Data-driven online monitoring of wind turbines

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademicpeer review

Uittreksel

Condition based maintenance is a modern approach to maintenance which has been successfully used in several industrial sectors. A specific problem in wind turbine maintenance is that failures of certain parts may be caused by the malperformance or failure of other parts. This mandates for approaches that can produce timely warnings by combining sensor data from different sources. More concretely, in this paper, we present a hybrid statistical approach to condition based maintenance by combining regression analysis with tools from statistical process control. Our approach improves the wind turbine maintenance practice by using adaptive alarm thresholds for the monitored parameters, whilst correcting for environmental factors or for other relevant parameters. We illustrate our approach with a case study demonstrating that we are able to predict upcoming failures much earlier than the current practice.

TaalEngels
TitelProceedings of the 12th EAI International Conference on Performance Evaluation Methodologies and Tools, VALUETOOLS 2019
UitgeverijAssociation for Computing Machinery, Inc
Pagina's143-150
Aantal pagina's8
ISBN van elektronische versie9781450365963
DOI's
StatusGepubliceerd - 12 mrt 2019
Evenement12th EAI International Conference on Performance Evaluation Methodologies and Tools, (VALUETOOLS 2019) - Palma de Mallorca, Spanje
Duur: 13 mrt 201915 mrt 2019

Congres

Congres12th EAI International Conference on Performance Evaluation Methodologies and Tools, (VALUETOOLS 2019)
Verkorte titelVALUETOOLS2019
LandSpanje
StadPalma de Mallorca
Periode13/03/1915/03/19

Vingerafdruk

Wind turbines
Monitoring
Statistical process control
Regression analysis
Sensors

Trefwoorden

    Citeer dit

    Kenbeek, T., Kapodistria, S., & Di Bucchianico, A. (2019). Data-driven online monitoring of wind turbines. In Proceedings of the 12th EAI International Conference on Performance Evaluation Methodologies and Tools, VALUETOOLS 2019 (blz. 143-150). Association for Computing Machinery, Inc. DOI: 10.1145/3306309.3306330
    Kenbeek, Thomas ; Kapodistria, Stella ; Di Bucchianico, Alessandro. / Data-driven online monitoring of wind turbines. Proceedings of the 12th EAI International Conference on Performance Evaluation Methodologies and Tools, VALUETOOLS 2019. Association for Computing Machinery, Inc, 2019. blz. 143-150
    @inproceedings{b10484eccd1a43cc9f44bb0f7cb6853a,
    title = "Data-driven online monitoring of wind turbines",
    abstract = "Condition based maintenance is a modern approach to maintenance which has been successfully used in several industrial sectors. A specific problem in wind turbine maintenance is that failures of certain parts may be caused by the malperformance or failure of other parts. This mandates for approaches that can produce timely warnings by combining sensor data from different sources. More concretely, in this paper, we present a hybrid statistical approach to condition based maintenance by combining regression analysis with tools from statistical process control. Our approach improves the wind turbine maintenance practice by using adaptive alarm thresholds for the monitored parameters, whilst correcting for environmental factors or for other relevant parameters. We illustrate our approach with a case study demonstrating that we are able to predict upcoming failures much earlier than the current practice.",
    keywords = "Condition based monitoring, Control charts, Regression analysis, Wind turbine",
    author = "Thomas Kenbeek and Stella Kapodistria and {Di Bucchianico}, Alessandro",
    year = "2019",
    month = "3",
    day = "12",
    doi = "10.1145/3306309.3306330",
    language = "English",
    pages = "143--150",
    booktitle = "Proceedings of the 12th EAI International Conference on Performance Evaluation Methodologies and Tools, VALUETOOLS 2019",
    publisher = "Association for Computing Machinery, Inc",
    address = "United States",

    }

    Kenbeek, T, Kapodistria, S & Di Bucchianico, A 2019, Data-driven online monitoring of wind turbines. in Proceedings of the 12th EAI International Conference on Performance Evaluation Methodologies and Tools, VALUETOOLS 2019. Association for Computing Machinery, Inc, blz. 143-150, Palma de Mallorca, Spanje, 13/03/19. DOI: 10.1145/3306309.3306330

    Data-driven online monitoring of wind turbines. / Kenbeek, Thomas; Kapodistria, Stella; Di Bucchianico, Alessandro.

    Proceedings of the 12th EAI International Conference on Performance Evaluation Methodologies and Tools, VALUETOOLS 2019. Association for Computing Machinery, Inc, 2019. blz. 143-150.

    Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademicpeer review

    TY - GEN

    T1 - Data-driven online monitoring of wind turbines

    AU - Kenbeek,Thomas

    AU - Kapodistria,Stella

    AU - Di Bucchianico,Alessandro

    PY - 2019/3/12

    Y1 - 2019/3/12

    N2 - Condition based maintenance is a modern approach to maintenance which has been successfully used in several industrial sectors. A specific problem in wind turbine maintenance is that failures of certain parts may be caused by the malperformance or failure of other parts. This mandates for approaches that can produce timely warnings by combining sensor data from different sources. More concretely, in this paper, we present a hybrid statistical approach to condition based maintenance by combining regression analysis with tools from statistical process control. Our approach improves the wind turbine maintenance practice by using adaptive alarm thresholds for the monitored parameters, whilst correcting for environmental factors or for other relevant parameters. We illustrate our approach with a case study demonstrating that we are able to predict upcoming failures much earlier than the current practice.

    AB - Condition based maintenance is a modern approach to maintenance which has been successfully used in several industrial sectors. A specific problem in wind turbine maintenance is that failures of certain parts may be caused by the malperformance or failure of other parts. This mandates for approaches that can produce timely warnings by combining sensor data from different sources. More concretely, in this paper, we present a hybrid statistical approach to condition based maintenance by combining regression analysis with tools from statistical process control. Our approach improves the wind turbine maintenance practice by using adaptive alarm thresholds for the monitored parameters, whilst correcting for environmental factors or for other relevant parameters. We illustrate our approach with a case study demonstrating that we are able to predict upcoming failures much earlier than the current practice.

    KW - Condition based monitoring

    KW - Control charts

    KW - Regression analysis

    KW - Wind turbine

    UR - http://www.scopus.com/inward/record.url?scp=85062827080&partnerID=8YFLogxK

    U2 - 10.1145/3306309.3306330

    DO - 10.1145/3306309.3306330

    M3 - Conference contribution

    SP - 143

    EP - 150

    BT - Proceedings of the 12th EAI International Conference on Performance Evaluation Methodologies and Tools, VALUETOOLS 2019

    PB - Association for Computing Machinery, Inc

    ER -

    Kenbeek T, Kapodistria S, Di Bucchianico A. Data-driven online monitoring of wind turbines. In Proceedings of the 12th EAI International Conference on Performance Evaluation Methodologies and Tools, VALUETOOLS 2019. Association for Computing Machinery, Inc. 2019. blz. 143-150. Beschikbaar vanaf, DOI: 10.1145/3306309.3306330