Please use this identifier to cite or link to this item:
Publication type: Conference paper
Type of review: Peer review (publication)
Title: Early fault detection based on wind turbine SCADA data using convolutional neural networks
Authors: Ulmer, Markus
Jarlskog, Eskil
Pizza, Gianmarco
Manninen, Jaakko
Goren Huber, Lilach
et. al: No
DOI: 10.21256/zhaw-20433
Proceedings: PHME 2020 : Proceedings of the 5th European Conference of the PHM Society
Volume(Issue): 5
Issue: 1
Conference details: 5th European Conference of the Prognostics and Health Management Society, Virtual Conference, 27-31 July 2020
Issue Date: Jul-2020
Publisher / Ed. Institution: PHM Society
ISBN: 978-1-936263-32-5
Language: English
Subjects: Fault detection; Fault diagnostics; Predictive maintenance; Wind turbines; Machine learning; Deep learning; Convolutional neural networks
Subject (DDC): 006: Special computer methods
Abstract: Early fault detection in wind turbines using the widely available SCADA data has been receiving growing interest due to its cost-effectiveness. As opposed to the large variety of fault detection methods based on high resolusion vibration data, the use of 10-minute SCADA data alone does not require any additional hardware or data storage solutions and would be immediately implementable in most wind farms. However, the strong variability of these data is challenging and requires significant improvements of existing methods to ensure early and reliable fault detection and isolation. Here we suggest to use Convolutional Neural Networks (CNNs) to enhance the detection accuracy and robustness. We demonstrate the superiority of the CNN model over standard fully connected neural networks (FCNN) using examples for faults with very different time dependent characteristics: an abruptly evolving and a slowly degrading fault. We show that the CNN is able to detect the faults earlier and with a higher accuracy and robustness of prediction than the FCNN model. We then extend the CNN model to a multi-output CNN (CNNm) which provides early fault detection based on a multitude of output variables simultaneously. We show that with the same training time and a similar detection quality as the single output CNN, the CNNm model is an ideal candidate for a practical and scalable fault detection algorithm based on already available 10-minute SCADA data for wind turbines.
Fulltext version: Published version
License (according to publishing contract): CC BY 3.0: Attribution 3.0 Unported
Departement: School of Engineering
Organisational Unit: Institute of Data Analysis and Process Design (IDP)
Published as part of the ZHAW project: Machine Learning Based Fault Detection for Wind Turbines
Appears in collections:Publikationen School of Engineering

Files in This Item:
File Description SizeFormat 
2020_Ulmer_etal_Early-fault-detection_PHM-Society.pdf1.41 MBAdobe PDFThumbnail

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.