Machines: Probabilistic Condition Monitoring of Azimuth Thrusters Based On Acceleration Measurements

machines
Article
Probabilistic Condition Monitoring of Azimuth Thrusters
Based on Acceleration Measurements
Riku-Pekka Nikula 1, * , Mika Ruusunen 1 , Joni Keski-Rahkonen 2 , Lars Saarinen 2 and Fredrik Fagerholm 2
1 Control Engineering, Environmental and Chemical Engineering, University of Oulu, P.O. Box 4300,
90014 Oulu, Finland; mika.ruusunen@oulu.fi
2 Kongsberg Maritime Finland Oy, P.O. Box 220, 26101 Rauma, Finland;
[email protected] (J.K.-R.); [email protected] (L.S.);
[email protected] (F.F.)
* Correspondence: riku-pekka.nikula@oulu.fi; Tel.: +358-50-350-5993
Abstract: Drill ships and offshore rigs use azimuth thrusters for propulsion, maneuvering and
steering, attitude control and dynamic positioning activities. The versatile operating modes and
the challenging marine environment create demand for flexible and practical condition monitoring
solutions onboard. This study introduces a condition monitoring algorithm using acceleration and
shaft speed data to detect anomalies that give information on the defects in the driveline components
of the thrusters. Statistical features of vibration are predicted with linear regression models and the
residuals are then monitored relative to multivariate normal distributions. The method includes an
automated shaft speed selection approach that identifies the normal distributed operational areas
from the training data based on the residuals. During monitoring, the squared Mahalanobis distance
to the identified distributions is calculated in the defined shaft speed ranges, providing information
on the thruster condition. The performance of the method was validated based on data from two
��
�� operating thrusters and compared with reference classifiers. The results suggest that the method
Citation: Nikula, R.-P.; Ruusunen,
could detect changes in the condition of the thrusters during online monitoring. Moreover, it had
M.; Keski-Rahkonen, J.; Saarinen, L.; high accuracy in the bearing condition related binary classification tests. In conclusion, the algorithm
Fagerholm, F. Probabilistic Condition has practical properties that exhibit suitability for online application.
Monitoring of Azimuth Thrusters
Based on Acceleration Measurements. Keywords: anomaly detection; azimuth thruster; classification; feature extraction; linear regression;
Machines 2021, 9, 39. https:// multivariate normal distribution; noisy data; vibration
doi.org/10.3390/machines9020039
Academic Editor: Hamid Reza Karimi

Received: 23 December 2020 1. Introduction
Accepted: 8 February 2021
Azimuth thrusters are used for propulsion systems and dynamic positioning (DP)
Published: 10 February 2021
of offshore platforms and vessels. In a drill ship, the thrusters are used to maintain the
ship position by counteracting environmental forces, such as wind, waves and current, but
Publisher’s Note: MDPI stays neutral
with regard to jurisdictional claims in
also for propulsion in transit from site to site. The environmental forces, the impacts with
published maps and institutional affil-
external objects like ice blocks, propeller operation, the pulsation from prime movers and
iations.
accessory systems together inflict complex vibrations and stress to the system [1]. Over the
long haul, the stress caused by the harsh environment may lead to fatigue, fracture and
tribological issues in the system [2,3]. This inflicts damage to gears and bearings, but also
other types of issues, such as propeller failures emerge [4].
The measurement technology for the condition monitoring (CM) of the azimuth
Copyright: © 2021 by the authors.
thrusters must be economically viable, maintenance-free and reliable due to the closed and
Licensee MDPI, Basel, Switzerland.
inaccessible construction. Therefore, the driveline components, such as the rolling element
This article is an open access article
distributed under the terms and
bearings and gears, are commonly monitored with the well-established indirect methods,
conditions of the Creative Commons
such as piezoelectric accelerometers or oil condition and wear debris sensors [5].
Attribution (CC BY) license (https:// Although the vibration responses of propulsion shafts are studied regularly based
creativecommons.org/licenses/by/ on laboratory experiments and simulations [1,6], the literature on the practical condition
4.0/). monitoring of azimuth thrusters is rare [2,3]. At the same time, the CM methods for
Machines 2021, 9, 39. https://doi.org/10.3390/machines9020039 https://www.mdpi.com/journal/machines

Machines: Probabilistic Condition Monitoring of Azimuth Thrusters Based On Acceleration Measurements

Uploaded by

Copyright:

Available Formats

Machines: Probabilistic Condition Monitoring of Azimuth Thrusters Based On Acceleration Measurements

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Machines: Probabilistic Condition Monitoring of Azimuth Thrusters Based On Acceleration Measurements

Uploaded by

Copyright:

Available Formats

machines

Academic Editor: Hamid Reza Karimi

Machines 2021, 9, 39. https://doi.org/10.3390/machines9020039 https://www.mdpi.com/journal/machines

You might also like