A Novel Data-Driven Fault Diagnosis Method Based on Deep Learning

Mechanical fault diagnosis is an essential means to reduce maintenance cost and ensure safety in production. Aiming to improve diagnosis accuracy, this paper proposes a novel data-driven diagnosis method based on deep learning. Nonstationary signals are preprocessed. A feature learning method based on deep learning model is designed to mine features automatically. The mined features are identified by a supervised classification method – support vector machine (SVM). Thanks to mining features automatically, the proposed method can overcome the weakness that manual feature extraction depends on much expertise and prior knowledge in traditional data-driven diagnosis method. The effectiveness of the proposed method is validated on two datasets. Experimental results demonstrate that the proposed method is superior to the traditional data-driven diagnosis methods.

[1]  Hongbo Xu,et al.  An intelligent fault identification method of rolling bearings based on LSSVM optimized by improved PSO , 2013 .

[2]  Konstantinos C. Gryllias,et al.  A Support Vector Machine approach based on physical model training for rolling element bearing fault detection in industrial environments , 2012, Eng. Appl. Artif. Intell..

[3]  Haidong Shao,et al.  Rolling bearing fault diagnosis using an optimization deep belief network , 2015 .

[4]  Nicolas Le Roux,et al.  Representational Power of Restricted Boltzmann Machines and Deep Belief Networks , 2008, Neural Computation.

[5]  Paolo Pennacchi,et al.  A data-driven method to enhance vibration signal decomposition for rolling bearing fault analysis , 2016 .

[6]  Wenping Wang,et al.  Fast B-spline curve fitting by L-BFGS , 2011, Comput. Aided Geom. Des..

[7]  Zhiwen Liu,et al.  Multi-fault classification based on wavelet SVM with PSO algorithm to analyze vibration signals from rolling element bearings , 2013, Neurocomputing.

[8]  Jing Yuan,et al.  Wavelet transform based on inner product in fault diagnosis of rotating machinery: A review , 2016 .

[9]  Li Zhang,et al.  Fisher-regularized support vector machine , 2016, Inf. Sci..

[10]  K. Loparo,et al.  Bearing fault diagnosis based on wavelet transform and fuzzy inference , 2004 .

[11]  Yang Yu,et al.  A roller bearing fault diagnosis method based on EMD energy entropy and ANN , 2006 .

[12]  Hai Qiu,et al.  Wavelet filter-based weak signature detection method and its application on rolling element bearing prognostics , 2006 .

[13]  Steven X. Ding,et al.  A Survey of Fault Diagnosis and Fault-Tolerant Techniques—Part I: Fault Diagnosis With Model-Based and Signal-Based Approaches , 2015, IEEE Transactions on Industrial Electronics.

[14]  Enrico Zio,et al.  Condition assessment for the performance degradation of bearing based on a combinatorial feature extraction method , 2014, Digit. Signal Process..

[15]  Noureddine Zerhouni,et al.  Bearing Health Monitoring Based on Hilbert–Huang Transform, Support Vector Machine, and Regression , 2015, IEEE Transactions on Instrumentation and Measurement.

[16]  Feng Jia,et al.  An Intelligent Fault Diagnosis Method Using Unsupervised Feature Learning Towards Mechanical Big Data , 2016, IEEE Transactions on Industrial Electronics.

[17]  Brigitte Chebel-Morello,et al.  Application of empirical mode decomposition and artificial neural network for automatic bearing fault diagnosis based on vibration signals , 2015 .

[18]  Yitao Liang,et al.  A novel bearing fault diagnosis model integrated permutation entropy, ensemble empirical mode decomposition and optimized SVM , 2015 .