Ice condition assessment using onboard accelerometers and statistical change detection

Hans-Martin Heyn*, Mogens Blanke, Roger Skjetne

*Corresponding author for this work

Research output: Contribution to journalJournal articleResearchpeer-review

Abstract

The presence of sea ice is the predominant risk for ship operations in the Arctic, and monitoring of ice condition around a vessel is crucial during all times of operation. This paper presents a system for online onboard assessment of ice condition. It is demonstrated that ice-induced accelerations in the bow section of the hull follow a bivariate t-distribution and that parameters of the distribution have a one to one relation to ice condition. The paper suggests a methodology to monitor the ice condition in real time through estimation of parameters that characterise the distribution of hull accelerations. It is shown how a Kullback-Leibler divergence measure can classify ice condition among a set of pre-trained conditions. An absolute measure of ice load is suggested as an alternative for situations when pre-training data are not available. The alternative algorithm quantifies the condition through the entropy of measured accelerations. The article presents a computationally easy methodology and tests against data collected during Arctic transit of an icebreaker. Further, the classification results are compared with the results from two standard methods from machine learning, decision tree and a support vector machine approaches. The results show that the statistical methods provide robust assessment of the prevailing ice conditions, independent of visual and weather conditions. The also comparison shows that the statistical classification methods, designed by process knowledge, provide steadier and more reliable results.
Original languageEnglish
JournalI E E E Journal of Oceanic Engineering
Number of pages20
ISSN0364-9059
DOIs
Publication statusAccepted/In press - 2019

Keywords

  • Arctic
  • Bivariate
  • t-distribution
  • Entropy
  • Generalised log-likelihood ratio
  • IMU
  • Kullback-Leibler divergence
  • Machine learning
  • Ocean engineering
  • Sea ice
  • Ship-ice interaction
  • Statistical change detection

Cite this

@article{8c16c424dade423689ce037ffc454152,
title = "Ice condition assessment using onboard accelerometers and statistical change detection",
abstract = "The presence of sea ice is the predominant risk for ship operations in the Arctic, and monitoring of ice condition around a vessel is crucial during all times of operation. This paper presents a system for online onboard assessment of ice condition. It is demonstrated that ice-induced accelerations in the bow section of the hull follow a bivariate t-distribution and that parameters of the distribution have a one to one relation to ice condition. The paper suggests a methodology to monitor the ice condition in real time through estimation of parameters that characterise the distribution of hull accelerations. It is shown how a Kullback-Leibler divergence measure can classify ice condition among a set of pre-trained conditions. An absolute measure of ice load is suggested as an alternative for situations when pre-training data are not available. The alternative algorithm quantifies the condition through the entropy of measured accelerations. The article presents a computationally easy methodology and tests against data collected during Arctic transit of an icebreaker. Further, the classification results are compared with the results from two standard methods from machine learning, decision tree and a support vector machine approaches. The results show that the statistical methods provide robust assessment of the prevailing ice conditions, independent of visual and weather conditions. The also comparison shows that the statistical classification methods, designed by process knowledge, provide steadier and more reliable results.",
keywords = "Arctic, Bivariate, t-distribution, Entropy, Generalised log-likelihood ratio, IMU, Kullback-Leibler divergence, Machine learning, Ocean engineering, Sea ice, Ship-ice interaction, Statistical change detection",
author = "Hans-Martin Heyn and Mogens Blanke and Roger Skjetne",
year = "2019",
doi = "10.1109/JOE.2019.2899473",
language = "English",
journal = "I E E E Journal of Oceanic Engineering",
issn = "0364-9059",
publisher = "IEEE Oceanic Engineering Society",

}

Ice condition assessment using onboard accelerometers and statistical change detection. / Heyn, Hans-Martin ; Blanke, Mogens; Skjetne, Roger.

In: I E E E Journal of Oceanic Engineering, 2019.

Research output: Contribution to journalJournal articleResearchpeer-review

TY - JOUR

T1 - Ice condition assessment using onboard accelerometers and statistical change detection

AU - Heyn, Hans-Martin

AU - Blanke, Mogens

AU - Skjetne, Roger

PY - 2019

Y1 - 2019

N2 - The presence of sea ice is the predominant risk for ship operations in the Arctic, and monitoring of ice condition around a vessel is crucial during all times of operation. This paper presents a system for online onboard assessment of ice condition. It is demonstrated that ice-induced accelerations in the bow section of the hull follow a bivariate t-distribution and that parameters of the distribution have a one to one relation to ice condition. The paper suggests a methodology to monitor the ice condition in real time through estimation of parameters that characterise the distribution of hull accelerations. It is shown how a Kullback-Leibler divergence measure can classify ice condition among a set of pre-trained conditions. An absolute measure of ice load is suggested as an alternative for situations when pre-training data are not available. The alternative algorithm quantifies the condition through the entropy of measured accelerations. The article presents a computationally easy methodology and tests against data collected during Arctic transit of an icebreaker. Further, the classification results are compared with the results from two standard methods from machine learning, decision tree and a support vector machine approaches. The results show that the statistical methods provide robust assessment of the prevailing ice conditions, independent of visual and weather conditions. The also comparison shows that the statistical classification methods, designed by process knowledge, provide steadier and more reliable results.

AB - The presence of sea ice is the predominant risk for ship operations in the Arctic, and monitoring of ice condition around a vessel is crucial during all times of operation. This paper presents a system for online onboard assessment of ice condition. It is demonstrated that ice-induced accelerations in the bow section of the hull follow a bivariate t-distribution and that parameters of the distribution have a one to one relation to ice condition. The paper suggests a methodology to monitor the ice condition in real time through estimation of parameters that characterise the distribution of hull accelerations. It is shown how a Kullback-Leibler divergence measure can classify ice condition among a set of pre-trained conditions. An absolute measure of ice load is suggested as an alternative for situations when pre-training data are not available. The alternative algorithm quantifies the condition through the entropy of measured accelerations. The article presents a computationally easy methodology and tests against data collected during Arctic transit of an icebreaker. Further, the classification results are compared with the results from two standard methods from machine learning, decision tree and a support vector machine approaches. The results show that the statistical methods provide robust assessment of the prevailing ice conditions, independent of visual and weather conditions. The also comparison shows that the statistical classification methods, designed by process knowledge, provide steadier and more reliable results.

KW - Arctic

KW - Bivariate

KW - t-distribution

KW - Entropy

KW - Generalised log-likelihood ratio

KW - IMU

KW - Kullback-Leibler divergence

KW - Machine learning

KW - Ocean engineering

KW - Sea ice

KW - Ship-ice interaction

KW - Statistical change detection

U2 - 10.1109/JOE.2019.2899473

DO - 10.1109/JOE.2019.2899473

M3 - Journal article

JO - I E E E Journal of Oceanic Engineering

JF - I E E E Journal of Oceanic Engineering

SN - 0364-9059

ER -