Wind Turbine Gearbox Failure Detection Based on SCADA Data : A Deep Learning Based Approach

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review

62 Scopus Citations
View graph of relations

Related Research Unit(s)

Detail(s)

Original languageEnglish
Article number3507911
Journal / PublicationIEEE Transactions on Instrumentation and Measurement
Volume70
Online published18 Dec 2020
Publication statusPublished - 2021

Abstract

Gearbox failure is one of top ranked factors leading to the unavailability of wind turbines. Existing data-driven studies of gearbox failure detection (GFD) focuses on improving detection accuracies while reducing false alarms has not received sufficient discussions. In this paper, we propose a deep joint variational autoencoder (JVAE) based monitoring method using wind farm supervisory control and data acquisition (SCADA) data to more effectively detect wind turbine gearbox failures. The JVAE based monitoring method includes two parts. First, a novel JVAE which takes a chunk of multivariate time series derived from collected SCADA data as inputs is developed. The JVAE utilizes two types of pre-defined parameters, behavior parameters (BPs) and conditional parameters (CPs), to produce reconstruction errors (REs) of the BP, which reflects the gearbox abnormality. Next, a statistical process control chart is developed to monitor REs and raise alarms. To validate advantages of the proposed method in GFD, five methods, the joint latent variational autoencoder (JLVAE) based, the variational autoencoder (VAE) based, full dimensional VAE (FDVAE) based, recurrent autoencoder (RAE) based, and one-class support vector machine (OCSVM) based monitoring methods, are considered as benchmarks. SCADA data with field reports of gearbox failure events collected from four commercial wind farms are utilized to demonstrate the effectiveness of the JVAE based monitoring method on GFD and its stronger ability of resisting false alarms.

Research Area(s)

  • anomaly detection, autoencoders, data mining, wind energy, wind turbine gearbox