Generative Adversarial Networks Selection Approach for Extremely Imbalanced Fault Diagnosis of Reciprocating Machinery

Diego Cabrera, Fernando Sancho, Jianyu Long, Rene Vinicio Sanchez, Shaohui Zhang, Mariela Cerrada, Chuan Li

Research output: Contribution to journalArticlepeer-review

22 Scopus citations

Abstract

At present, countless approaches to fault diagnosis in reciprocating machines have been proposed, all considering that the available machinery dataset is in equal proportions for all conditions. However, when the application is closer to reality, the problem of data imbalance is increasingly evident. In this paper, we propose a method for the creation of diagnoses that consider an extreme imbalance in the available data. Our approach first processes the vibration signals of the machine using a wavelet packet transform-based feature-extraction stage. Then, improved generative models are obtained with a dissimilarity-based model selection to artificially balance the dataset. Finally, a Random Forest classifier is created to address the diagnostic task. This methodology provides a considerable improvement with 99% of data imbalance over other approaches reported in the literature, showing performance similar to that obtained with a balanced set of data.

Original languageEnglish
Article number8718595
Pages (from-to)70643-70653
Number of pages11
JournalIEEE Access
Volume7
DOIs
StatePublished - 1 Jan 2019

Keywords

  • GAN
  • Imbalanced data
  • model selection
  • random Forest
  • reciprocating machinery

Fingerprint

Dive into the research topics of 'Generative Adversarial Networks Selection Approach for Extremely Imbalanced Fault Diagnosis of Reciprocating Machinery'. Together they form a unique fingerprint.

Cite this