基于多路稀疏自编码的轴承状态动态监测

PDF(3464 KB)

振动与冲击 ›› 2016, Vol. 35 ›› Issue (19) : 125-131.

论文

基于多路稀疏自编码的轴承状态动态监测

张绍辉

作者信息 +

Bearing condition dynamic monitoring based on Multi-way sparse autocoder

Zhang Shaohui

Author information +

文章历史 +

摘要

机械系统的运行是一个时变的过程，为了更好的监测系统的健康状况，通常在设备系统的关键部位加装各种传感器，由此产生大量的数据，传统的单一数据或者人为经验指导均无法快速有效的提取其中的状态信息，排除冗余成分的影响，实现对设备运行状态实时有效的判断。为了有效利用设备上的多路传感器信息，并融合这些信息提取描述系统运行状态的有效成分，实现对机械系统的在线监测。提出利用稀疏自编码深度学习模型对各个传感器采集到的数据进行融合，并结合平方预测误差SPE(Square prediction error-SPE) 指标描述设备运行状态，轴承仿真及轴承故障实验证明，采用稀疏自编码与平方预测误差相结合的模型能够有效的监测轴承故障，并对故障部位进行准确定位。

Abstract

Mechanical systems are working in time-varying process. In order to better monitor the health of the system, various sensors are installed in key parts of the equipment system, thereby generating large amounts of data. Traditional single data or human experience are both unable to quickly and efficiently extract the state information, excluding the impact of redundant components and make effective judgments for the operational status of equipment at real-time. In order to make use of multiple sensor information on the device and integration of these information for extraction the ingredients to achieve on-line monitoring of mechanical systems, a method of sparse autocoder deep learning model is proposed, which is to fusion of sensors data. It is combined with the SPE (Square prediction error-SPE) to describe the equipment running status indicators. Bearing simulation and bearing fault experiments show, that sparse autocoder deep learning model can effectively monitor bearing failure and fault location.

导出引用

张绍辉. 基于多路稀疏自编码的轴承状态动态监测[J]. 振动与冲击, 2016, 35(19): 125-131

Zhang Shaohui . Bearing condition dynamic monitoring based on Multi-way sparse autocoder[J]. Journal of Vibration and Shock, 2016, 35(19): 125-131

参考文献

[1] Hinton, G. E and Salakhutdinov, R. Reducing the dimensionality of data with neural networks. [J]. Science, 2006, 313: 504-507.
[2] Hinton, G. E, Osindero. S, Y. W. A fast learning algorithm for deep belief nets. [J]. Neural Computation, 2006, 18(7): 1527-1554.
[3] Honglak Lee, Roger Grosse, Rajesh Ranganath, et al. Unsupervised Learning of Hierarchical Representations with Convolutional Deep Belief Networks.[J]. Communications of The ACM, 2011, 54: 95-103.
[4] Feng Li, Loc Tran, Kim-Han Thung, et al. Robust Deep Learning for Improved Classification of AD/MCI Patients. [J]. Machine Learning in Medical Imaging, Lecture Notes in Computer Science, 2014, 8679: 240-247.
[5] Xiaonan Hu, Qihe Liu, Hongbin Cai, et al. Gas Recognition Under Sensor Drift by Using Deep Learning.[J]. Practical Applications of Intelligent Systems Advances in Intelligent Systems and Computing, 2014, 279: 23-33.
[6] 深度学习：推进人工智能的梦想[EB/OL].http://www.csdn.net/article/2013-05-29/2815479, 2013
Deep learning: advancing the dream of artificial intelligence[EB/OL].http://www.csdn.net/article/2013-05-29/2815479, 2013
[7] Adam项目展示微软研究院人工智能领域新突破[EB/OL].http://blog.sina.com.cn/s/blog_4caedc7a0102uxma.html, 2014.
Adam project show Microsoft research new breakthroughs in artificial intelligence field [EB/OL].http://blog.sina.co m.cn/s/blog_4caedc7a0102uxma.html, 2014.
[8]谷歌4亿美元收购人工智能公司DeepMind [EB/OL].http://tech.sina.com.cn/i/2014-01-27/09259131393.shsht, 2014.
Google's $400 million takeover of the company DeepMind artificial intelligence[EB/OL].http://tech.sina.com.cn/i/201 4-0 1-27/09259131393.shtml, 2014.
[9] P Tamilselvan, P Wang. Failure diagnosis using deep belief learning based health state classification.[J]. Reliability Engineering and System Safety, 2013, 115: 124-135.
[10] V.T Tran, F.AThobiani, A Ball. An approach to fault diagnosis of reciprocating compressor valves using Teager-Kaiser energy operator and deep belief networks.[J]. Expert Systems with Applications, 2014, 41: 4113-4122.
[11] 王宪保, 李洁, 姚明海, 等.基于深度学习的太阳能电池片表面缺陷检测方法[J]. 模式识别与人工智能, 2014, 27: 517-523.
Wang Xian-Bao, Li Jie, Yao Ming-Hai, et al. Solar Cells Surface Defects Detection Based on Deep Learning[J]. Pattern Recognition and Artificial Intelligence, 2014, 27: 517-523.
[12] Nomikos, P, MacGregor,J.F.Multivariate SPC charts for monitoring batch processes[J]. Technometrics,1995,37: 41-59.
[13] Y.F.WANG, P. J. KOOTSOOKOS. Modeling of low shaft speed bearing faults for condition monitoring[J]. Mechanical Systems and Signal Processing, 1998, vol.12, no.3: 415-426.
[14] Qiu H,Lee J,Lin J,et al.Wavelet filter-based weak signature detection method and its application on rolling element bearing prognostics[J]. Journal of Sound and Vibration, 2006, 289(4/5):1066-1090.
[15] 王雷. 基于流形学习的滚动轴承故障诊断若干方法研究[D]. 大连：大连理工大学, 2013.
Wang Lei. Research on Rolling Element Bearing Fault Diagnosis Methods Based on Manifold Learning[D]. DaLian，Da Lian University of Technology, 2013.