1. ZHAW digitalcollection
2. School of Engineering
3. Publikationen
4. Publikationen School of Engineering

Publikationstyp:	Konferenz: Sonstiges
Art der Begutachtung:	Keine Angabe
Titel:	Implementing AI-based innovation in industry
Autor/-in:	Goren Huber, Lilach Acquaviva, Michele Pizza, Gianmarco
et. al:	No
Angaben zur Konferenz:	Live-Case-Workshop for EMBA Digital Transformation, University Zurich, 6 July 2021
Erscheinungsdatum:	6-Jul-2021
Sprache:	Englisch
Schlagwörter:	Artificial intelligence; Industry; Innovation; Data science; Deep learning; Machine learning; Predictive maintenance
Fachgebiet (DDC):	006: Spezielle Computerverfahren 620: Ingenieurwesen
Zusammenfassung:	The Supervisory Control and Data Acquisition (SCADA) system installed on every wind turbine collects performance and condition data from various components of the turbine in time intervals of 10 minutes. The data is stored and has been used primarily for performance monitoring (identifying losses in the power production) until now. Realizing that this vast amount of historical data from all turbines has a much bigger potential, Nispera decided to launch an innovation project to harvest this potential and offer its clients a new platform for automated detection and localization of technical anomalies and faults in various turbine components. Early detection of faults allows for an intelligent planning of maintenance activities, leading to considerable reduction in the Operation and Maintenance (O&M) expenses of the wind farm operator. “Predictive maintenance” approaches start to replace reactive and preventive approaches to maintenance in a large variety of application fields, ranging from the aircraft industry, through trains, large production machines and public infrastructures. Deploying predictive maintenance algorithms is becoming increasingly attractive owing to the huge progress of the last years regarding machine data availability, cost-effective storage solutions and efficient intelligent algorithms for data analytics, including machine learning and deep learning methods. For Nispera’s clients, predictive maintenance is even more attractive because this service is offered within a more generic platform, which has access to the SCADA data without the need for any new hardware installation. This makes Nispera’s solution cost-effective com-pared to other condition monitoring solutions available on the market. In this way, Nispera directly addresses the needs of wind park owners and operators for continuous monitoring of their turbines, independent of the OEMs.
URI:	https://digitalcollection.zhaw.ch/handle/11475/22923
Volltext Version:	Publizierte Version
Lizenz (gemäss Verlagsvertrag):	Lizenz gemäss Verlagsvertrag
Departement:	School of Engineering
Organisationseinheit:	Institut für Datenanalyse und Prozessdesign (IDP)
Publiziert im Rahmen des ZHAW-Projekts:	Machine Learning Based Fault Detection for Wind Turbines
Enthalten in den Sammlungen:	Publikationen School of Engineering

Alle Ressourcen in diesem Repository sind urheberrechtlich geschützt, soweit nicht anderweitig angezeigt.