What is it about?
In this paper, we proposed a novel approach based on Gaussian Process (GP) for anomaly detection. Yaw misalignment is used as a case study for this paper. In order to judge GP model effectiveness, two other methods based on binning constructed have been tested and compared with GP based algorithm.
Featured Image
Why is it important?
In this paper, we found that GP model was able to detect the anomaly effectively with the alarm raised only 1.5 hrs. after the fault occurred. Not only is the GP method able to detect the yaw misalignment quickly, but it produces no false positives, in contrast to other binned based models (described in the paper), hence confirming that the GP approach provides both fast and robust fault identification.
Perspectives
Writing this article was a great pleasure as it has co-authors with whom I have had long-standing collaborations.
Dr Ravi Pandit
Cranfield University
Read the Original
This page is a summary of: SCADA based wind turbine anomaly detection using Gaussian Process (GP) models for wind turbine condition monitoring purposes , IET Renewable Power Generation, May 2018, the Institution of Engineering and Technology (the IET),
DOI: 10.1049/iet-rpg.2018.0156.
You can read the full text:
Contributors
The following have contributed to this page
