The Application of Machine Learning and Low Frequency Sonar for Subsea Power Cable Integrity Evaluation

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Subsea power cables are essential assets for the
electrical transmission and distribution networks. They are
crucial in ensuring the security of electricity supply and
supporting the global expansion in offshore renewable energy
generation. After reviewing historical data on subsea cable
failure modes, we established that existing monitoring systems do not account for over 70% of subsea cable failure modes. The
current technologies focus on electrical failure modes and subsea
cable asset management strategies are typically reactive or time
based, with inspection limited to diver and/or ROV supported
video footage which has several limitations, such as requiring
good visibility, access to the cable, challenges in locating the cable
and inability to identify failure modes at the interface of the
seabed. To overcome these limitations, we propose an innovative
sensor technology that can provide the in-situ integrity analysis
of the subsea cable. In this paper, we applied low frequency
sonar technology to undertake detailed and in-situ assessment of
subsea cable integrity. Specifically, in our work, a wideband low
frequency (LF) sonar scanning system is manufactured to collect
acoustic response from different subsea power cable samples
with different inner structure and external failure modes. In
addition, accelerated life cycle testing was conducted by
manually introduce controlled stages of corrosion and abrasion
to the cables to obtain integrity data at various cable degradation
levels.
Seminal results provide a detailed library of LF sonar
responses to cable type and failure mode variations. The results
of preliminary data analysis demonstrate the ability to
distinguish subsea cables by differences in diameter and cable
types and achieve an overall 95%+ accuracy rate to detect
different cable degradation stages.
Original languageEnglish
Title of host publicationOCEANS 2019 Seattle Online Proceedings
PublisherIEEE
Publication statusAccepted/In press - 12 Jul 2019
EventOCEANS 2019 - Seattle, Seattle, United States
Duration: 27 Oct 201931 Oct 2019
https://seattle19.oceansconference.org/

Conference

ConferenceOCEANS 2019
CountryUnited States
CitySeattle
Period27/10/1931/10/19
Internet address

Fingerprint

Sonar
Learning systems
Cables
Failure modes
Remotely operated vehicles
Asset management
Electric power transmission networks
Electric power distribution
Visibility
Life cycle
Electricity
Inspection
Corrosion
Scanning
Degradation

Cite this

@inproceedings{a3084f74cc9546cabc26601d1fabf3ba,
title = "The Application of Machine Learning and Low Frequency Sonar for Subsea Power Cable Integrity Evaluation",
abstract = "Subsea power cables are essential assets for theelectrical transmission and distribution networks. They arecrucial in ensuring the security of electricity supply andsupporting the global expansion in offshore renewable energygeneration. After reviewing historical data on subsea cablefailure modes, we established that existing monitoring systems do not account for over 70{\%} of subsea cable failure modes. Thecurrent technologies focus on electrical failure modes and subseacable asset management strategies are typically reactive or timebased, with inspection limited to diver and/or ROV supportedvideo footage which has several limitations, such as requiringgood visibility, access to the cable, challenges in locating the cableand inability to identify failure modes at the interface of theseabed. To overcome these limitations, we propose an innovativesensor technology that can provide the in-situ integrity analysisof the subsea cable. In this paper, we applied low frequencysonar technology to undertake detailed and in-situ assessment ofsubsea cable integrity. Specifically, in our work, a wideband lowfrequency (LF) sonar scanning system is manufactured to collectacoustic response from different subsea power cable sampleswith different inner structure and external failure modes. Inaddition, accelerated life cycle testing was conducted bymanually introduce controlled stages of corrosion and abrasionto the cables to obtain integrity data at various cable degradationlevels.Seminal results provide a detailed library of LF sonarresponses to cable type and failure mode variations. The resultsof preliminary data analysis demonstrate the ability todistinguish subsea cables by differences in diameter and cabletypes and achieve an overall 95{\%}+ accuracy rate to detectdifferent cable degradation stages.",
author = "Wenshuo Tang and David Flynn and Brown, {Keith Edgar} and Valentin Robu and Xingyu Zhao",
year = "2019",
month = "7",
day = "12",
language = "English",
booktitle = "OCEANS 2019 Seattle Online Proceedings",
publisher = "IEEE",
address = "United States",

}

Tang, W, Flynn, D, Brown, KE, Robu, V & Zhao, X 2019, The Application of Machine Learning and Low Frequency Sonar for Subsea Power Cable Integrity Evaluation. in OCEANS 2019 Seattle Online Proceedings. IEEE, OCEANS 2019, Seattle, United States, 27/10/19.

The Application of Machine Learning and Low Frequency Sonar for Subsea Power Cable Integrity Evaluation. / Tang, Wenshuo; Flynn, David; Brown, Keith Edgar; Robu, Valentin; Zhao, Xingyu.

OCEANS 2019 Seattle Online Proceedings. IEEE, 2019.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - The Application of Machine Learning and Low Frequency Sonar for Subsea Power Cable Integrity Evaluation

AU - Tang, Wenshuo

AU - Flynn, David

AU - Brown, Keith Edgar

AU - Robu, Valentin

AU - Zhao, Xingyu

PY - 2019/7/12

Y1 - 2019/7/12

N2 - Subsea power cables are essential assets for theelectrical transmission and distribution networks. They arecrucial in ensuring the security of electricity supply andsupporting the global expansion in offshore renewable energygeneration. After reviewing historical data on subsea cablefailure modes, we established that existing monitoring systems do not account for over 70% of subsea cable failure modes. Thecurrent technologies focus on electrical failure modes and subseacable asset management strategies are typically reactive or timebased, with inspection limited to diver and/or ROV supportedvideo footage which has several limitations, such as requiringgood visibility, access to the cable, challenges in locating the cableand inability to identify failure modes at the interface of theseabed. To overcome these limitations, we propose an innovativesensor technology that can provide the in-situ integrity analysisof the subsea cable. In this paper, we applied low frequencysonar technology to undertake detailed and in-situ assessment ofsubsea cable integrity. Specifically, in our work, a wideband lowfrequency (LF) sonar scanning system is manufactured to collectacoustic response from different subsea power cable sampleswith different inner structure and external failure modes. Inaddition, accelerated life cycle testing was conducted bymanually introduce controlled stages of corrosion and abrasionto the cables to obtain integrity data at various cable degradationlevels.Seminal results provide a detailed library of LF sonarresponses to cable type and failure mode variations. The resultsof preliminary data analysis demonstrate the ability todistinguish subsea cables by differences in diameter and cabletypes and achieve an overall 95%+ accuracy rate to detectdifferent cable degradation stages.

AB - Subsea power cables are essential assets for theelectrical transmission and distribution networks. They arecrucial in ensuring the security of electricity supply andsupporting the global expansion in offshore renewable energygeneration. After reviewing historical data on subsea cablefailure modes, we established that existing monitoring systems do not account for over 70% of subsea cable failure modes. Thecurrent technologies focus on electrical failure modes and subseacable asset management strategies are typically reactive or timebased, with inspection limited to diver and/or ROV supportedvideo footage which has several limitations, such as requiringgood visibility, access to the cable, challenges in locating the cableand inability to identify failure modes at the interface of theseabed. To overcome these limitations, we propose an innovativesensor technology that can provide the in-situ integrity analysisof the subsea cable. In this paper, we applied low frequencysonar technology to undertake detailed and in-situ assessment ofsubsea cable integrity. Specifically, in our work, a wideband lowfrequency (LF) sonar scanning system is manufactured to collectacoustic response from different subsea power cable sampleswith different inner structure and external failure modes. Inaddition, accelerated life cycle testing was conducted bymanually introduce controlled stages of corrosion and abrasionto the cables to obtain integrity data at various cable degradationlevels.Seminal results provide a detailed library of LF sonarresponses to cable type and failure mode variations. The resultsof preliminary data analysis demonstrate the ability todistinguish subsea cables by differences in diameter and cabletypes and achieve an overall 95%+ accuracy rate to detectdifferent cable degradation stages.

M3 - Conference contribution

BT - OCEANS 2019 Seattle Online Proceedings

PB - IEEE

ER -