Semi-Supervised Bearing Fault Diagnosis and Classification Using Variational Autoencoder-Based Deep Generative Models

Many industries are evaluating the use of the Internet of Things (IoT) technology to perform remote monitoring and predictive maintenance on their mission-critical assets and equipment, for which mechanical bearings are their indispensable components. Although many data-driven methods have been applied to bearing fault diagnosis, most of them belong to the supervised learning paradigm that requires a large amount of labeled training data to be collected in advance. In practical applications, however, obtaining labeled data that accurately reflect real-time bearing conditions can be more challenging than collecting large amounts of unlabeled data. In this paper, we thus propose a semi-supervised learning scheme for bearing fault diagnosis using variational autoencoder (VAE)-based deep generative models, which can effectively leverage a dataset when only a small subset of data have labels. Finally, a series of experiments were conducted using the University of Cincinnati Intelligent Maintenance System (IMS) Center dataset and the Case Western Reserve University (CWRU) bearing dataset. The experimental results demonstrate that the proposed semi-supervised learning schemes outperformed some mainstream supervised and semi-supervised benchmarks with the same percentage of labeled data samples. Additionally, the proposed methods can mitigate the label inaccuracy issue when identifying naturally-evolved bearing defects.