基于机器视觉和盲源分离的机械故障检测

doi:10.16183/j.cnki.jsjtu.2020.154

摘要/Abstract

摘要：

为解决从复杂的信号环境下提取所需的信号,克服传统方式上信号获取与处理方法的不足和多源故障振动信号位置不确定等问题,针对机械转子的多源故障情况进行研究,提出一种基于机器视觉和盲源分离的旋转机械故障检测方法.首先介绍了基于机器视觉和盲源分离问题的数学原理,然后基于盲源信号分离方法和超定视觉盲源分离方法分析获取的高速视频,从而实现多源振动信号的分离与定位.最后,实验结果表明本文中提出的检测方法能够对旋转机械多源故障进行准确定位.该方法将机器视觉测量方法与盲源分离信号处理方法进行结合,实现了对多源故障有效分离识别.

关键词: 多源故障, 机器视觉, 盲源分离, 分离识别

Abstract:

In order to solve the difficulties in extracting the required signal from a complex signal environment, and overcome the shortcomings of traditional methods for signal acquisition and processing, and the uncertain location of multi-source fault vibration signals, the multi-source fault of mechanical rotor is studied, and a fault detection method for rotating machinery based on machine vision and blind source separation is proposed. First, the basic mathematical principles of machine vision and blind source separation problem are introduced. Next, the acquired high-speed video is analyzed based on the blind source signal separation method and the overdetermined visual blind source separation method to achieve the separation and positioning of multi-source vibration signals. The experimental results show that the detection method proposed in this paper can accurately locate the multi-source faults of rotating machinery. This method combines the measurement methods of machine vision with the signal processing method of blind source separation to achieve an effective separation and identification on the multi-source faults.

Key words: multi-source fault, machine vision, blind source seperation, separation and identification

中图分类号:

TH133

彭聪, 刘彬, 周乾. 基于机器视觉和盲源分离的机械故障检测[J]. 上海交通大学学报, 2020, 54(9): 953-960.

PENG Cong, LIU Bin, ZHOU Qian. Mechanical Fault Detection Based on Machine Vision and Blind Source Separation[J]. Journal of Shanghai Jiaotong University, 2020, 54(9): 953-960.

图/表 10

图1

图2

图3

图4

表1

不同分集模式下PI系数与全局矩阵表

分集模式	PI系数	G_A
未分集	0.5790	$1.000000 0.474490 0.699818 1.000000$
二重分集	0.5947	$1.000000 0.003566 0.920868 1.000000$
四重分集	0.8876	$1.000000 0.840490 0.979818 1.000000$

表1

图5

图6

图7

图8

图9

参考文献 25

[1]	张津. 旋转机械振动信号故障诊断研究[J]. 装备机械, 2017(4):55-60.
	ZHANG Jin. Research on vibration signal fault diagnosis of rotating machinery[J]. Equipment Machine, 2017(4):55-60.
[2]	蒋龙, 臧春艳, 胡学深, 等. 基于低频振动信号的GIL机械故障诊断[J]. 电力科学与技术学报, 2019,34(3):86-91.
	JIANG Long, ZANG Chunyan, HU Xueshen, et al. Research on the diagnosis of GIL mechanical fault by low frequency vibration signal[J]. Journal of Electric Power Science and Technology, 2019,34(3):86-91.
[3]	LI G Z, TANG G, WANG H Q, et al. Blind source separation of composite bearing vibration signals with low rank and sparse decomposition[J]. Measurement, 2019,145:323-334.
[4]	XIAO Y Q, WANG H C. A two-step blind source extraction method and its application in fault diagnosis of rolling element bearing[J]. Journal of Mechanical Science and Technology, 2019,33(3):1141-1148.
[5]	GHEMARI Z, SAAD S. Development of model and enhancement of measurement precision of sensor vibration[J]. IEEE Sensors Journal, 2012,12(12):3454-3459.
[6]	蒲锰, 苗启义. 基于机器视觉的矿井提升机PLC 实时故障诊断[J].可编程控制器与工厂自动化, 2012(7):90-92.
	PU Meng, MIAO Qiyi. Mine hoist PLC real-time fault diagnosis based on machine vision[J]. Programmable Logic Controller and Factory Automation, 2012(7):90-92.
[7]	李双, 王仲生. 基于机器视觉的航空发动机转子裂纹故障识别系统[J]. 计算机测量与控制, 2009,17(4):631-632.
	LI Shuang, WANG Zhongsheng. Aero-engine rotor crack identification system based on machine vision[J]. Computational Measurement & Control, 2009,17(4):631-632.
[8]	潘锋, 阎镭, 向桂山, 等. 基于机器视觉技术的气动系统状态监控与故障诊断[J]. 机床与液压, 2005,33(8):203-204.
	PAN Feng, YAN Lei, XIANG Guishan, et al. State monitoring and fault diagnosis for pneumatic system based on machine vision[J]. Machine Tool & Hydraulics, 2005,33(8):203-204.
[9]	WANG X X, GUO J, LU S L, et al. A computer-vision-based rotating speed estimation method for motor bearing fault diagnosis[J]. Measurement Science & Technology, 2017,28(6):065012.
[10]	YANG Y C, DORN C, MANCINI T, et al. Blind identification of full-field vibration modes from video measurements with phase-based video motion magnification[J]. Mechanical System and Signal Processing, 2017,85:567-590.
[11]	JUN H, CHEN Y, ZHANG Q H, et al. Blind source separation method for bearing vibration signals[J]. IEEE Access, 2018(6):658-664.
[12]	LU J T, CHENG W, CHU Y P, et al. Post-nonlinear blind source separation with kurtosis constraints using augmented Lagrangian particle swarm optimization and its application to mechanical systems[J]. Journal of Vibration and Control, 2019,25(16):2246-2260.
[13]	李振壁, 王康, 姜媛媛. 盲源分离技术研究与方法综述[J]. 科学技术与工程, 2017,17(14):141-147.
	LI Zhenbi, WANG Kang, JIANG Yuanyuan. Research and survey on methods of blind source separation technology[J]. Science Technology and Engineering, 2017,17(14):141-147.
[14]	GONG X F, LIN Q H, CONG F Y, et al. Double coupled canonical polyadic decomposition for joint bind source separation[J]. IEEE Transactions on Signal Processing, 2018,66(13):3475-3490.
[15]	MOURAD N, REILLY J P, KIRUBARAJAN T. Majorization-minimization for blind source separation of sparse sources[J]. Signal Processsing, 2017,131:120-133.
[16]	WANG R J, ZHAN Y J, ZHOU H F. A method of underdetermined blind source separation in time-domain[J]. International Journal of Electronics, 2012,99(4):543-555.
[17]	MAGGIONI G M, KOCEVSKA S, GROVER M A, et al. Analysis of multicomponent ionic mixtures using blind source separation: A processing case study[J]. Industrial & Engineering Chemistry Research, 2019,58(50):22640-22651.
[18]	EHSANDOUST B, BABAIE-ZADEH M, RIVET B, et al. Blind source separation in nonlinear mixtures: Separability and a basic algorithm[J]. IEEE Transactions on Signal Processing, 2017,65(16):4339-4352.
[19]	ZHOU W L, CHELIDZE D. Blind source separation based vibration mode identification[J]. Mechanical Systems and Signal Processing, 2007,21(8):3072-3087.
[20]	BREWICK P T, SMYTH A W. On the application of blind source separation for damping estimation of bridges under traffic loading[J]. Journal of Sound and Vibration, 2014,333(26):7333-7351.
[21]	FORTUNA J, MARTINEZ A M. Rigid structure from motion from a blind source separation perspective[J]. International Journal of Computer Vision, 2010,88(3):404-424.
[22]	CICHOCKI A. Blind signal processing methods for analyzing multichannel brain signals[J]. International Journal of Bioelectromagnitism, 2004,6(1):1-21.
[23]	LU N Y, JIANG B, MENG X F, et al. Diagnosis, diagnosticability analysis, and test point design for multiple faults based on multisignal modeling and blind source separation[J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2020,50(1):137-148.
[24]	ZHOU B, CHEN C Z, ZHAO X G, et al. Separation for vibration and acoustic compound signals and multi-unit fault diagnosis[J]. Journal of Vibration, Measurement and Diagnosis, 2012,32(4):619-623.
[25]	YI Z G, PAN N, GUO Y. Mechanical compound faults extraction based on improved frequency domain blind deconvolution algorithm[J]. Mechanical Systems and Signal Processing, 2018,113:180-188.