Smart anomaly detection for Slocum underwater gliders with a variational autoencoder with long short-term memory networks

Bedja-Johnson, Zachary; Wu, Peng; Grande, Davide; Anderlini, Enrico

doi:10.1016/j.apor.2021.103030

Cited by 8 publications

(1 citation statement)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section, the anomaly detection results will be presented in comparison with model-based and rule-based results acquired in [6], [11]. The anomaly detection results will then be applied to annotate the dive cycles of the deployments to train a supervised learning model for fault diagnostics.…”

Section: Resultsmentioning

confidence: 99%

Anomaly Detection and Fault Diagnostics for Underwater Gliders Using Deep Learning

Harris

Salavasidis

et al. 2021

OCEANS 2021: San Diego – Porto

View full text Add to dashboard Cite

Near Real-Time (NRT) anomaly detection and fault diagnostics for underwater gliders are challenging because satellite connections with limited bandwidth allow only decimated data to be sent back from the remote vehicle, whilst on-board systems are constrained by power and computational limits. Currently, anomaly detection and fault diagnostics for such vehicles require intensive monitoring from the operating pilots, which prohibits large scale deployments with multiple vehicles. This paper presents a system with NRT anomaly detection and fault diagnostics for multi-vehicle underwater glider fleets based on Bidirectional Generative Adversarial Networks with assistive hints. The unsupervised anomaly detection system is applied to assist in annotating deployment datasets to train a supervised fault diagnostics model. The results suggest that the anomaly detection system has successfully detected different types of anomalies, validated against model-based and rule-based approaches. In addition, the supervised fault diagnostics system has achieved high fault diagnostics accuracy on the test dataset.

show abstract

Section: Resultsmentioning

confidence: 99%