Sparse autoencoder algorithm based on spectral envelope curve and Its application in gearbox fault diagnosis

PDF(2774 KB)

Journal of Vibration and Shock ›› 2018, Vol. 37 ›› Issue (4) : 249-256.

Zhang Shaohui Luo Jiesi

Author information +

History +

Abstract

Build fault diagnosis model based on deep learning by time domain or frequency domain as a low-level input information directly can effectively weaken the interference of man-made factors and improve the development of artificial intelligence in mechanical fault diagnosis. However, time domain signal length is difficult to draw, while frequency domain signalis too length lossing computation efficiency. Aiming at the problem, put forward to extract frequency domain signal envelope, which would get the trend of frequency information, then combined with sparse autoencoder to constructs the fault diagnosis mode. Gearbox fault diagnosis experiments indicate that, comparing with the original input frequency domain, the proposed method can effectively speed up the computation process and decrease the memory space, while keeping the ability of condition recognition.

Key words

deep learning / sparse autoencoder / gearbox / fault diagnosis

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

Zhang Shaohui Luo Jiesi . Sparse autoencoder algorithm based on spectral envelope curve and Its application in gearbox fault diagnosis[J]. Journal of Vibration and Shock, 2018, 37(4): 249-256

References

[1]林近山, 陈前. 基于非平稳时间序列双标度指数特征的齿轮箱故障诊断[J]. 机械工程学报, 2012, 48(13): 108-114.
Lin Jinshan, Chen Qian. Fault Diagnosis of Gearboxes Based on the Double-scaling-exponent Characteristic of Nonstationary Time Series[J]. Journal of Mechanical Engineering, 2012, 48(13): 108-114.
[2]王健, 冯健, 韩志艳. 基于流形学习的局部保持PCA算法在故障检测中的应用[J]. 控制与决策,2013,5(28):683-687.
Wang Jian, Feng Jian, Han Zhiyan. Locally preserving PCA method based on manifold learning and its application in fault detection[J].Control and Decision,2013,5(28):683-687.
[3]Jianbo Yu. A nonlinear probabilistic method and contribution analysis for machine condition monitoring[J]. Mechanical Systems and Signal Processing, 2013, (37): 293-314.
[4]Hinton, G. E and Salakhutdinov, R. Reducing the dimensionality of data with neural networks. [J]. Science, 2006, 313: 504-507.
[5]Hinton, G. E, Osindero. S, Y. W. A fast learning algorithm for deep belief nets. [J]. Neural Computation, 2006, 18(7): 1527-1554.
[6]Yoshua Bengio. Learning Deep Architectures for AI[J]. Foundations and Trends in Machine Learning, 2009, 2(1), pp. 1-127.
[7]Yoshua Bengio, Pascal Lamblin, Dan Popovici, et al. Greedy Layer-Wise Training of Deep Networks[C]. Advances in Neural Information Processing Systems 19(NIPS’06), 2007, pages 153-160.
[8]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.
[9]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.
[10] P Tamilselvan, P Wang. Failure diagnosis using deep belief learning based health state classification[J]. Reliability Engineering and System Safety, 2013, 115: 124-135.
[11] 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.
[12] Yang Fu, Yun Zhang, Haiyu Qiao, et al. Analysis of Feature Extracting Ability for Cutting State Monitoring Using Deep Belief Networks[J]. 15th CIRP Conference on Modelling of Machining Operations, 2015, 31: 29 – 34.
[13]Qinghua Hu, Rujia Zhang, Yucan Zhou. Transfer learning for short-term wind speed prediction with deep neural networks[J]. Renewable Energy, 2016, 85: 83-95.
[14]Meng Gan, CongWang, Chang'an Zhu. Construction of hierarchical diagnosis network based on deep learning and its application in the fault pattern recognition of rolling element bearings[J]. Mechanical Systems and Signal Processing, 2016, (72-73), 92-104.
[15]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(6): 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(6): 517-523.
[16]黄海波, 李人宪, 杨琪, 等. 基于DBNs的车辆悬架减振器异响鉴别方法[J]. 西南交通大学学报, 2015, 50(5): 776-782.
Huang Haibo, Li Renxian, YANG Qi, et al. Identifying Abnormal Noise of Vehicle Suspension Shock Absorber Based on Deep Belief Networks[J]. Journal of Southwest Jiaotong University, 2015, 50(5): 776-782.
[17]赵旻昊. 基于深度学习的数据融合在FPSO监测预警系统上的应用[D]. 天津大学, 2013.
Zhao Minmin. Data Fusion Based on Deep Learning and Its Application for FPSO Monitoring System[D].Tianjin：Tianjin University, 2013.
[18]雷亚国, 贾峰, 周昕, 等. 基于深度学习理论的机械装备大数据健康监测方法[J]. 机械工程学报, 2015, 51(21): 49-56.
Lei Yaguo, Jia Feng, Zhou Xin, et al. A Deep Learning-based Method for Machinery Health Monitoring with Big Data[J]. Chinese Journal of Mechanical Engineering, 2015, 51(21): 49-56.
[19]谢吉朋. 云平台下基于深度学习的高速列车走行部故障诊断技术研究[D]. 西南交通大学, 2015.
Xie Jipeng. Research on fault diagnosis of high speed running gear based on deep learning under cloud platform[D]. Xi’an：Southwest Jiaotong University, 2015.
[20]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.
[21]张绍辉, 李巍华. 可变近邻参数的局部线性嵌入算法及其在轴承状态识别中的应用[J]. 机械工程学报, 2013, 49(1): 81-87.
Zhang Shaohui, Li Weihua. Variable Nearest Neighbor Locally Linear Embedding and Applications in Bearing Condition Recognition [J]. Chinese Journal of Mechanical Engineering, 2013, 49(1): 81-87