Loading…

Class-relevant feature density estimator for open set fault classification of industrial equipment using vibration signals

Recently, the application of vibration signals to the fault diagnosis of industrial equipment has attracted increased attention. Open set recognition allows deep networks to detect unknown faults while maintaining a high-classification accuracy for known faults, which is necessary for practical indu...

Full description

Saved in:
Bibliographic Details
Published in:Measurement : journal of the International Measurement Confederation 2024-01, Vol.224, p.113806, Article 113806
Main Authors: Mei, Jie, Liu, Wei, Zhu, Ming, Qi, Yongka, Xu, Wenbo, Xu, Hui
Format: Article
Language:English
Subjects:
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Recently, the application of vibration signals to the fault diagnosis of industrial equipment has attracted increased attention. Open set recognition allows deep networks to detect unknown faults while maintaining a high-classification accuracy for known faults, which is necessary for practical industrial applications. Existing distance- and probability-based open set recognition methods show significant potential in handling this challenging task. In this study, we combine a deep backbone network and probabilistic model to construct a class-relevant feature density estimator (CRFDE) that integrates the advantages of distance- and probability-based methods. Specifically, a loss function is developed to enable the backbone network to extract the class-relevant features and probabilistic model to estimate them, where the employed probabilistic model is improved from variational auto-encoder (VAE) to class-conditional VAE (CCVAE) that can estimate the class-conditional data densities. The output class-relevant feature densities of CCVAE are treated as special distances to determine the class belongingness of the input samples. We validated the proposed CRFDE on two public motor bearing datasets and one laboratory gas-insulated switchgear vibration signal dataset. The results revealed that the proposed CRFDE achieved higher F1 scores than the existing methods. •The open set classification task in fault diagnosis is addressed.•A class-relevant feature density estimator that combines a backbone and novel probabilistic CCVAE is proposed.•A novel loss function is developed that jointly enables the backbone network to extract the class-relevant features and CCVAE to estimate them.•Experimental results demonstrate the superior performance of the proposed method.
ISSN:0263-2241
1873-412X
DOI:10.1016/j.measurement.2023.113806