状态下铣削力信号的各频段信号能量，归一化处理后，输入LS-SVM多类分类器，实现铣削刀具磨损状态的识别。针对LS-SVM的惩罚因子和核参数对模型识别精度影响较大的问题，提出回溯搜索算法（BSA）进行自动参数寻优。实验结果表明，谐波小波包比小波包在刀具磨损状态特征提取时具有更好的识别效果。与粒子群算法进行比较，证明BSA优化LS-SVM具有更高的识别精度。

关键词: 刀具磨损, 谐波小波包, 回溯搜索算法, 最小二乘支持向量机

Abstract: Aiming at the problems of milling tool wear state recognitions, a state recognition method was proposed based on harmonic wavelet packet and LS-SVM. To overcome the band overlapping problems in traditional wavelet packet decompositions, the milling force signal energies of each bands were extracted in different wear states by harmonic wavelet packet, which were brought in multi-class LS-SVM classifier after normalizing, then the classification recognition of different cutting tool states was achieved. BSA was proposed to search the optimal values of the kernel functional parameters and error penalty factors which affected the precision of the LS-SVM significantly. Experimental results show that harmonic wavelet packet is more effective and feasible than wavelet packet, and the proposed milling tool wear recognition method has higher accuracy.

Key words: tool wear, harmonic wavelet packet, backtracking search algorithm(BSA), least squares support vector machine(LS-SVM)

中图分类号:

TH164

董彩云1;张超勇1;孟磊磊1;肖鹏飞1;罗敏2;林文文3. 基于谐波小波包和BSA优化LS-SVM的铣刀磨损状态识别研究[J]. 中国机械工程.

DONG Caiyun1;ZHANG Chaoyong1;MENG Leilei1;XIAO Pengfei1;LUO Min2;LIN Wenwen3. State Recognition of Milling Tool Wears Based on Harmonic Wavelet Packet and BSA Optimization LS-SVM[J]. China Mechanical Engineering.

参考文献

[1]TETI R, JEMIELNIAK K, O'DONNELL G, et al. Advanced Monitoring of Machining Operations[J]. CIRP Annals—Manufacturing Technology,2010,59(2):717-739.
[2]ROTH J T, DJURDJANOVIC D, YANG X, et al. Quality and Inspection of Machining Operations: Tool Condition Monitoring[J]. Journal of Manufacturing Science & Engineering, 2010, 132(4):575-590.
[3]SNR D E D. Sensor Signals for Tool-wear Monitoring in Metal Cutting Operations—a Review of Methods[J]. International Journal of Machine Tools & Manufacture, 2000, 40(8):1073-1098.
[4]丛龙慧，韩玉杰.小波分析在刀具磨损状态检测中的应用[J].林业机械与木工设备，2009，37(4)：51-52.
CONG Longhui, HAN Yujie. Application of Wavelet Analysis in Tool Wear Status Detection[J]. Forestry Machinery & Woodworking Equipment, 2009，37(4)：51-52.

[5]陈侃，傅攀，李威霖，等．钛合金车削加工过程中刀具磨损状态监测的小波包子带能量变换特征提取新方法[J]．组合机床与自动化加工技术，2011(1)：35-38.
CHEN Kan, FU Pan, LI Weilin, et al. The Tool Wear Monitoring Based on SUB-WPA Feature Selection in Process of Titanium Alloy Machining[J]. Modular Machine Tool & Automatic Manufacturing Technique, 2011(1):35-38.
[6]林颖, 刘亚俊, 陈忠. 基于分形理论和神经网络的刀具磨损监测[J]. 中国机械工程, 2004, 15(16):20-22.
LIN Ying, LIU Yajun, CHEN Zhong. Tool Wear Detection Using Fractal Theory and Neural Network[J].China Mechanical Engineering, 2004, 15(16):20-22.
[7]NEWLAND D E. Harmonic Wavelet Analysis[J]. Proceedings of the Royal Society A： Mathematical Physical & Engineering Sciences, 1993, 443:203-225.
[8]NEWLAND D E. Wavelet Analysis of Vibration: Part 1—Theory[J].Journal of Vibration and Acoustics,1994,116(4):409-416.
[9]NEWLAND D E. Wavelet Analysis of Vibration: Part 2—Wavelet Maps[J].Journal of Vibration and Acoustics,1994,116(4):417-425.
[10]高强，何正嘉．谐波小波及其时频剖面图在旋转机械诊断中的应用[J].西安交通大学学报，2000,34(9)：62-66.
GAO Qiang, HE Zhengjia. Application of Harmonic Wavelet and Its Time-frequency Profile Plot to Diagnosis of Rotating Machinery[J].Journal of Xi'an Jiaotong University,2000,34(9):62-66.
[11]陈洁,沈远彤,李宏伟.基于谐波小波的弱信号提取[J].信号处理,2005(增刊1)：40-43.
CHEN Jie, SHEN Yuantong, LI Hongwei. Applying Harmonic Wavelet Extracting Weak Signal[J].Signal Processing,2005(S1):40-43.
[12]万方义，许庆余．裂纹转子—滑动轴承系统动静件碰摩故障的谐波小波分析[C]//2002年全国振动工程及应用学术会议论文集.北京，2002：111-116.
WAN Fangyi, XU Qingyu. Harmonic Wavelet Analysis on Cracked Rotor Sliding Bearing System with Rotor and Stator Rubbing[C]//Proceedings of the 2002 National Conference on Vibration Engineering and Application.Beijing,2002:111-116.
[13]肖忠会．谐波小波分析及其在旋转机械信号分析中的应用[J]．风机技术，2001（1）：43-46.
XIAO Zhonghui. Harmonic Wavelet Analysis and Its Application to Analyzing Signals of Rotating Machinery[J].Compressor Blower & Fan Technology,2001（1）:43-46.
[14]关山，王龙山，聂鹏．基于EMD与LS-SVM的刀具磨损识别方法[J]．北京航空航天大学学报，2011，37(2)：144-148.
GUAN Shan, WANG Longshan, Nie Peng. Identification Method of Tool Wear Based on Empirical Mode Decomposition and Least Squares Support Vector Machine[J].Journal of Beijing University of Aeronautics and Astronautics,2011,37(2):144-148.
[15]SHI D F, GINDY N N. Tool Wear Predictive Model Based on Least Squares Support Vector Machines[J].Mechanical Systems and Signal Processing,2007,21(4):1799-1814.
[16]WIDODO A, YANG B S. Support Vector Machine in Machine Condition Monitoring and Fault Diagnosis[J].Mechanical Systems and Signal Processing,2007,21(6):2560-2574.
[17]李威霖,傅攀,张尔卿.基于粒子群优化LS-SVM的车刀磨损量识别技术研究[J].计算机应用研究,2014,31(4)：1094-1097.
LI Weilin, FU Pan, ZHANG Erqing. Application of Particle Swarm Optimization-Least Square Support Vector Machine in Tool Wear Monitoring[J].Application Research of Computers,2014,31(4):1094-1097.
[18]CIVICIOGLU P. Backtracking Search Optimization Algorithm for Numerical Optimization Problems[J].Applied Mathematics & Computation,2013,219(15):8121-8144.
[19]张文斌,周晓军,林勇,等.基于谐波小波包方法的旋转机械故障信号提取[J].振动与冲击,2009,28(3)：87-89.
ZHANG Wenbin, ZHOU Xiaojun, LIN Yong, et al. Harmonic Wavelet Packet Method Used to Extract Fault Signal of a Rotation Machinery[J].Journal of Vibration and Shock,2009,28(3):87-89.
[20]VLADIMIR N, VAPNIK V. Statistical Learning Theory[M].New York:Wiley,1998.
[21]VAPNIK V.The Nature of Statistical Learning Theory[M].Dordrecht: Springer Science & Business Media,2013.
[22]SUYKENS J A K, GESTEL T V, Brabanter J D, et al. Least Squares Support Vector Machines[J]. Euphytica, 2002, 2(2):1599-1604.
[23]SUYKENS J A K. Least Squares Support Vector Machine Classifiers[J].Neural Processing Letters,1999,9(3):293-300.
[24]HSU C W, LIN C J. A Comparison of Methods for Multiclass Support Vector Machines[J]. IEEE Transactions on Neural Networks,2002,13(2):415-425.
[25]董晓睿.基于支持向量机的多分类模型的研究和设计[D].南昌：南昌大学,2013.
DONG Xiaorui. Research and Design of Multiclassification Model Based on Support Vector Machine[D]. Nanchang:Nanchang University,2013.
[26]王晓娟,刘三阳,田文凯.带高效变异尺度系数和贪婪交叉策略的回溯搜索优化算法[J].计算机应用,2014,34(9)：2543-2546.
WANG Xiaojuan, LIU Sanyang, TIAN Wenkai. Improved Backtracking Search Optimization Algorithm with New Effective Mutation Scale Factor and Greedy Crossover Strategy[J].Journal of Computer Applications,2014,34(9):2543-2546.
[27]田文凯.一种高效自学习性回溯搜索优化算法[J].电子科技,2015,28(2)：41-45.
TIAN Wenkai. Effective Self-learning Backtracking Search Optimization Algorithm[J].Electronic Science and Technology,2015,28(2):41-45.
[28]李牧东,赵辉,翁兴伟.具有广泛学习策略的回溯搜索优化算法[J].系统工程与电子技术,2015,37(4)：958-963.
LI Mudong, ZHAO Hui, WENG Xingwei. Backtracking Search Optimization Algorithm with Comprehensive Learning Strategy[J].Journal of Systems Engineering and Electronics,2015,37(4):958-963.