具有自寻优和协同感知的主轴系统故障数据分析研究

PDF(2076 KB)

振动与冲击 ›› 2022, Vol. 41 ›› Issue (22) : 284-292.

论文

王伟平1，王琦1,2，于洋1

作者信息 +

Research on fault data analysis of spindle system with self-optimization and collaborative perception

WANG Weiping1, WANG Qi1,2, YU Yang1

Author information +

文章历史 +

摘要

围绕智能机床主轴系统故障诊断数据的融合分析问题展开研究，提出了一种具有自寻优和多维度协同感知的数据分析算法。设计了在强化学习驱动下的以双路径深度学习模型为核心的算法在线自寻优部分；基于离线、在线振动数据的波动特征分析、细节时频分析，以及电流特征分析，建立了多维度协同感知部分；采用D-S证据理论，对数据分析结果进行了量化融合判定。用凯斯西储大学（CWRU）轴承数据集，对所提算法主体环节的故障数据分析能力进行了验证。基于实际机床主轴系统的故障数据，对算法整体进了全面验证，以0.960 1的协同评估概率结果量化辨识出实际机床主轴系统的具体故障，验证了所提算法整体的有效性和准确性。
关键词：主轴系统；自寻优；协同感知；深度学习；D-S证据理论

Abstract

Focusing on the fusion analysis of fault diagnosis data of intelligent machine tool spindle system, a data analysis algorithm with self-optimization and multi-dimensional collaborative perception was proposed. The online self-optimization part of the algorithm based on the dual path deep learning model driven by reinforcement learning was designed. Based on the fluctuation characteristic analysis, detailed time-frequency analysis and current characteristic analysis of off-line and on-line vibration data, a multi-dimensional cooperative perception part was established. Using D-S evidence theory, the quantitative fusion judgment of data analysis results was carried out. The fault data analysis ability of the main link of the proposed algorithm was verified by using the Case Western Reserve University (CWRU) bearing data set. Based on the fault data of the actual machine tool spindle system, the algorithm was comprehensively verified. The specific fault of the actual machine tool spindle system was quantitatively identified with the collaborative evaluation probability result of 0.960 1, which verified the effectiveness and accuracy of the whole proposed algorithm.
Key Words: spindle system；self-optimization；collaborative perception；deep learning；D-S evidence theory

导出引用

王伟平1，王琦1,2，于洋1. 具有自寻优和协同感知的主轴系统故障数据分析研究[J]. 振动与冲击, 2022, 41(22): 284-292

WANG Weiping1, WANG Qi1,2, YU Yang1. Research on fault data analysis of spindle system with self-optimization and collaborative perception[J]. Journal of Vibration and Shock, 2022, 41(22): 284-292

参考文献

[1]韩秋实,许宝杰,王红军,等.旋转机械故障诊断监测专家系统中的时间序列模式识别技术研究[J].机械工程学报,2002(3):104-107.
HAN Qiushi, XU Baojie, WANG Hongjun,et al. Study on time series pattern recognition technology in expert system for fault diagnosis and monitoring of rotating machinery[J]. Journal of Mechanical Engineering,2002(3):104-107.
[2]陈亚农,郜普刚,何田,等.局部均值分解在滚动轴承故障综合诊断中的应用[J].振动与冲击,2012,31(3):73-78.
CHEN Yanong, GAO Pugang, HE Tian, et al. Application of local mean decomposition in comprehensive fault diagnosis of rolling bearing[J].Journal of Vibration and Shock,2012,31(3):73-78.
[3] XI S T, CAO H R, CHEN X F,et al. Dynamic modeling of machine tool spindle bearing system and model based diagnosis of bearing fault caused by collision[J]. Procedia CIRP,2018,77:614-617.
[4] BERREDJEM T, BENIDIR M. Bearing faults diagnosis using fuzzy expert system relying on an improved range overlaps and Similarity method[J]. Expert Systems With Applications,2018,108:134-142.
[5] 程卫东,赵德尊,刘东东.基于故障特征系数模板的变转速滚动轴承故障诊断[J].振动与冲击,2017,36(7):123-129.
CHENG Weidong, ZHAO Dezun, LIU Dongdong. Fault diagnosis of variable speed rolling bearing based on fault characteristic coefficient template[J]. Journal of Vibration and Shock,2017,36(7):123-129.
[6] ZHANG N N, WU L F, YANG J,et al. Naive bayes bearing fault diagnosis based on enhanced independence of data[J]. Sensors,2018,18(2):463.
[7] ZHOU Q,LIU L. Research on fault diagnosis of complex equipment based on artificial intelligence[J]. Journal of Physics: Conference Series,2020,1550(2):022028.
[8] ZHANG R T, LI B B, JIAO B. Application of Xgboost algorithm in bearing fault diagnosis[J]. IOP Conference Series: Materials Science and Engineering,2019,490(7):072062.
[9] 齐咏生,郭春雨,师芳,等.基于双结构深度学习的滚动轴承故障智能诊断[J].振动与冲击,2021,40(10):103-113.
QI Yongsheng, GUO Chunyu, SHI Fang, et al. Intelligent fault diagnosis of rolling bearing based on dual structure deep learning[J]. Journal of Vibration and Shock, 2021,40(10):103-113.
[10] YANG Z B,ZHANG J P,ZHAO Z B,et al. Interpreting network knowledge with attention mechanism for bearing fault diagnosis[J]. Applied Soft Computing,2020,97(PB):106829.
[11] PHAM M T,KIM J M,KIM C H. Deep learning-based bearing fault diagnosis method for embedded systems[J]. Sensors,2020,20(23):6886.
[12] AN J, AI P, LIU D K,et al. Deep domain adaptation model for bearing fault diagnosis with domain alignment and discriminative feature learning[J]. Shock and Vibration,2020,2020:1-10.
[13] HUANG T D, FU S, FENG H N,et al. Bearing fault diagnosis based on shallow multi-scale convolutional neural network with attention[J]. Energies,2019,12(20):3937.
[14] SHEN C Q, XIE J Q, Wang D,et al. Improved hierarchical adaptive deep belief network for bearing fault diagnosis[J]. Applied Sciences,2019,9(16):3374.
[15] ISHOLA N B, ADEYEMI O O, ADESINA A J,et al. Adaptive neuro-fuzzy inference system-genetic algorithm vs. response surface methodology: A case of optimization of ferric sulfate-catalyzed esterification of palm kernel oil[J]. Process Safety and Environmental Protection,2017,111:68-70.
[16] VIEGAS R A , MOTA F D A D S, APCSC A ,et al. A multi-criteria-based hazard and operability analysis for process safety[J]. Process Safety and Environmental Protection, 2020,144:310-321.
[17] WANG R X, JIANG H K, LI X Q,et al. A reinforcement neural architecture search method for rolling bearing fault diagnosis[J]. Measurement, 2020,154:107417.
[18] OSAROGIAGBON A U, KHAN F, VENKATESAN R, et al. Review and analysis of supervised machine learning algorithms for hazardous events in drilling operations[J]. Process Safety and Environmental Protection,2021,147:367-384.
[19] TORRES M E, COLOMINAS M A, SCHLOTTHAUER G, et al. A complete ensemble empirical mode decomposition with adaptive noise[C]//IEEE International Conference on Acoustics, Speech and Signal Processing. Prague :IEEE, 2011.
[20] JIAN X Z,LI W L,GUO X G,et al. Fault diagnosis of motor bearings based on a one-dimensional fusion neural network[J]. Sensors,2019,19(1):122.