Health Indicator for Low-Speed Axial Bearings Using Variational Autoencoders

6533b86cfe1ef96bd12c8c12

RESEARCH PRODUCT

Health Indicator for Low-Speed Axial Bearings Using Variational Autoencoders

Huynh Van Khang Martin Hemmer Tor I. Waag Andreas Klausen Kjell G. Robbersmyr

subject

0209 industrial biotechnology General Computer Science generative models Computer science condition monitoring 02 engineering and technology Latent variable unsupervised learning Fault detection and isolation Bearing fault detection 020901 industrial engineering & automation VDP::Teknologi: 500::Maskinfag: 570 0202 electrical engineering electronic engineering information engineering General Materials Science variational autoencoder conditional variational autoencoder business.industry Dimensionality reduction 020208 electrical & electronic engineering General Engineering Pattern recognition Data point Autoregressive model Rolling-element bearing False alarm Artificial intelligence lcsh:Electrical engineering. Electronics. Nuclear engineering business lcsh:TK1-9971

description

This paper proposes a method for calculating a health indicator (HI) for low-speed axial rolling element bearing (REB) health assessment by utilizing the latent representation obtained by variational inference using Variational Autoencoders (VAEs), trained on each speed reference in the dataset. Further, versatility is added by conditioning on the speed, extending the VAE to a conditional VAE (CVAE), thereby incorporating all speeds in a single model. Within the framework, the coefficients of autoregressive (AR) models are used as features. The dimensionality reduction inherent in the proposed method lowers the need of expert knowledge to design good condition indicators. Moreover, the suggested methodology allows for setting the probability of false alarms when encoding new data points to the latent variable space using the trained model. The effectiveness of the proposed method is validated based on two different datasets: from a workshop test of an offshore drilling machine and from an in-house test rig for axial bearings. In both datasets, the HI is exceeding the warning and alarm levels with a probability of false alarm (PFA) of 10 -6 , and the method is most effective at lower shaft speeds. publishedVersion

year	journal	country	edition	language
2020-01-01	IEEE Access

10.1109/access.2020.2974942 https://ieeexplore.ieee.org/document/9001012/