Vibration fault detection in wind turbines based on normal behaviour models without feature engineering

TL;DR

This paper introduces a feature-engineering-free fault detection method for wind turbine vibrations using convolutional autoencoders to learn normal spectral responses, enabling effective damage identification without manual feature extraction.

Contribution

The novel approach applies convolutional autoencoders to automatically learn spectral features of normal vibrations, simplifying implementation and improving fault detection in wind turbines.

Findings

Successfully detects damaged components in turbines

Operates without manual feature engineering

Effective on real turbine and test rig data

Abstract

Most wind turbines are remotely monitored 24/7 to allow for an early detection of operation problems and developing damage. We present a new fault detection method for vibration-monitored drivetrains that does not require any feature engineering. Our method relies on a simple model architecture to enable a straightforward implementation in practice. We propose to apply convolutional autoencoders for identifying and extracting the most relevant features from the half spectrum in an automated manner, saving time and effort. Thereby, a spectral model of the normal vibration response is learnt for the monitored component from past measurements. We demonstrate that the model can successfully distinguish damaged from healthy components and detect a damaged generator bearing and damaged gearbox parts from their vibration responses. Using measurements from commercial wind turbines and a test rig, we show that vibration-based fault detection in wind turbine drivetrains can be performed without the usual upfront definition of spectral features. Another advantage of the presented method is that the entire half spectrum is monitored instead of the usual focus on monitoring individual frequencies and harmonics.