Multiple Wavelet Coefficients Fusion in Deep Residual Networks for Fault Diagnosis - PowerPoint PPT Presentation

View by Category
About This Presentation
Title:

Multiple Wavelet Coefficients Fusion in Deep Residual Networks for Fault Diagnosis

Description:

A Deep Neural Network Based Fault Diagnosis Method. M. Zhao, M. Kang, B. Tang, M. Pecht, "Multiple Wavelet Coefficients Fusion in Deep Residual Networks for Fault Diagnosis," IEEE Transactions on Industrial Electronics, DOI: 10.1109/TIE.2018.2866050 – PowerPoint PPT presentation

Number of Views:11
Date added: 3 October 2018
Slides: 14
Provided by: Username withheld or not provided

less

Write a Comment
User Comments (0)
Transcript and Presenter's Notes

Title: Multiple Wavelet Coefficients Fusion in Deep Residual Networks for Fault Diagnosis


1
Multiple Wavelet Coefficients Fusion in Deep
Residual Networks for Fault Diagnosis
  • Minghang Zhao, Myeongsu Kang, Baoping Tang,
    Michael Pecht
  • M. Zhao, M. Kang, B. Tang, M. Pecht, "Multiple
    Wavelet Coefficients Fusion in Deep Residual
    Networks for Fault Diagnosis," IEEE Transactions
    on Industrial Electronics, DOI
    10.1109/TIE.2018.2866050

2
Backgrounds
  • Accurate fault diagnosis is important to ensure
    the safety of automobiles and helicopters,
    long-term generation of electric power, and
    reliable operating of other electrical and
    mechanical systems.
  • Discrete wavelet packet transform (DWPT), an
    effective tool to decompose non-stationary
    vibration signals into various frequency bands,
    has been widely applied for machine fault
    diagnosis 1.
  • Besides, the usage of deep learning methods is
    becoming more and more popular to automatically
    learn discriminative features from vibration
    signals for improving diagnostic accuracies 2.
  • M. Zhao, M. Kang, B. Tang, M. Pecht, "Multiple
    Wavelet Coefficients Fusion in Deep Residual
    Networks for Fault Diagnosis," IEEE Transactions
    on Industrial Electronics, DOI
    10.1109/TIE.2018.2866050

3
Motivations
  • However, there is still no consensus as to which
    wavelet (e.g., DB1, DB2, and DB3) can achieve an
    optimal performance in fault diagnosis.
  • Besides, different wavelets may be optimal for
    recognizing different kinds of faults under
    different working conditions.
  • It is very unlikely for one certain wavelet to be
    the most effective in recognizing all kinds of
    faults (such as bearing inner raceway faults,
    outer raceway faults, and rolling element
    faults).
  • Therefore, the fusion of multiple wavelets into
    deep neural networks has an potential to improve
    the accuracy of a fault diagnostic task which
    involves the recognition of various fault types.
  • M. Zhao, M. Kang, B. Tang, M. Pecht, "Multiple
    Wavelet Coefficients Fusion in Deep Residual
    Networks for Fault Diagnosis," IEEE Transactions
    on Industrial Electronics, DOI
    10.1109/TIE.2018.2866050

4
Input Data Configuration
  • The wavelet coefficients at various frequency
    bands obtained using a certain wavelet can be
    stacked to be a 2D matrix then, the 2D matrices
    derived from multiple wavelets can be formed to
    be a 3D matrix.
  • M. Zhao, M. Kang, B. Tang, M. Pecht, "Multiple
    Wavelet Coefficients Fusion in Deep Residual
    Networks for Fault Diagnosis," IEEE Transactions
    on Industrial Electronics, DOI
    10.1109/TIE.2018.2866050

5
An Overview of Deep Residual Networks
  • The deep residual network (DRN) is an improved
    variant of convolutional neural networks (CNNs),
    which uses identity shortcuts to ease the
    difficulty of training 3-4.

BN Batch normalization ReLU Rectifier linear
unit Conv 33 Convolution with kernels in the
size of 33 GAP Global average pooling
  • M. Zhao, M. Kang, B. Tang, M. Pecht, "Multiple
    Wavelet Coefficients Fusion in Deep Residual
    Networks for Fault Diagnosis," IEEE Transactions
    on Industrial Electronics, DOI
    10.1109/TIE.2018.2866050

6
The First Developed Method
  • To achieve multiple wavelet coefficients fusion,
    a simple method is to concatenate these 2D
    matrices of wavelet coefficients and feed them
    into a DRN.
  • The method was named as Multiple Wavelet
    Coefficients Fusion in a Deep Residual Network by
    Concatenation (MWCF-DRN-C).

m an indicator of the number of convolutional
kernels
  • M. Zhao, M. Kang, B. Tang, M. Pecht, "Multiple
    Wavelet Coefficients Fusion in Deep Residual
    Networks for Fault Diagnosis," IEEE Transactions
    on Industrial Electronics, DOI
    10.1109/TIE.2018.2866050

7
The Second Developed Method
  • An individual convolutional layer with trainable
    parameters is applied to each 2D matrix of
    wavelet coefficients with the goal of converting
    the important wavelet coefficients to be large
    features. Then, the element-wise maximum features
    are chosen to be the output in the maximization
    layer 5.
  • The method was named as Multiple Wavelet
    Coefficients Fusion in a Deep Residual Network by
    Maximization (MWCF-DRN-M).
  • M. Zhao, M. Kang, B. Tang, M. Pecht, "Multiple
    Wavelet Coefficients Fusion in Deep Residual
    Networks for Fault Diagnosis," IEEE Transactions
    on Industrial Electronics, DOI
    10.1109/TIE.2018.2866050

8
Explanations on the Second Developed Method
  • The 2D matrices of wavelet coefficients are
    different representations of the same vibration
    signal.
  • It is unavoidable that these 2D matrices of
    wavelet coefficients contain much
    redundant/repetitive information.
  • M. Zhao, M. Kang, B. Tang, M. Pecht, "Multiple
    Wavelet Coefficients Fusion in Deep Residual
    Networks for Fault Diagnosis," IEEE Transactions
    on Industrial Electronics, DOI
    10.1109/TIE.2018.2866050

9
Explanations on the Second Developed Method
  • The maximization layer and the convolutional
    layers before it can be interpreted as a
    trainable feature selection process, which allows
    the important features to be passed to the
    subsequent layers while the relatively
    unimportant features being abandoned.
  • M. Zhao, M. Kang, B. Tang, M. Pecht, "Multiple
    Wavelet Coefficients Fusion in Deep Residual
    Networks for Fault Diagnosis," IEEE Transactions
    on Industrial Electronics, DOI
    10.1109/TIE.2018.2866050

10
Experimental Setup
  • A drivetrain dynamics simulator 6 was used to
    simulate the faults.
  • Experiments were conducted under the 10-fold
    cross-validation scheme.
  • Comparisons were made with the conventional CNN
    and DRN to demonstrate the efficacy of the
    developed MWCF-DRN-C and MWCF-DRN-M.
  • M. Zhao, M. Kang, B. Tang, M. Pecht, "Multiple
    Wavelet Coefficients Fusion in Deep Residual
    Networks for Fault Diagnosis," IEEE Transactions
    on Industrial Electronics, DOI
    10.1109/TIE.2018.2866050

11
Results
  • M. Zhao, M. Kang, B. Tang, M. Pecht, "Multiple
    Wavelet Coefficients Fusion in Deep Residual
    Networks for Fault Diagnosis," IEEE Transactions
    on Industrial Electronics, DOI
    10.1109/TIE.2018.2866050

12
Conclusions
  • The fusion of multiple wavelet coefficients in
    deep neural networks can be able to improve the
    fault diagnostic performance.
  • In the experimental result, the MWCF-DRN-M method
    was slightly better than the MWCF-DRN-C method by
    yielding a 0.80 improvement in terms of overall
    average testing accuracy.
  • M. Zhao, M. Kang, B. Tang, M. Pecht, "Multiple
    Wavelet Coefficients Fusion in Deep Residual
    Networks for Fault Diagnosis," IEEE Transactions
    on Industrial Electronics, DOI
    10.1109/TIE.2018.2866050

13
References
  • R. Yan, R. X. Gao, and X. Chen, Wavelets for
    fault diagnosis of rotary machines A review with
    applications, Signal Process., vol. 96, pp.
    115, 2014.
  • M. Zhao, M. Kang, B. Tang, and M. Pecht, Deep
    Residual Networks With Dynamically Weighted
    Wavelet Coefficients for Fault Diagnosis of
    Planetary Gearboxes, IEEE Transactions on
    Industrial Electronics, vol. 65, no. 5, pp.
    42904300, 2018.
  • K. He, X. Zhang, S. Ren, and J. Sun, Deep
    residual learning for image recognition, in
    Proc. IEEE Conf. Comput. Vision Pattern
    Recognit., Seattle, WA, USA, Jun. 2730, 2016,
    pp. 770778.
  • K. He, X. Zhang, S. Ren, and J. Sun, Identity
    mappings in deep residual networks, in Computer
    VisionECCV 2016 (Lecture Notes in Computer
    Science 9908), B. Leibe, J. Matas, N. Sebe, and
    M. Welling, Eds., Cham, Switzerland Springer,
    2016, pp. 630645.
  • Z. Liao and C. Gustavo, A deep convolutional
    neural network module that promotes competition
    of multiple-size filters, Pattern Recognit.,
    vol. 71, pp. 94105, 2017.
  • Drivetrain Diagnostics Simulator. SpectraQuest,
    Richmond, VA, USA, Online. Available
    http//spectraquest.com/drivetrains/details/dds/
  • M. Zhao, M. Kang, B. Tang, M. Pecht, "Multiple
    Wavelet Coefficients Fusion in Deep Residual
    Networks for Fault Diagnosis," IEEE Transactions
    on Industrial Electronics, DOI
    10.1109/TIE.2018.2866050
About PowerShow.com