Modeling and Soft-fault Diagnosis of Underwater Thrusters with Recurrent Neural Networks

TL;DR

This paper evaluates the use of Recurrent Neural Networks for data-driven fault detection and diagnosis in underwater thrusters, addressing challenges posed by soft-faults and model deviations in autonomous underwater vehicles.

Contribution

It introduces an RNN-based scheme for fault diagnosis of underwater thrusters using empirical data, comparing different feature extraction methods.

Findings

RNNs effectively detect soft-faults in underwater thrusters.

Using residuals as features improves fault classification accuracy.

Empirical data validates the proposed fault diagnosis approach.

Abstract

Noncritical soft-faults and model deviations are a challenge for Fault Detection and Diagnosis (FDD) of resident Autonomous Underwater Vehicles (AUVs). Such systems may have a faster performance degradation due to the permanent exposure to the marine environment, and constant monitoring of component conditions is required to ensure their reliability. This works presents an evaluation of Recurrent Neural Networks (RNNs) for a data-driven fault detection and diagnosis scheme for underwater thrusters with empirical data. The nominal behavior of the thruster was modeled using the measured control input, voltage, rotational speed and current signals. We evaluated the performance of fault classification using all the measured signals compared to using the computed residuals from the nominal model as features.