LS-SVM回归算法在刀具磨损量预测中的应用

摘要/Abstract

摘要：

提出了基于最小二乘支持向量机回归算法的刀具磨损量预测方法。该方法首先利用经验模态分解算法对非线性、非平稳的声发射信号进行平稳化处理，得到了若干个固有模态函数；然后建立了每个固有模态函数的自回归模型，并提取模型系数构造特征向量；最后采用最小二乘支持向量机回归算法实现了刀具磨损量的预测。该方法与神经网络预测算法相比,具有更高的预测准确率,可有效预测当前切削状态下10s后的刀具磨损量。

关键词: 刀具磨损量预测, 最小二乘支持向量机, 经验模态分解, 自回归模型

Abstract:

Aiming at online predicting tool wear accurately, a method based on the regression algorithm of LS-SVM was proposed. First the acoustic emission signals were decomposed into several intrinsic mode functions(IMF) employing empirical mode decomposition. Then, an AR model of each IMF was established respectively. AR model coefficients were extracted to construct feature vector. Finally, the feature vectors were feed into LS-SVM and prediction of tool wear was realized. The experimental results show that it can predict the amount of tool wear after 10s according to the current cutting conditions and the proposed method has better accuracy compared with neural network algorithm.

Key words: tool wear prediction;lease square support vector machine(LS-SVM);empirical mode decomposition(EMD);auto regressive(AR) , model

中图分类号:

TH165.3

关山, 闫丽红, 彭昶. LS-SVM回归算法在刀具磨损量预测中的应用[J]. 中国机械工程, 2015, 26(2): 217-222.

Guan Shan, Yan Lihong, Peng Chang. Application of Regression Algorithm of LS-SVM in Tool Wear Prediction[J]. China Mechanical Engineering, 2015, 26(2): 217-222.

参考文献

[1]关山,聂鹏.L-M优化算法BP网络在刀具磨损量预测中的应用[J].机床与液压,2012,40(15):22-26.
Guan Shan,Nie Peng.Application of Improved L-M Optimization Algorithm BP Neural Network in Tool Wear Prediction[J]. Machine Tool & Hydraulics,2012,40(15):22-26.
[2]王国锋,李启铭,秦旭达,等.支持向量机在刀具磨损多状态监测中的应用[J].天津大学学报,2011,49(1):35-39.
Wang Guofeng,Li Qiming,Qin Xuda,et al.Application of Support-vector Machine in Tool Wear of Multi-stage Monitoring[J]. Journal of Tianjin University,2011,49(1):35-39.
[3]王计生,喻俊馨,黄惟公.小波包分析和支持向量机在刀具故障诊断中的应用[J].振动、测试与诊断,2008,28(3):273-276.
Wang Jisheng,Yu Junxin,Huang Weigong.Application of Wavelet Package Analysis and Support Vector Machine to Fault Diagnosis of Cutting Tool[J].Journal of Vibration,Measurement & Diagnosis,2008,28(3):273-276.
[4]Zhu Kunpeng,Wong Yoke San,Hong Geok Soon.Wavelet Analysis of Sensor Signals for Tool Condition Monitoring:A Review and Some New Results[J].International Journal of Machine Tools & Manufacture,2009,49(7):537-553.
[5]Dutta S,Datta A,Das Chakladar N,et al.Detection of Tool Condition from the Turned Surface Images Using an Accurate Grey Level Co-occurrence Technique[J].Precision Engineering,2012,36(3):458-466.
[6]Zhu Kunpeng,Yoke San Wong,Geok Soon Hong.Multi-category Micro-milling Tool Wear Monitoring with Continuous Hidden Markov Models[J].Mechanical Systems and Signal Processing,2009,23(2):547-560.
[7]Huang N E,Shen Z,Long S R,et al.The Empirical Mode Decomposition and the Hilbert Spectrum for Nonlinear and Non-stationary Time Series Analysis[J]. Proceedings of the Royal Society of London Series A:Mathematical and Physical Sciences, 1998,454:903-995.
[8]刘立君,王奇,杨克已,等.基于EMD和频谱校正的故障诊断方法[J].仪器仪表学报,2011,32(6):1278-1283.
Liu Lijun,Wang Qi,Yang Keji,et al.EMD and Spectrum Correction-based Fault Diagnosis Method[J].Chinese Journal of Scientific Instrument,2011,32(6):1278-1283.
[9]周云龙,王锁斌,刘永奇.自回归和EMD用于离心式风机不对中故障分析[J].振动、测试与诊断,2011,31(5)： 582-585.
Zhou Yunlong,Wang Suobin,Liu Yongqi.Application of EMD and Auto-regressive Model in Centrifugal Fan Misalignment Fault Analysis[J].Journal of Vibration,Measurement & Diagnosis,2011,31(5):582-585.
[10]吴森,韦灼彬,王绍忠,等.基于AR模型和主成分分析的损伤识别方法[J].振动、测试与诊断,2012,32(5):841-845.
Wu Sen,Wei Zhuobin,Wang Shaozhong,et al.Damage Identification Based on AR Model and PCA[J].Journal of Vibration, Measurement & Diagnosis, 2012,32(5):841-845.
[11]王利伟，王姣.云-SVM模型及在数控机床刀具磨损状态预测中的应用[J].组合机床与自动化加工技术，2012(9):25-27.
Wang Liwei,Wang Jiao.Cloud-SVM Model and Its Application in the Prediction of CNC Machine Tool Wear State[J]. Modular Machine Tool & Automatic Manufacturing Technique，2012(9)：25-27.
[12]郭新晨.最小二乘支持向量机算法及其应用研究[D].吉林：吉林大学，2008.

[1]	余杭卓1;秦圣峰1,2;丁国富1;江磊1;梁红琴1. 侧铣加工刀具回转轮廓误差预测技术研究[J]. 中国机械工程, 2020, 31(03): 306-313.
[2]	宁静;冉伟;种传杰;陈春俊. 基于S变换的高速列车小幅蛇行识别方法[J]. 中国机械工程, 2019, 30(09): 1097-1102,1110.
[3]	葛亮, 苗瑞, 葛秋原, 吴易洲. [质量优化]窄搭接焊缝涡流信号的特征提取与缺陷识别[J]. 中国机械工程, 2019, 30(02): 225-229.
[4]	张旭刚, 敖秀奕, 张华, 江志刚, . [机械装备再制造]考虑失效特征的废旧零部件再制造成本预测模型研究[J]. 中国机械工程, 2018, 29(21): 2594-2599.
[5]	钱承;胡红生. 基于最小二乘支持向量机的压电作动器迟滞非线性建模及参数辨识[J]. 中国机械工程, 2018, 29(07): 835-841.
[6]	肖鹏飞1;张超勇1;罗敏1;林文文2. 基于自适应动态无偏最小二乘支持向量机的刀具磨损预测建模[J]. 中国机械工程, 2018, 29(07): 842-849.
[7]	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, 2017, 28(17): 2080-2089,2108.
[8]	王帅1,2;向阳1,2;王磊1,2. 基于集总经验模态分解和极坐标表示的瞬时转速诊断方法[J]. 中国机械工程, 2017, 28(15): 1848-1853,1861.
[9]	马艳丽;金兵;张学欣;韩捷. 基于全矢融合与多维经验模态分解的滚动轴承退化过程频谱结构研究[J]. 中国机械工程, 2017, 28(14): 1747-1752.
[10]	张淑清1;李威1;张立国1，2;胡永涛1;钱;磊1;姜万录1. 基于多元经验模态分解互近似熵及GG聚类的轴承故障诊断[J]. 中国机械工程, 2016, 27(24): 3362-3367.
[11]	陈换过, 陈培, 陈文华, 蔡丽, 沈建洋, 吴建伟, 吴明建, . 采样频率对聚合经验模态分解的影响研究[J]. 中国机械工程, 2016, 27(18): 2472-2476.
[12]	韩中合, 徐搏超, 朱霄珣, 焦宏超 . 基于近似熵和集成经验模态分解的转子多故障诊断方法研究[J]. 中国机械工程, 2016, 27(16): 2186-2189,2248.
[13]	郑近德, 潘海洋, 潘紫微, 罗洁思. 自适应无参经验小波变换及其在转子故障诊断中的应用[J]. 中国机械工程, 2016, 27(16): 2218-2224.
[14]	崔宝珍, 马泽玮, 李会龙, 王珊. 基于广义形态学滤波和Hilbert边际谱的滚动轴承故障诊断[J]. 中国机械工程, 2016, 27(11): 1484-1488.
[15]	何青, 褚东亮, 毛新华. 基于EEMD和MFFOA-SVM滚动轴承故障诊断[J]. 中国机械工程, 2016, 27(09): 1191-1197.