基于DNN整机建模的滚珠丝杠进给系统关键结合部动态特性参数辨识

摘要
图/表
参考文献(29)
相关文章 (8)

全文: PDF (4715 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要针对滚珠丝杠进给系统关键结合部动态特性参数的辨识精度不高等问题。提出利用可表征结合部动态特性参数与整机固有频率之间映射关系的深度神经网络(Deep Neural Network, DNN)建立进给系统整机的等效动力学模型；结合进给系统固有频率的DNN预测值与实验模态分析值，采用粒子群优化(Particle Swarm Optimization, PSO)算法对进给系统关键结合部的不同方向的刚度、阻尼参数同时辨识。以自行设计制造的进给系统试验台为实例进行整机建模、实验、参数辨识等分析；最终的辨识结果达到很高精度，说明该方法是可行、有效的。

	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
	朱迪
	张玮
	黄之文
	朱坚民

关键词 ：滚珠丝杠进给系统, 关键结合部, 动态特性参数, 深度神经网络, 整机建模

Abstract：Aiming at the problem of low identification accuracy for key joints’ dynamic characteristic parameters of ball screw feed system, the deep neural network (DNN) which can characterize the mapping relationship between the dynamic characteristic parameters of the joint and the natural frequency of the whole machine, is proposed to establish the equivalent dynamic model of the whole feeding system. With the DNN predicted value and the experimental modal analysis value for the natural frequency of the whole feed system, the particle swarm optimization (PSO) algorithm is used to identify the stiffness and damping parameters of the key joints’ different directions for the feed system at the same time. As an example, the whole machine modeling, experiment and parameter identification are conducted for the self-designed and manufactured feeding system test-bed. The final identification result achieves high accuracy, which shows that the method is feasible and effective.

Key words： ball screw feed system key joints dynamic characteristic parameters deep neural network whole machine modeling

收稿日期: 2021-09-23 出版日期: 2023-02-15

引用本文:

朱迪，张玮，黄之文，朱坚民. 基于DNN整机建模的滚珠丝杠进给系统关键结合部动态特性参数辨识[J]. 振动与冲击, 2023, 42(3): 243-254.
ZHU Di, ZHANG Wei, HUANG Zhiwen, ZHU Jianmin. Dynamic characteristics parametric identification of key joint of ball screw feed system based on DNN modelling. JOURNAL OF VIBRATION AND SHOCK, 2023, 42(3): 243-254.

链接本文:

http://jvs.sjtu.edu.cn/CN/ 或 http://jvs.sjtu.edu.cn/CN/Y2023/V42/I3/243

[1] 陈勇将，汤文成，华洪良，等. 含虚拟材料结合部的高速滚珠丝杠进给系统动态特性分析[J]. 机床与液压，2021, 49(08): 156-160.
CHEN Yong-jiang, TANG Wen-cheng, HUA Hong-liang, et al. Dynamic characteristic analysis of high-speed ball screw feed system with virtual material joint [J]. Machine tool and hydraulic, 2021, 49 (08): 156-160.
[2] 刘栋，梅雪松，冯斌，等. 基于Symlets小波滤波的滚珠丝杠伺服进给系统频响特性辨识[J]. 机械工程学报，2011, 47(13)：153-159.
LIU Dong, MEI Xue-song, FENG Bin, et al. Identification of frequency response characteristics of ball screw servo feed system based on Symlets wavelet filter [J]. Journal of mechanical engineering, 2011, 47 (13): 153-159.
[3] 赵宏林，丁庆新，曾鸣，等. 机床结合部特性的理论解析及应用[J]. 机械工程学报，2008, 44(12): 208-214.
ZHAO Hong-lin, DING Qing-xin, ZENG Ming, et al. Theoretical analysis and application of characteristics of machine tool joint [J]. Journal of mechanical engineering, 2008, 44 (12): 208-214.
[4] 王世军，赵金娟，张慧军，等. 一种结合部法向刚度的预估方法[J]. 机械工程学报，2011, 47(21): 111-115+122.
WANG Shi-jun, ZHAO Jin-juan, ZHANG Hui-jun, et al. A prediction method of normal stiffness of joint [J]. Journal of mechanical engineering, 2011, 47 (21): 111-115 + 122.
[5] 董冠华，殷勤，殷国富，等. 机床结合部动力学建模与辨识方法的研究[J]. 机械工程学报，2016, 52(05): 162-168.
DONG Guan-hua, YIN Qin, YIN Guo-fu, et al. Research on Dynamic Modeling and identification method of machine tool joint [J]. Journal of mechanical engineering, 2016, 52 (05): 162-168.
[6] 李小彭，王冰冰，运海萌，等. 直线滚动导轨有限元模态分析及参数识别[J]. 中国工程机械学报，2016, 14(5): 375-380.
LI Xiao-peng, WANG Bing-bing, YUN Hai-meng, et al. Finite element modal analysis and parameter identification of linear rolling guide [J]. Chinese Journal of construction machinery, 2016, 14 (5): 375-380.
[7] OKWUDIRE C E. Improved Screw–Nut Interface Model for High-Performance Ball Screw Drives[J]. Journal of Mechanical Design, 2011, 133(4): 10-25.
[8] 付振彪，王太勇，张雷，等. 滚珠丝杠进给系统动力学建模与动态特性分析[J]. 振动与冲击，2019, 38(16): 56-63.
FU Zhen-biao, WANG Tai-yong, ZHANG Lei, et al. Dynamic modeling and dynamic characteristic analysis of ball screw feed system [J]. Vibration and impact, 2019, 38 (16): 56-63.
[9] 蒋书运，祝书龙. 带滚珠丝杠副的直线导轨结合部动态刚度特性[J]. 机械工程学报，2010, 46(01): 92-99.
JIANG Shu-yun, ZHU Shu-long. Dynamic stiffness characteristics of linear guide rail joint with ball screw pair [J]. Journal of mechanical engineering, 2010, 46 (01): 92-99.
[10] 董亮，汤文成，刘立. 滚珠丝杠进给系统混合建模及其振动时变性分析[J]. 振动与冲击，2013, 32(20): 196-202.
DONG Liang, TANG Wen-cheng, LIU Li. Hybrid modeling and vibration time-varying analysis of ball screw feed system [J]. Vibration and impact, 2013, 32 (20): 196-202.
[11] 邵瑞影，王洪军，姜宝华，等. 高速滚珠丝杠进给系统参数辨识方法与实验研究[J]. 机床与液压，2020, 48(11): 92-98+133.
SHAO Rui-ying, WANG Hong-jun, JIANG Bao-hua, et al. Parameter identification method and experimental research of high speed ball screw feed system [J]. Machine tool and hydraulic, 2020, 48 (11): 92-98 + 133.
[12] 朱坚民，张统超，王健，等. 数控机床进给单元滚动结合部轴向动态特性参数识别[J]. 振动与冲击，2015, 34(16): 1-8.
ZHU Jian-min, ZHANG Tong-chao, WANG Jian, et al. Identification of axial dynamic characteristic parameters of rolling joint of feed unit of NC machine tool [J]. Vibration and impact, 2015, 34 (16): 1-8.
[13] 田丰庆，朱坚民，李孝茹，等. 基于频响函数法的固定结合部参数辨识研究[J]. 振动与冲击，2018, 37(11): 18-26.
TIAN Feng-qing, ZHU Jian-min, LI Xiao-ru, et al. Study on parameter identification of fixed joint based on method of frequency response function [J]. Vibration and impact, 2018, 37 (11): 18-26.
[14] 毛健，赵红东，姚婧婧. 人工神经网络的发展及应用[J].电子设计工程，2011, 19(24): 62-65.
MAO Jian, ZHAO Hong-dong, YAO Jing-jing. Development and application of artificial neural network [J]. Electronic design engineering, 2011, 19 (24): 62-65.
[15] 夏瑜潞. 人工神经网络的发展综述[J]. 电脑知识与技术，2019, 15(20): 227-229.
XIA Yu-lu. Review of the development of artificial neural networks [J]. Computer knowledge and technology, 2019, 15 (20): 227-229.
[16] 张学良，黄玉美，赵宏林，等. 利用BP网络预测结合面基础特性参数[J]. 机械科学与技术，1996(05): 185-188.
ZHANG Xue-liang, HUANG Yu-mei, ZHAO Hong-lin, et al. Prediction of basic characteristic parameters of joint surface by BP network [J]. Mechanical science and technology, 1996 (05): 185-188.
[17] 黄俊，汪振华，袁军堂，等. 滚珠丝杠-螺母副结合部轴向动态特性参数测试与分析[J]. 中国机械工程，2017, 28(10): 1149-1155.
HUANG Jun, WANG Zhen-hua, YUAN Jun-tang, et al. Test and analysis of axial dynamic characteristic parameters of ball screw nut joint [J]. China Mechanical Engineering, 2017, 28 (10): 1149-1155.
[18] 朱坚民，周亚南，何丹丹，等. 基于神经网络建模的机床滑动结合面动态特性参数识别[J]. 振动与冲击，2018, 37(07): 109-115+131.
ZHU Jian-min, ZHOU Ya-nan, HE Dan-dan, et al. Dynamic characteristic parameter identification of machine tool sliding joint based on neural network modeling [J]. Vibration and impact, 2018, 37 (07): 109-115 + 131.
[19] SHERWOOD B, WANG L. Partially linear additive quantile regression in ultra-high dimension[J]. The Annals of Statistics, 2016, 44(1): 288-317.
[20] 朱虎明，李佩，焦李成，等. 深度神经网络并行化研究综述[J]. 计算机学报，2018, 41(08): 1861-1881.
ZHU Hu-ming, LI Pei, JIAO Li-cheng, et al. Review of deep neural network parallelization [J]. Journal of computer science, 2018, 41 (08): 1861-1881.
[21] 焦李成，杨淑媛，刘芳，等. 神经网络七十年：回顾与展望[J].计算机学报，2016, 39(08): 1697-1716.
JIAO Li-cheng, YANG Shu-yuan, LIU Fang, et al. Seventy years of neural network: review and prospect [J]. Journal of computer science, 2016, 39 (08): 1697-1716.
[22] 赵春华，胡恒星，陈保家，等. 基于深度学习特征提取和WOA-SVM状态识别的轴承故障诊断[J]. 振动与冲击，2019, 38(10): 31-37+48.
ZHAO Chun-hua, HU Xing-xing, CHEN Bao-jia, et al. Bearing fault diagnosis based on deep learning feature extraction and woa-svm state recognition [J]. Vibration and shock, 2019, 38 (10): 31-37 + 48.
[23] XIA M, LI T, LIU L Z, et al. Intelligent fault diagnosis approach with unsupervised feature learning by stacked denoising autoencoder[J]. IET Science, Measurement & Technology, 2017, 11(6): 687-695.
[24] 陈亮，汪景福，王娜，等. 基于DNN算法的移动视频推荐策略[J]. 计算机学报，2016, 39(08): 1626-1638.
CHEN Liang, WANG Jing-fu, WANG Na, et al. Mobile video recommendation strategy based on DNN algorithm [J]. Journal of computer science, 2016, 39 (08): 1626-1638.
[25] ZHANG W, LIU X R, HUANG Z W, et al. Dynamic parameters identification for sliding joints of surface grinder based on deep neural network modeling[J]. Advances in Mechanical Engineering, 2021, 13(2): 1-15.
[26] 罗文峰，余岭. 基于特征参数的栓接结合部螺栓预紧力评估[J]. 振动与冲击，2019, 38(04): 121-128.
LUO Wen-feng, YU Ling. Bolt preload evaluation of bolted joint based on characteristic parameters [J]. Vibration and impact, 2019, 38 (04): 121-128.
[27] 芮红锋，胡小秋，郭丹枫. 角接触球轴承动态特性参数测试方法[J]. 振动与冲击，2013, 32(08): 88-90.
RUI Hong-feng, HU Xiao-qiu, GUO Dan-feng. Test method for dynamic characteristic parameters of angular contact ball bearings [J]. Vibration and shock, 2013, 32 (08): 88-90.
[28] 朱坚民, 张统超, 李孝茹. 基于结合部刚度特性的滚珠丝杠进给系统动态特性分析[J]. 机械工程学报, 2015, 51(17): 72-82.
ZHU Jian-min, ZHANG Tong-chao, LI Xiao-ru. Dynamic characteristics analysis of ball screw feed system based on joint stiffness characteristics [J] Journal of mechanical engineering, 2015, 51 (17): 72-82.
[29] 朱坚民, 郑洲洋, 胡育佳, 等. 滚珠丝杠进给系统滚动结合部径向动态特性参数辨识[J]. 中国机械工程, 2018, 29(04): 441-449.
ZHU Jian-min, ZHENG Zhou-yang, HU Yu-jia, et al. Radial dynamic characteristic parameter identification of rolling joint of ball screw feed system [J] China Mechanical Engineering, 2018, 29 (04): 441-449.