基于多传感器信号的主轴回转误差在线回归预测方法研究

doi:10.3969/j.issn.1000-1158.2024.09.07

摘要
图/表
参考文献(30)
相关文章 (15)

全文: PDF (0 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要通过对主轴回转误差形成机理分析,基于多传感器信号构建了主轴回转误差回归预测模型。首先,使用LMD分解方法和皮尔逊相关系数算法对主轴回转误差密切相关的主轴前轴承振动信号、主轴电流信号和前轴承声发射信号进行特征量提取和寻优降维,克服了以往机床主轴回转误差预测中原始信号类型过于单一的问题。其次,针对各监测信号与机床主轴回转误差之间的非线性问题,利用支持向量机模型特有的RBF核函数实现多输入量下的非线性预测、找到数据之间的复杂关系,但模型中宽度系数σ、惩罚因子C和不敏感损失系数ε的有效确定是建立其RBF核函数的难题,为此建立了基于粒子群算法的支持向量机模型对主轴回转误差进行回归预测。再次,为评价该模型的有效性,提出了基于均方误差、平均绝对误差和决定系数的主轴回转误差回归预测模型评价方法。最后,使用i5m4数控加工中心对上述预测模型进行了实验研究,结果表明:该PSO-SVM回归预测模型的均方误差为0.19%,平均绝对误差为4.58%,决定系数为0.9237,相对于优化前模型,该PSO-SVM回归预测模型可准确有效实现主轴回转误差的预测。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	迟玉伦
	宋卓阳
	王国强
	姚磊

关键词 ：几何量计量, 主轴回转误差, 多传感器信号, PSO-SVM, LMD, 皮尔森相关系数

Abstract：By analyzing the formation mechanism of spindle rotation errors, regression forecasting model of spindle rotation errors which based on multi-sensor signal was built. Firstly, the LMD method and Pearson correlation coefficient method were used to extract feature values and optimize dimensionality reduction for the vibration signals, current signals, and acoustic emission signals of the front bearing, which solve the problem that types of original signals used in prediction of spindle rotation error of CNC machine tools were too single.Secondly, aiming at the nonlinear problems between various monitoring signals and rotation errors of the machine tool spindle, the RBF kernel function was used to achieve nonlinear prediction under multiple inputs and find complex relationships between datas.However,to establish RBF kernel function, the effective determination of width coefficient σ, penalty factor C and insensitive loss coefficient ε was a challenge in the model. Therefore, a support vector machine model based on particle swarm optimization algorithm was established to predict the spindle rotation errors. Once again, to evaluate the effectiveness of the model, a regression prediction model evaluation method for spindle rotation error based on mean square error, mean absolute error and coefficient of determination was proposed. Finally, experimental research was conducted on above prediction model in the i5m4 CNC machining center. The results showed that the mean square error of PSO-SVM regression prediction model was 0.19%, the average absolute error was 4.58%, the coefficient of determination was 0.9237. Compared with the model before optimization, the PSO-SVM regression forecasting model can predict the spindle rotation errors accurately and effectively.

Key words： geometric measurement;spindle rotation error multi signal PSO-SVM LMD PCA

收稿日期: 2023-10-07 发布日期: 2024-09-26

PACS:

TB92

基金资助:国家自然科学基金(51605294)

通讯作者: 姚磊(1983- ),山东菏泽人,上海理工大学讲师,主要从事物联网等方面研究。Email:yaolei_usst@126.com E-mail: Chiyulun@163.com

作者简介: 迟玉伦(1983-),黑龙江牡丹江人,上海理工大学机械工程学院高级实验师,主要从事现代制造技术等方面研究。Email:chiyulun@163.com

引用本文:

迟玉伦,宋卓阳,王国强,姚磊. 基于多传感器信号的主轴回转误差在线回归预测方法研究[J]. 计量学报, 2024, 45(9): 1300-1313.
CHI Yulun,SONG Zhuoyang,WANG Guoqiang,YAO Lei. Study on Regression Prediction Method of Multi Signal Spindle PSO-SVM Rotation Error Based on LMD. Acta Metrologica Sinica, 2024, 45(9): 1300-1313.

链接本文:

http://jlxb.china-csm.org:81/Jwk_jlxb/CN/10.3969/j.issn.1000-1158.2024.09.07 或 http://jlxb.china-csm.org:81/Jwk_jlxb/CN/Y2024/V45/I9/1300

［7］	李想, 邓建, 浮燕, 等. 主轴回转精度测试方法研究［J］. 机械设计, 2016, 33(7): 39-45.
［17］	马朝永, 盛志鹏, 胥永刚, 等. 基于自适应频率切片小波变换的滚动轴承故障诊断［J］. 农业工程学报, 2019, 35(10): 34-41.
［13］	Soliman E, Ismail F. Chatter detection by monitoring spindle drive current［J］. International Journal of Advanced Manufacturing Technology, 1997, 13: 27-34.
［9］	康婷, 汪鹏鹏. 基于动力学模型的轴承间隙对机床主轴回转精度的影响研究［J］. 制造技术与机床, 2021 (8): 170-174.
［28］	郭强, 李红霞, 李玉晓. 基于改进粒子群算法的数控加工参数优化研究［J］. 机械制造与自动化, 2021, 50(3): 132-135.
［10］	梁建红. 基于Bi-LSTM网络的电主轴回转误差预测方法研究［D］. 绵阳:西南科技大学, 2021.
［23］	刁宁昆, 马怀祥, 王金师, 等. 基于MPE与PSO-SVM的滚动轴承故障诊断［J］. 电子测量技术, 2021, 44(21): 44-48.
［29］	刘洋, 关世玺, 沙业典. 基于粒子群优化法的支持向量机回归对膛线加工切削力的预测［J］. 工具技术, 2022, 56(2): 62-65.
［30］	沈建新, 杨善林. 智能电网视角下粒子群优化支持向量机的用电量预测［J］. 科技管理研究, 2013, 33(11): 235-238.
［11］	张新明. 声发射技术在滚动轴承故障诊断中的应用［D］. 北京: 清华大学, 2006.
［4］	李树森, 任毅, 陈素平, 等. 静压气体轴承主轴系统回转误差的控制与补偿［J］. 润滑与密封, 2016, 41(2): 23-25.
［5］	杨赫然, 赵桐, 孙兴伟, 等. 基于改进遗传算法的机床主轴径向回转误差分离技术研究［J］. 仪器仪表学报, 2021, 42(1): 82-91.
［14］	刘晓胜, 吴乐南, 马玉林, 等. 基于电流信号的铣削颤振识别技术研究［J］. 机械工程学报, 2000, 36(4): 25-29.
［12］	ZHUO R J, DENG Z H, CHEN B, et al. Research on online intelligent monitoring system of band saw blade wear status based on multi-feature fusion of acoustic emission signals［J］. The International Journal of Advanced Manufacturing Technology, 2022, 121(7-8): 4533-4548.
［15］	JONATHAN S S. The Local Mean Decomposition and Its Application to EEG Perception Data. ［J］. Journal of the Royal Society Interface, 2005, 2(5): 443-454.
	XU Z F, LI X D, ZHANG C C, et al. Research on Small Sample Rolling Bearing Fault Diagnosis Based on Siamese Network［J］. Chinese Journal of Scientific Instrument, 2022, 43(10): 241-251.
	MA C Y, SHENG Z P, XU Y G, et al. Rolling Bearing Fault Diagnosis Based on Adaptive Frequency Slicing Wavelet Transform ［J］. Transactions of the Chinese Society of Agricultural Engineering, 2019, 35(10): 34-41.
	LIN J G, HU Z X, LI J, et al. Fault Diagnosis of Rolling Bearings at Low Speed Based on AE Signal and LMD ［J］. Journal of Power Engineering, 2019, 39(4): 293-298.
［1］	罗勇. 高速主轴动态回转精度分析及试验研究［D］. 南京: 南京航空航天大学, 2019.
［16］	徐卓飞, 李旭东, 张婵婵, 等. 基于孪生网络的小样本滚动轴承故障诊断研究［J/OL］. 仪器仪表学报, 2022, 43(10): 241-251.
［19］	刘若男, 辛义忠, 李岩. 基于皮尔逊相关系数的动态签名验证方法［J］. 仪器仪表学报, 2022, 43(7): 279-287.
［21］	肖心园, 江冰, 任其文, 等. 基于插值法和皮尔逊相关的光伏数据清洗［J］. 信息技术, 2019, 43(5): 19-22.
［25］	孙康, 金江涛, 李春, 等. 基于优化经验小波变换与改进支持向量机的齿轮箱故障检测策略［J］. 热能动力工程, 2022, 37(8): 186-196.
［3］	YE C, ZHAO X S, GAO W G, et al. A novel multi-probe method for separating spindle radial error from artifact roundness error［J］. The International Journal of Advanced Manufacturing Technology, 2017, 93(1-4): 623-634.
	LI S S, REN Y, CHEN S P, et al. Control and Compensation of Spindle System Rotary Error in Hydrostatic Gas Bearings ［J］. Lubrication and Sealing, 2016, 41(2): 23-25.
	YANG H R, ZHAO T, SUN X W, et al. Research on Spindle Radial Rotary Error Separation Technology Based on Improved Genetic Algorithm ［J］. Chinese Journal of Scientific Instrument, 2021, 42(1): 82-91.
	WEI X J, WANG H J, WANG Z, et al. Research on Spindle Rotary Error Based on a New Time Domain Three-point Method ［J］. Machine Tool & Hydraulics, 2019, 549(11): 83-85.
［18］	林江刚, 胡正新, 李晶, 等. 低转速下基于AE信号与LMD的滚动轴承故障诊断［J］. 动力工程学报, 2019, 39(4): 293-298.
	LI J C. Analysis of the Influence of Spindle Rotary Error on Machining Accuracy ［J］. Industrial Design, 2012 (2): 170.
［6］	魏许杰, 王红军, 王泽, 等. 基于新的时域三点法的机床主轴回转误差研究［J］. 组合机床与自动化加工技术, 2019, 549(11): 83-85.
［8］	刘蜀韬, 杨平, 康海燕, 等. 基于三点法的主轴回转误差二次分离技术［J］. 制造技术与机床, 2008 (2): 112-115.
［24］	金江涛, 许子非, 李春, 等. 基于深度学习与支持向量机的滚动轴承故障诊断研究［J］. 热能动力工程, 2022, 37(6): 176-184.
［2］	李九川. 机床主轴回转误差对加工精度影响分析［J］. 工业设计, 2012 (2): 170.
	LI X, DENG J, FU Y, et al. Research on Spindle Rotary Accuracy Testing Method ［J］. Machinery Design, 2016, 33(7): 39-45.
	LIU S T, YANG P, KANG H Y, et al. Secondary Separation Technology of Spindle Rotary Error Based on Three-point Method ［J］. Manufacturing Technology & Machine Tool, 2008 (2): 112-115.
	KANG T, WANG P P. Research on the Influence of Bearing Clearance on Spindle Rotary Accuracy Based on Dynamic Model ［J］. Manufacturing Technology & Machine Tool, 2021 (8): 170-174.
	LIU X S, WU L N, MA Y L, et al. Research on Milling Chatter Recognition Technology Based on Current Signals［J］. Journal of Mechanical Engineering, 2000, 36(4): 25-29.
	LIU R N, XIN Y Z, LI Y. Dynamic Signature Verification Method Based on Pearson Correlation Coefficient ［J］. Chinese Journal of Scientific Instrument, 2022, 43(7): 279-287.
［20］	纪德洋, 金锋, 冬雷, 等. 基于皮尔逊相关系数的光伏电站数据修复［J］. 中国电机工程学报, 2022, 42(4): 1514-1523.
［22］	WEI K W, ZHANG J, HE Y, et al . Faulty Feeder Detection Method Based on VMD-FFT and Pearson Correlation Coefficient of Non-Power Frequency Component in Resonant Grounded Systems［J］. Energies, 2020, 13(18): 4724-4724.
	DIAO N K, MA H X, WANG J S, et al. Rolling Bearing Fault Diagnosis Based on MPE and PSO-SVM ［J］. Electronic Measurement Technology, 2021, 44(21): 44-48.
	JIN J T, XU Z F, LI C, et al. Research on Fault Diagnosis of Rolling Bearings Based on Deep Learning and Support Vector Machine ［J］. Journal of Thermal Power Engineering, 2022, 37(6): 176-184.
	SUN K, JIN J T, Li C, et al. Gearbox Fault Detection Strategy Based on Optimized Empirical Wavelet Transform and Improved Support Vector Machine ［J］. Journal of Thermal Power Engineering, 2022, 37(8): 186-196.
［27］	CHEN D R, JIA M L, CHEN K T , et al. An Improved Co-evolutionary Strategy for Nonlinear Constrained System Based on Particle Swarm Optimization［J］. Journal of Signal Processing, 2012, 16(6): 511-518.
	GUO Q, LI H X, LI Y X. Research on CNC Machining Parameter Optimization Based on Improved Particle Swarm Optimization Algorithm ［J］. Machinery Manufacturing and Automation, 2021, 50(3): 132-135
	JI D Y, JIN F, DONG L, et al. Data Restoration of Photovoltaic Power Plant Based on Pearson Correlation Coefficient ［J］. Proceedings of the CSEE, 2022, 42(4): 1514-1523.
	XIAO X Y, JIANG B, REN Q W, et al. Data Cleaning of Photovoltaic Power Generation Based on Interpolation and Pearson Correlation ［J］. Information Technology, 2019, 43(5): 19-22.
［26］	KANKAR P K, SHARMA S C, Harsha S P. Vibration-based fault diagnosis of a rotor bearing system using artificial neural network and support vector machine［J］. Int. J. of Modelling, Identification and Control, 2012, 15(3): 185-198.
	LIU Y, GUAN S X, SHA Y D. Prediction of Cutting Force in Rifling Machining Based on Support Vector Machine Regression Optimized by Particle Swarm Optimization ［J］. Tool Engineering, 2022, 56(2): 62-65.
	SHEN J X, YANG S L. Power Consumption Prediction of Intelligent Power Grid Based on Particle Swarm Optimization Support Vector Machine ［J］. Science and Technology Management Research, 2013, 33(11): 235-238.