Testing Topological Data Analysis for Condition Monitoring of Wind Turbines

##plugins.themes.bootstrap3.article.main##

##plugins.themes.bootstrap3.article.sidebar##

Published Jun 27, 2024
Simone Casolo
Alexander Stasik Zhenyou Zhang
Signe Riemer-Sørensen

Abstract

We present an investigation of how topological data analysis (TDA) can be applied to condition-based monitoring (CBM) of wind turbines for energy generation.
TDA is a branch of data analysis focusing on extracting mean- ingful information from complex datasets by analyzing their structure in state space and computing their underlying topo- logical features. By representing data in a high-dimensional state space, TDA enables the identification of patterns, anoma- lies, and trends in the data that may not be apparent through traditional signal processing methods.

For this study, wind turbine data was acquired from a wind park in Norway via standard vibration sensors at different lo- cations of the turbine’s gearbox. Both the vibration acceler- ation data and its frequency spectra were recorded at infre- quent intervals for a few seconds at high frequency and fail- ure events were labelled as either gear-tooth or ball-bearing failures. The data processing and analysis are based on a pipeline where the time series data is first split into intervals and then transformed into multi-dimensional point clouds via a time-delay embedding. The shape of the point cloud is an- alyzed with topological methods such as persistent homol- ogy to generate topology-based key health indicators based on Betti numbers, information entropy and signal persistence. Such indicators are tested for CBM and diagnosis (fault de- tection) to identify faults in wind turbines and classify them accordingly. Topological indicators are shown to be an in- teresting alternative for failure identification and diagnosis of operational failures in wind turbines.

How to Cite

Casolo, S., Stasik, A., Zhang, Z., & Riemer-Sørensen, S. (2024). Testing Topological Data Analysis for Condition Monitoring of Wind Turbines. PHM Society European Conference, 8(1), 10. https://doi.org/10.36001/phme.2024.v8i1.4117
Abstract 463 | PDF Downloads 273

##plugins.themes.bootstrap3.article.details##

Keywords
References
Section