Interpretable Convolutional Neural Network through Layer-wise Relevance Propagation for Machine Fault Diagnosis

John Grezmak, Jianjing Zhang, Peng Wang, Kenneth A. Loparo, Robert X. Gao

Research output: Contribution to journalArticlepeer-review

56 Scopus citations

Abstract

As a state-of-the-art pattern recognition technique, convolutional neural networks (CNNs) have been increasingly investigated for machine fault diagnosis, due to their ability in analyzing nonlinear and nonstationary high-dimensional data that are typically associated with the performance degradation process of machines. A key issue of interest is how the inputs to CNNs that contain fault-related patterns are learned by CNNs to recognize discriminatory information for fault diagnosis. Understanding this link will help establish connection to the physical meaning of the diagnosis, contributing to the broad acceptance of CNNs as a trustworthy complement to physics-based reasoning by human experts. Using Layer-wise Relevance Propagation (LRP) as an indicator, this paper investigates the performance of a CNN trained by time-frequency spectra images of vibration signals measured on an induction motor. The LRP provides pixel-level representation of which values in the input signal contribute the most to the diagnosis results, thereby providing an improved understanding of how the CNN learns to distinguish between fault types from these inputs. Results have shown that the patterns learned by CNNs in the time-frequency spectra images are intuitive and consistent with respect to network re-training. Comparison with using raw time series and discrete Fourier transform coefficients as inputs reveals that time-frequency images allow for more consistent pattern recognition by CNNs.

Original languageEnglish
Article number8930493
Pages (from-to)3172-3181
Number of pages10
JournalIEEE Sensors Journal
Volume20
Issue number6
DOIs
StatePublished - Mar 15 2020

Bibliographical note

Funding Information:
Manuscript received September 25, 2019; revised November 27, 2019; accepted November 27, 2019. Date of publication December 10, 2019; date of current version February 14, 2020. This work was supported in part by the National Science Foundation under Grant CNS-1737612 and Grant CMMI-1830295 and in part by the Institute for Smart, Secure, and Connected Systems (ISSACS) through the Cleveland Foundation under the IOT Collaborative. The associate editor coordinating the review of this article and approving it for publication was Prof. Ruqiang Yan. (Corresponding author: Robert X. Gao.) J. Grezmak, J. Zhang, and R. X. Gao are with the Department of Mechanical and Aerospace Engineering, Case Western Reserve University, Cleveland, OH 44016 USA (e-mail: jeg100@case.edu; jxz170@case.edu; robert.gao@case.edu).

Publisher Copyright:
© 2001-2012 IEEE.

Keywords

  • Motor fault diagnosis
  • convolutional neural network
  • layer-wise relevance propagation

ASJC Scopus subject areas

  • Instrumentation
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Interpretable Convolutional Neural Network through Layer-wise Relevance Propagation for Machine Fault Diagnosis'. Together they form a unique fingerprint.

Cite this