The Optimized Deep Belief Networks With Improved Logistic Sigmoid Units and Their Application in Fault Diagnosis for Planetary Gearboxes of Wind Turbines

Efficient and accurate planetary gearbox fault diagnosis is the key to enhance the reliability and security of wind turbines. Therefore, an intelligent and integrated approach based on deep belief networks (DBNs), improved logistic Sigmoid (Isigmoid) units, and impulsive features is proposed in this paper. The vanishing gradient problem is an inherent drawback of conventional Sigmoid units, and it usually occurs in the backpropagation process of DBNs, resulting in that the training is considerably slowed down and the classification rate is reduced. To solve this problem, Isigmoid units are designed to combine the merits of unsaturation from leaky rectified linear (LReL) units. The results of handwritten digit recognition experiments show the superiority of Isigmoid over Sigmoid on convergence speed and classification accuracy. Since impulses contain much useful fault information, especially for early failures, an integrated approach using the optimized Morlet wavelet transform, kurtosis index, and soft-thresholding is applied to extract impulse components from original signals to improve the diagnosis accuracy. Then, the features extracted from original signals and impulsive signals are employed to train and test the DBNs with Isigmoid, Sigmoid, and LReL units for comparison. Finally, the results of planetary gearbox fault diagnosis show that Isigmoid has higher comprehensive performance than conventional sigmoid and LReL.

[1]  David He,et al.  On the Use of a Single Piezoelectric Strain Sensor for Wind Turbine Planetary Gearbox Fault Diagnosis , 2015, IEEE Transactions on Industrial Electronics.

[2]  Geoffrey E. Hinton.  Training Products of Experts by Minimizing Contrastive Divergence , 2002, Neural Computation.

[3]  Fulei Chu,et al.  Application of regularization dimension to gear damage assessment , 2010 .

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

[5]  Hui Li,et al.  The Improved Training Algorithm of Back Propagation Neural Network with Self-adaptive Learning Rate , 2009, 2009 International Conference on Computational Intelligence and Natural Computing.

[6]  Liming Wang,et al.  Optimal demodulation subband selection for sun gear crack fault diagnosis in planetary gearbox , 2018, Measurement.

[7]  Yi Qin,et al.  A New Family of Model-Based Impulsive Wavelets and Their Sparse Representation for Rolling Bearing Fault Diagnosis , 2018, IEEE Transactions on Industrial Electronics.

[8]  Yi Qin,et al.  Weak transient fault feature extraction based on an optimized Morlet wavelet and kurtosis , 2016 .

[9]  Jun Yu,et al.  Fault diagnosis of planetary gearbox with incomplete information using assignment reduction and flexible naive Bayesian classifier , 2018 .

[10]  Andrew L. Maas.  Rectifier Nonlinearities Improve Neural Network Acoustic Models , 2013 .

[11]  Mark A. Kramer,et al.  Diagnosis using backpropagation neural networks—analysis and criticism , 1990 .

[12]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

[13]  Byeng D. Youn,et al.  Multi-Sensor Health Diagnosis Using Deep Belief Network Based State Classification , 2011 .

[14]  Bing He,et al.  Feature fusion using kernel joint approximate diagonalization of eigen-matrices for rolling bearing fault identification , 2016 .

[15]  Andrew D. Ball,et al.  An approach to fault diagnosis of reciprocating compressor valves using Teager-Kaiser energy operator and deep belief networks , 2014, Expert Syst. Appl..

[16]  Tianqi Chen,et al.  Empirical Evaluation of Rectified Activations in Convolutional Network , 2015, ArXiv.

[17]  Jürgen Schmidhuber,et al.  Learning Complex, Extended Sequences Using the Principle of History Compression , 1992, Neural Computation.

[18]  Ruslan Salakhutdinov,et al.  On the quantitative analysis of deep belief networks , 2008, ICML '08.

[19]  Yaoyu Li,et al.  A review of recent advances in wind turbine condition monitoring and fault diagnosis , 2009, 2009 IEEE Power Electronics and Machines in Wind Applications.

[20]  Bongtae Han,et al.  Autocorrelation-based time synchronous averaging for condition monitoring of planetary gearboxes in wind turbines , 2016 .

[21]  Ming J. Zuo,et al.  Feature selection for damage degree classification of planetary gearboxes using support vector machine , 2011 .

[22]  Richard Hans Robert Hahnloser,et al.  Digital selection and analogue amplification coexist in a cortex-inspired silicon circuit , 2000, Nature.

[23]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[24]  Benedikt K. Humpert.  Improving back propagation with a new error function , 1994, Neural Networks.

[25]  Zhipeng Feng,et al.  Fault diagnosis for wind turbine planetary gearboxes via demodulation analysis based on ensemble empirical mode decomposition and energy separation , 2012 .

[26]  Wentian Zhao,et al.  Fault diagnosis network design for vehicle on-board equipments of high-speed railway: A deep learning approach , 2016, Eng. Appl. Artif. Intell..

[27]  Haidong Shao,et al.  Electric Locomotive Bearing Fault Diagnosis Using a Novel Convolutional Deep Belief Network , 2018, IEEE Transactions on Industrial Electronics.

[28]  Xue Sen Lin,et al.  Engine components fault diagnosis using an improved method of deep belief networks , 2016, 2016 7th International Conference on Mechanical and Aerospace Engineering (ICMAE).

[29]  Darryll J. Pines,et al.  A review of vibration-based techniques for helicopter transmission diagnostics , 2005 .

[30]  Yi Qin,et al.  Multicomponent decomposition by wavelet modulus maxima and synchronous detection , 2017 .

[31]  Geoffrey E. Hinton.  A Practical Guide to Training Restricted Boltzmann Machines , 2012, Neural Networks: Tricks of the Trade.

[32]  Liang Guo,et al.  A neural network constructed by deep learning technique and its application to intelligent fault diagnosis of machines , 2018, Neurocomputing.

[33]  Yoshua Bengio,et al.  Deep Sparse Rectifier Neural Networks , 2011, AISTATS.