Skip to main navigation Skip to search Skip to main content

Shallow versus Deep Neural Networks in Gear Fault Diagnosis

  • Giansalvo Cirrincione
  • , Rahul Ranjeev Kumar
  • , Ali Mohammadi
  • , Shahin Hedayati Kia
  • , Pietro Barbiero
  • , Jacopo Ferretti

Research output: Contribution to journal › Article › peer-review

Abstract

Accurate gear defect detection in induction machine based systems is a fundamental issue in several industrial applications. At this aim, shallow neural networks, i.e., architectures with only one hidden layer, have been used after a feature extraction step from vibration, torque, acoustic pressure and electrical signals. Their additional complexity is justified by their ability in
extracting its own features and in the very high-test classification rates. These signals are here analyzed, both geometrically and topologically, in order to estimate the class manifolds and their reciprocal positioning. At this aim, the different states of the gears
are studied by using linear (Pareto charts, biplots, principalangles)
and nonlinear (curvilinear component analysis) techniques, while
the class clusters are visualized by using the parallel coordinates. It
is deduced that the class manifolds are compact and well separated.
This result justifies the use of a shallow neural network, instead
of a deep one, as already remarked in the literature, but with
no theoretical justification. The experimental section confirms this
assertion, and also compares the shallow neural network results
with the other machine learning techniques used in the literature.
Index Terms—Classification algorithm, fault detection, fault
diagnosis, gears, induction motors, multilayer perceptron, neural
networks, principal component analysis, vibrations.
Original languageEnglish
Pages (from-to)1-10
Number of pages10
JournalIEEE Transactions on Energy Conversion
Volume35
Issue number3
DOIs
Publication statusPublished online - 3 Mar 2020

Keywords

  • Classification algorithm
  • fault detection
  • fault diagnosis
  • gears
  • induction motors
  • multilayer perceptron
  • neural networks
  • principal component analysis
  • vibrations

Fingerprint

Dive into the research topics of 'Shallow versus Deep Neural Networks in Gear Fault Diagnosis'. Together they form a unique fingerprint.

Cite this