Machine Learning Based Fault Detection for Wind Turbines
Description
Nispera is a third-party energy forecasting and performance monitoring solution provider for renewable energy assets. In this project we develop a new software module for condition-based and predictive maintenance for the main components of wind turbines and integrate it in the existing platform of Nispera. For this purpose we develop state of the art machine learning algorithms for early fault detection and isolation in critical turbine components. Early detection enables wind farm owners to schedule maintenance in a planned manner before a complete stoppage of the turbine, thus avoiding long downtimes and the related high costs. The cost effectiveness of this software solution is due to the fact that the required data is recorded and stored by the Supervisory Control And Data Acquisition (SCADA) system which is already present on all wind farms and thus does not require any additional investment by the Owner. We develop a framework to combine time series data together with error log data in order to enhance the precision and robustness of the fault detection algorithms and allow for their generalization to various operating conditions and equipment manufacturers.
Key Data
Projectlead
Project team
Markus Ulmer, Jannik Zgraggen
Project partners
Nispera AG
Project status
completed, 11/2018 - 05/2021
Funding partner
Innovationsprojekt / Projekt Nr. 32513.1 IP-ICT
Publications
-
Uncertainty informed anomaly scores with deep learning : robust fault detection with limited data
2022 Zgraggen, Jannik; Pizza, Gianmarco; Goren Huber, Lilach
-
Scaling-up deep learning based predictive maintenance for commercial machine fleets : a case study
2022 Ulmer, Markus; Zgraggen, Jannik; Pizza, Gianmarco; Goren Huber, Lilach
-
Transfer learning approaches for wind turbine fault detection using deep learning
2021 Zgraggen, Jannik; Ulmer, Markus; Jarlskog, Eskil; Pizza, Gianmarco; Goren Huber, Lilach
-
Deep learning for fault detection : the path to predictive maintenance of wind turbines
2021 Ulmer, Markus; Jarlskog, Eskil; Pizza, Gianmarco; Goren Huber, Lilach
-
Deep Learning und Predictive Maintenance : Anwendungsfall Windturbinen
2021 Goren Huber, Lilach; Pizza, Gianmarco
-
Implementing AI-based innovation in industry
2021 Goren Huber, Lilach; Acquaviva, Michele; Pizza, Gianmarco
-
Implementing smart maintenance in industry : deep learning for wind turbine fault detection
2021 Goren Huber, Lilach
-
Early fault detection based on wind turbine SCADA data using convolutional neural networks
2020 Ulmer, Markus; Jarlskog, Eskil; Pizza, Gianmarco; Manninen, Jaakko; Goren Huber, Lilach
-
Cross-turbine training of convolutional neural networks for SCADA-based fault detection in wind turbines
2020 Ulmer, Markus; Jarlskog, Eskil; Pizza, Gianmarco; Goren Huber, Lilach
-
An AI-based fault detection model using alarms and warnings from the SCADA system
2020 Pizza, Gianmarco; Notaristefano, Antonio; Fabbri, Gregory Sean; Goren Huber, Lilach
Technikumstrasse 81
8400 Winterthur