Prognosis of a Wind Turbine Gearbox Bearing Using Supervised Machine Learning

Elasha Elasha,Shanbr Shanbr,Li Li,Mba Mba

doi:10.3390/s19143092

Elasha Elasha, Shanbr Shanbr + Show 2 more

Open Access

https://doi.org/10.3390/s19143092

Copy DOI

Abstract

Deployment of large-scale wind turbines requires sophisticated operation and maintenance strategies to ensure the devices are safe, profitable and cost-effective. Prognostics aims to predict the remaining useful life (RUL) of physical systems based on condition measurements. Analyzing condition monitoring data, implementing diagnostic techniques and using machinery prognostic algorithms will bring about accurate estimation of the remaining life and possible failures that may occur. This paper proposes to combine two supervised machine learning techniques, namely, regression model and multilayer artificial neural network model, to predict the RUL of an operational wind turbine gearbox using vibration measurements. Root Mean Square (RMS), Kurtosis (KU) and Energy Index (EI) were analysed to define the bearing failure stages. The proposed methodology was evaluated through a case study involving vibration measurements of a high-speed shaft bearing used in a wind turbine gearbox.

Highlights

The continuous monitoring of wind turbine systems and their constituent components can be the most effective way to eliminate unplanned maintenance and increase availability
This study aims to ascertain the feasibility of artificial neural network (ANN) models to predict the remaining useful life (RUL) of rolling element bearings used in real-world applications, and to explore the possibility of combining regression models with ANNs to form a better prognostic model
A data-driven prognostic method has been developed and tested using vibration signals collected from an operational wind turbine gearbox

Summary

Introduction

The continuous monitoring of wind turbine systems and their constituent components (e.g., drive trains, generators and blades) can be the most effective way to eliminate unplanned maintenance and increase availability. Wind turbine systems are operating under adverse condition, such as vastly varying speeds, loads and temperatures. Bearings in wind turbine systems generally operate under adverse conditions such as chemical effects of lubricant, contamination and moisture, as a result, bearings are subject to performance degradation if no preventive actions are taken. The high demands for renewable energy resources has resulted in further demands on wind turbines availability and reliability, especially on the key components such as the gearbox and bearings [1]. A gearbox is one of the most important units in the drive train system of a wind turbine. A gear box consists of gears, bearings and shafts that are subject to continual variable operational speed and loads

Objectives

Methods

Results

Conclusion