基于CEEMD和GWO-SVR的铣削振动信号前瞻预测

摘要
图/表
参考文献(22)
相关文章 (7)

全文: PDF (4856 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要汽车覆盖件模具多采用镶块式模件拼接后整体加工，拼接区加工时易引发载荷突变产生冲击振动，影响拼接区的整体加工质量，为了提高拼接区的加工精度，对铣削过程的时域振动信号进行前瞻预测。首先基于互补式集合经验模态分解方法将铣削振动信号进行6层模态分解，得到各层本征模态函数及趋势序列；然后分别构建不同工况下的支持向量回归预测模型，采用灰狼优化算法对支持向量回归中的参数进行寻优分析；最后对时域振动信号进行重构和前瞻预测。试验结果表明，在淬硬钢拼接区铣削过程中，结合CEEMD和GWO-SVR的铣削振动信号前瞻预测方法相较于其它传统方法具有更良好的预测效果，在预测时间为0.12秒时总体预测准确率达94%以上。

	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
	吴石
	张轩瑞
	刘献礼

关键词 ：铣削振动, 前瞻预测, 互补式集成经验模态, 支持向量回归, 灰狼优化算法

Abstract：Auto cover molds are mostly processed as a whole after the splicing of insert-type modules. When the splicing area is processed, it is easy to cause sudden load changes and shock vibration, which affects the overall processing quality of the splicing area. In order to improve the processing accuracy of the splicing area, the time domain of the milling process Prospective prediction of vibration signals. First, based on the complementary ensemble empirical mode decomposition method, the milling vibration signal is subjected to 6-layer modal decomposition to obtain the eigenmode function and trend sequence of each layer; then the support vector regression prediction models under different working conditions are constructed respectively, and the gray wolf is used The optimization algorithm analyzes the parameters in the support vector regression; finally, reconstructs and predicts the time-domain vibration signal. The test results show that the forward-looking prediction method of milling vibration signals combined with CEEMD and GWO-SVR has a better prediction effect than other traditional methods in the milling process of the hardened steel splicing zone. The overall prediction is accurate when the prediction time is 0.12 seconds. The rate is over 94%.

Key words： Miling vibrationl Perspective forecast Integrated empirical mode Support vector regression Grey Wolf optimization algorithm

收稿日期: 2020-12-22 出版日期: 2022-06-15

引用本文:

吴石,张轩瑞,刘献礼. 基于CEEMD和GWO-SVR的铣削振动信号前瞻预测[J]. 振动与冲击, 2022, 41(11): 199-209.
WU Shi, ZHANG Xuanrui, LIU Xianli. Forward-looking prediction of milling vibration signal based on CEEMD and GWO-SVR. JOURNAL OF VIBRATION AND SHOCK, 2022, 41(11): 199-209.

链接本文:

http://jvs.sjtu.edu.cn/CN/ 或 http://jvs.sjtu.edu.cn/CN/Y2022/V41/I11/199

[1] 吴石, 林连冬, 肖飞, 等. 基于多类超球支持向量机的铣削颤振预测方法[J]. 仪器仪表学报, 2012, 33(11): 2414-2421.
WU S, LIN L D, XIAO F, et al. Milling chatter prediction method based on multiclass hypersphere support vector machine[J]. Chinese Journal of Scientific Instrument, 2012, 33(11): 2414-2421.
[2] ZHANG S J, TO S, ZHANG G Q, et al. A review of machine-tool vibration and its influence upon surface generation in ultra-precision machining[J]. International Journal of Machine Tools and Manufacture， 2015,91: 34-42.
[3] KANKAR P K, SHARMA S C, HARSHA S P. Rolling element bearing fault diagnosis using wavelet transform[J]. Journal of Vibration and Control, 2011, 74(10): 1638-1645.
[4] 李志农, 朱明, 褚福磊, 等. 基于经验小波变换的机械故障诊断方法研究[J]. 仪器仪表学报, 2014, 35(11): 2423-2432.
LI Z N, ZHU M, CHU F L, et al. Mechanical fault diagnosis method based on empirical wavelet transform[J]. Chinese Journal of Scientific Instrument, 2014, 35(11): 2423-2432.
[5] XU F, PETER W T. A method combining refined composite multiscale fuzzy entropy with PSO-SVM for roller bearing fault diagnosis[J]. Journal of Central South University, 2019, 26(09): 2404-2417.
[6] 李从志, 郑近德, 潘海洋, 等. 基于精细复合多尺度散布熵与支持向量机的滚动轴承故障诊断方法[J]. 中国机械工程, 2019, 30(14): 1713-1719.
LI C Z, ZHENG J D, PAN H Y, et al. Fault diagnosis method of rolling bearings based on refined composite multiscale dispersion entropy and support vector machine[J]. China Mechanical Engineering, 2019, 30(14): 1713-1719.
[7] WU Z, HUANG N E. Ensemble empirical mode decomposition:A Noise-Assisted data analysis method[J]. Advances in Adaptive Data Analysis, 2009, 1(1): 1-41.
[8] 雷苗, 彭宇, 彭喜元. 面向混沌时间序列预测的隐式特征提取算法[J]. 仪器仪表学报, 2014, 35(1): 1-7.
LEI M, PENG Y, PENG X Y. Novel hidden feature extraction method for chaotic time series prediction[J]. Chinese Journal of Scientific Instrument, 2014, 35(1): 1-7.
[9] 王民, 冯猛, 姚子良, 等. 基于ARIMA的磨削颤振预测方法[J]. 北京工业大学学报, 2016, 42(04): 609-613.
WANG M, FENG M, YAO Z L, et al. Prediction of grinding chatter based on the ARIMA[J]. Journal of Beijing University of Technology. 2016, 42(04): 609-613..
[10] 吴海滨, 陈寅生, 张庭豪, 等. 改进多尺度幅值感知排列熵与随机森林结合的滚动轴承故障诊断[J]. 光学精密工程, 2020, 28(03): 621-631.
WU H B, CHEN Y S, ZHANG T H, et al. Rolling bearing fault diagnosis by improved multiscale amplitude-aware permutation entropy and random forest[J].Optics and Precision Engineering, 2020, 28(03): 621-631.
[11] 苏祖强, 汤宝平, 邓蕾, 等. 有监督LLTSA特征约简旋转机械故障诊断[J]. 仪器仪表学报, 2014, 35(08): 1766-1771.
SU Z Q, TANG B P, DENG L, et al. Rotating machinery fault diagnosis with supervised-linear local tangent space alignment for dimension reduction [J]. Chinese Journal of Scientific Instrument, 2014, 35(08): 1766-1771.
[12] AN X L, YANG L, PAN L P. Nonlinear prediction of condition parameter degradation trend for hydropower unit based on radial basis function interpolation and wavelet transform[J]. Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science, 2015, 229(18): 3515-3525.
[13] 李晓晖, 傅攀, 曹伟青, 等. 机械密封端面接触状态的声发射监测研究[J]. 振动与冲击, 2016, 35(08): 83-89.
LI X H, FU P, CAO W Q, et al. The study of acoustic emission monitoring for contact state of seal end faces [J]. Journal of Vibration and Shock, 2016, 35(08): 83-89.
[14] 瓦普尼克•弗拉基米尔. 统计学理论[M]. 张学工，译. 北京：清华大学出版社, 2000.
VAPNIK VN. The Essence of Statistical Learning Theory[M]. Zhang X G, translation. Beijing: Tsinghua University Press, 2000.
[15] 任世锦, 潘剑寒, 李新玉, 等. 基于ELMD与改进SMSVM的机械故障诊断方法[J]. 南京航空航天大学学报, 2019, 51(05): 693-703.
REN S J, PAN J H, LI X Y, et al. Novel Machinery Fault Diagnosis Approach via ELMD and Improved SMSVM [J]. Journal of Nanjing University of Aeronautics & Astronautics, 2019, 51(05): 693-703.
[16] LI Z, YANG Z, PENG Y, et al. Prediction of chatter stability for milling process using Runge-Kutta-based complete discretization method[J]. The International Journal of Advanced Manufacturing Technology, 2016, 86(1-4): 943-952.
[17] SHI J H, SONG Q H, LIU Z Q, et al. A novel stability prediction approach for thin-walled component milling considering material removing process[J]. Chinese Journal of Aeronautics, 2017, 30(05): 1789-1798.
[18] HAN J J, ZHU J, ZHENG W, et al. Influence of metal forming parameters on surface roughness and establishment of surface roughness prediction model[J]. International Journal of Mechanical Sciences, 2019, 163:105093.
[19] WANG F B, WANG Y Q. Investigate on milling force of cryogenic cooling processing aluminum honeycomb treated by ice fixation[J]. The International Journal of Advanced Manufacturing Technology, 2018, 98(5-8): 1253-1265.
[20] YEH J R, SHIEH J S, HUANG N E. Complementary ensemble empirical mode decomposition: a novel noise enhanced data analysis method[J]. Advances in Adaptive Data Analysis, 2010, 2(2): 135-156.
[21] 韦祥, 李本威, 吴易明. GFD和核主元分析的机械振动特征提取[J]. 振动、测试与诊断, 2019, 39(01): 32-38+219.
WEI X, LI B W, WU Y M. Vibration feature extraction based on generalized fractal dimension and kernel principal component analysisi[J]. Journal of Vibration, Measurement＆Diagnosis, 2019, 39(01): 32-38+219.
[22] MIRJALILI S, MIRJALILI S M, LEWIS A. Grey wolf optimizer[J]. Advances in Engineering Software, 2014, 69: 46-61.