Noise-Robust Representation for Fault Identification with Limited Data via Data Augmentation

##plugins.themes.bootstrap3.article.main##

##plugins.themes.bootstrap3.article.sidebar##

Published Jun 29, 2022
Zahra Taghiyarrenani Amirhossein Berenji

Abstract

Noise will be unavoidably present in the data collected from physical environments, regardless of how sophisticated the measurement equipment is. Furthermore, collecting enough faulty data is a challenge since operating industrial machines in faulty modes not only has severe consequences to the machine health, but also may affect collateral machinery critically, from health state point of view. In this paper, we propose a method of denoising with limited data for the purpose of fault identification. In addition, our method is capable of removing multiple levels of noise simultaneously. For this purpose, inspired by unsupervised contrastive learning, we first augment the data with multiple levels of noise. Later, we construct a new feature representation using Contrastive Loss. The last step is building a classifier on top of the learned representation; this classifier can detect various faults in noisy environments. The experiments on the SOUTHEAST UNIVERSITY (SEU) dataset of bearings confirm that our method can simultaneously remove multiple noise levels.

How to Cite

Taghiyarrenani, Z., & Berenji, A. . (2022). Noise-Robust Representation for Fault Identification with Limited Data via Data Augmentation. PHM Society European Conference, 7(1), 473–479. https://doi.org/10.36001/phme.2022.v7i1.3334
Abstract 305 | PDF Downloads 218

##plugins.themes.bootstrap3.article.details##

Keywords

Fault identification, data augmentation, unsupervised learning, bearings

Section
Technical Papers