2024
Maestro-Prieto, Jose Alberto; Ramírez-Sanz, José Miguel; Andrés Bustillo, and Juan José Rodriguez-Díez
Semi-supervised diagnosis of wind-turbine gearbox misalignment and imbalance faults Journal Article
In: Applied Intelligence, 2024, ISSN: 1573-7497.
Abstract | Links | BibTeX | Tags: Bearing failures, Fault detection and diagnosis, Powertrain failures, Semi-supervised learning, Wind turbine
@article{Maestro-Prieto2024,
title = {Semi-supervised diagnosis of wind-turbine gearbox misalignment and imbalance faults},
author = {Jose Alberto Maestro-Prieto and José Miguel Ramírez-Sanz and Andrés Bustillo,and Juan José Rodriguez-Díez},
url = {https://doi.org/10.1007/s10489-024-05373-6},
doi = {10.1007/s10489-024-05373-6},
issn = {1573-7497},
year = {2024},
date = {2024-03-28},
journal = {Applied Intelligence},
abstract = {Both wear-induced bearing failure and misalignment of the powertrain between the rotor and the electrical generator are common failure modes in wind-turbine motors. In this study, Semi-Supervised Learning (SSL) is applied to a fault detection and diagnosis solution. Firstly, a dataset is generated containing both normal operating patterns and seven different failure classes of the two aforementioned failure modes that vary in intensity. Several datasets are then generated, maintaining different numbers of labeled instances and unlabeling the others, in order to evaluate the number of labeled instances needed for the desired accuracy level. Subsequently, different types of SSL algorithms and combinations of algorithms are trained and then evaluated with the test data. The results showed that an SSL approach could improve the accuracy of trained classifiers when a small number of labeled instances were used together with many unlabeled instances to train a Co-Training algorithm or combinations of such algorithms. When a few labeled instances (fewer than 10% or 327 instances, in this case) were used together with unlabeled instances, the SSL algorithms outperformed the result obtained with the Supervised Learning (SL) techniques used as a benchmark. When the number of labeled instances was sufficient, the SL algorithm (using only labeled instances) performed better than the SSL algorithms (accuracy levels of 87.04% vs. 86.45%, when labeling 10% of instances). A competitive accuracy of 97.73% was achieved with the SL algorithm processing a subset of 40% of the labeled instances.},
keywords = {Bearing failures, Fault detection and diagnosis, Powertrain failures, Semi-supervised learning, Wind turbine},
pubstate = {published},
tppubtype = {article}
}
Both wear-induced bearing failure and misalignment of the powertrain between the rotor and the electrical generator are common failure modes in wind-turbine motors. In this study, Semi-Supervised Learning (SSL) is applied to a fault detection and diagnosis solution. Firstly, a dataset is generated containing both normal operating patterns and seven different failure classes of the two aforementioned failure modes that vary in intensity. Several datasets are then generated, maintaining different numbers of labeled instances and unlabeling the others, in order to evaluate the number of labeled instances needed for the desired accuracy level. Subsequently, different types of SSL algorithms and combinations of algorithms are trained and then evaluated with the test data. The results showed that an SSL approach could improve the accuracy of trained classifiers when a small number of labeled instances were used together with many unlabeled instances to train a Co-Training algorithm or combinations of such algorithms. When a few labeled instances (fewer than 10% or 327 instances, in this case) were used together with unlabeled instances, the SSL algorithms outperformed the result obtained with the Supervised Learning (SL) techniques used as a benchmark. When the number of labeled instances was sufficient, the SL algorithm (using only labeled instances) performed better than the SSL algorithms (accuracy levels of 87.04% vs. 86.45%, when labeling 10% of instances). A competitive accuracy of 97.73% was achieved with the SL algorithm processing a subset of 40% of the labeled instances.