Anomaly detection techniques for the condition monitoring of tidal turbines

Grant Galloway, Victoria Catterson, Craig Love, Andrew Robb

Research output: Contribution to conferencePaper

2 Citations (Scopus)

Abstract

Harnessing the power of currents from the sea bed, tidal power has great potential to provide a means of renewable energy generation more predictable than similar technologies such as wind power. However, the nature of the operating environment provides challenges, with maintenance requiring a lift operation to gain access to the turbine above water. Failures of system components can therefore result in prolonged periods of downtime while repairs are completed on the surface, removing the system’s ability to produce electricity and damaging revenues. The utilization of effective condition monitoring systems can therefore prove particularly beneficial to this industry.

This paper explores the use of the CRISP-DM data mining process model for identifying key trends within turbine sensor data, to define the expected response of a tidal turbine. Condition data from an operational 1 MW turbine, installed off the coast of Orkney, Scotland, was used for this study. The effectiveness of modeling techniques, including curve fitting, Gaussian mixture modeling, and density estimation are explored, using tidal turbine data in the absence of faults. The paper shows how these models can be used for anomaly detection of live turbine data, with anomalies indicating the possible onset of a fault within the
system.

Conference

ConferenceAnnual Conference of the Prognostics and Health Management Society 2014 (PHM)
CountryUnited States
CityFort Worth
Period29/09/142/10/14

Fingerprint

Condition monitoring
Turbines
Tidal power
Curve fitting
Wind power
Data mining
Coastal zones
Repair
Electricity
Sensors
Water
Industry

Keywords

  • tidal power
  • renewable energy
  • tidal turbine maintenance
  • turbine sensor data

Cite this

Galloway, G., Catterson, V., Love, C., & Robb, A. (2014). Anomaly detection techniques for the condition monitoring of tidal turbines. Paper presented at Annual Conference of the Prognostics and Health Management Society 2014 (PHM), Fort Worth, United States.
Galloway, Grant ; Catterson, Victoria ; Love, Craig ; Robb, Andrew. / Anomaly detection techniques for the condition monitoring of tidal turbines. Paper presented at Annual Conference of the Prognostics and Health Management Society 2014 (PHM), Fort Worth, United States.12 p.
@conference{21212aae452f4da5b28e36bcb747b9ff,
title = "Anomaly detection techniques for the condition monitoring of tidal turbines",
abstract = "Harnessing the power of currents from the sea bed, tidal power has great potential to provide a means of renewable energy generation more predictable than similar technologies such as wind power. However, the nature of the operating environment provides challenges, with maintenance requiring a lift operation to gain access to the turbine above water. Failures of system components can therefore result in prolonged periods of downtime while repairs are completed on the surface, removing the system’s ability to produce electricity and damaging revenues. The utilization of effective condition monitoring systems can therefore prove particularly beneficial to this industry.This paper explores the use of the CRISP-DM data mining process model for identifying key trends within turbine sensor data, to define the expected response of a tidal turbine. Condition data from an operational 1 MW turbine, installed off the coast of Orkney, Scotland, was used for this study. The effectiveness of modeling techniques, including curve fitting, Gaussian mixture modeling, and density estimation are explored, using tidal turbine data in the absence of faults. The paper shows how these models can be used for anomaly detection of live turbine data, with anomalies indicating the possible onset of a fault within thesystem.",
keywords = "tidal power, renewable energy, tidal turbine maintenance, turbine sensor data",
author = "Grant Galloway and Victoria Catterson and Craig Love and Andrew Robb",
year = "2014",
month = "9",
language = "English",
note = "Annual Conference of the Prognostics and Health Management Society 2014 (PHM) ; Conference date: 29-09-2014 Through 02-10-2014",

}

Galloway, G, Catterson, V, Love, C & Robb, A 2014, 'Anomaly detection techniques for the condition monitoring of tidal turbines' Paper presented at Annual Conference of the Prognostics and Health Management Society 2014 (PHM), Fort Worth, United States, 29/09/14 - 2/10/14, .

Anomaly detection techniques for the condition monitoring of tidal turbines. / Galloway, Grant; Catterson, Victoria; Love, Craig; Robb, Andrew.

2014. Paper presented at Annual Conference of the Prognostics and Health Management Society 2014 (PHM), Fort Worth, United States.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Anomaly detection techniques for the condition monitoring of tidal turbines

AU - Galloway, Grant

AU - Catterson, Victoria

AU - Love, Craig

AU - Robb, Andrew

PY - 2014/9

Y1 - 2014/9

N2 - Harnessing the power of currents from the sea bed, tidal power has great potential to provide a means of renewable energy generation more predictable than similar technologies such as wind power. However, the nature of the operating environment provides challenges, with maintenance requiring a lift operation to gain access to the turbine above water. Failures of system components can therefore result in prolonged periods of downtime while repairs are completed on the surface, removing the system’s ability to produce electricity and damaging revenues. The utilization of effective condition monitoring systems can therefore prove particularly beneficial to this industry.This paper explores the use of the CRISP-DM data mining process model for identifying key trends within turbine sensor data, to define the expected response of a tidal turbine. Condition data from an operational 1 MW turbine, installed off the coast of Orkney, Scotland, was used for this study. The effectiveness of modeling techniques, including curve fitting, Gaussian mixture modeling, and density estimation are explored, using tidal turbine data in the absence of faults. The paper shows how these models can be used for anomaly detection of live turbine data, with anomalies indicating the possible onset of a fault within thesystem.

AB - Harnessing the power of currents from the sea bed, tidal power has great potential to provide a means of renewable energy generation more predictable than similar technologies such as wind power. However, the nature of the operating environment provides challenges, with maintenance requiring a lift operation to gain access to the turbine above water. Failures of system components can therefore result in prolonged periods of downtime while repairs are completed on the surface, removing the system’s ability to produce electricity and damaging revenues. The utilization of effective condition monitoring systems can therefore prove particularly beneficial to this industry.This paper explores the use of the CRISP-DM data mining process model for identifying key trends within turbine sensor data, to define the expected response of a tidal turbine. Condition data from an operational 1 MW turbine, installed off the coast of Orkney, Scotland, was used for this study. The effectiveness of modeling techniques, including curve fitting, Gaussian mixture modeling, and density estimation are explored, using tidal turbine data in the absence of faults. The paper shows how these models can be used for anomaly detection of live turbine data, with anomalies indicating the possible onset of a fault within thesystem.

KW - tidal power

KW - renewable energy

KW - tidal turbine maintenance

KW - turbine sensor data

UR - http://www.phmsociety.org/node/1390

UR - http://www.phmsociety.org/events/conference/phm/14

M3 - Paper

ER -

Galloway G, Catterson V, Love C, Robb A. Anomaly detection techniques for the condition monitoring of tidal turbines. 2014. Paper presented at Annual Conference of the Prognostics and Health Management Society 2014 (PHM), Fort Worth, United States.