Exploration of Unsupervised Deep Learning-Based Gear Fault Detection for Wind Turbine Gearboxes

Gearboxes are critical mechanical components in various modern constructions, including wind turbines, making their real-time monitoring and the prevention of major failures essential. Machine learning (ML) offers a precise and robust method for early-stage failure detection and efficient gear monit...

Full description

Saved in:
Bibliographic Details
Main Authors: Bartłomiej Kiczek, Michał Batsch
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Energies
Subjects:
Online Access:https://www.mdpi.com/1996-1073/18/14/3630
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849246560952516608
author Bartłomiej Kiczek
Michał Batsch
author_facet Bartłomiej Kiczek
Michał Batsch
author_sort Bartłomiej Kiczek
collection DOAJ
description Gearboxes are critical mechanical components in various modern constructions, including wind turbines, making their real-time monitoring and the prevention of major failures essential. Machine learning (ML) offers a precise and robust method for early-stage failure detection and efficient gear monitoring during operation, with computational efficiency that allows for use on edge devices. This article presents a method for detecting surface damage on gear teeth using unsupervised machine learning. Using only experimentally measured vibrational signals from a healthy gearbox as a training set, novel neural network architectures, including convolutional and recurrent autoencoders, were employed and compared with a classical dense autoencoder. The study confirmed the effectiveness of these methods in gear transmission diagnostics and demonstrated the potential for achieving high-quality classification metrics using unsupervised learning.
format Article
id doaj-art-6cf8186340054eefa8e78ab89bf747a2
institution Kabale University
issn 1996-1073
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Energies
spelling doaj-art-6cf8186340054eefa8e78ab89bf747a22025-08-20T03:58:27ZengMDPI AGEnergies1996-10732025-07-011814363010.3390/en18143630Exploration of Unsupervised Deep Learning-Based Gear Fault Detection for Wind Turbine GearboxesBartłomiej Kiczek0Michał Batsch1Department of Quantitative Methods in Management, Lublin University of Technology, 20-618 Lublin, PolandDepartment of Mechanical Engineering, Rzeszów University of Technology, 35-959 Rzeszów, PolandGearboxes are critical mechanical components in various modern constructions, including wind turbines, making their real-time monitoring and the prevention of major failures essential. Machine learning (ML) offers a precise and robust method for early-stage failure detection and efficient gear monitoring during operation, with computational efficiency that allows for use on edge devices. This article presents a method for detecting surface damage on gear teeth using unsupervised machine learning. Using only experimentally measured vibrational signals from a healthy gearbox as a training set, novel neural network architectures, including convolutional and recurrent autoencoders, were employed and compared with a classical dense autoencoder. The study confirmed the effectiveness of these methods in gear transmission diagnostics and demonstrated the potential for achieving high-quality classification metrics using unsupervised learning.https://www.mdpi.com/1996-1073/18/14/3630gearsdeep learningautoencodersneural networksfault detectionanomaly detection
spellingShingle Bartłomiej Kiczek
Michał Batsch
Exploration of Unsupervised Deep Learning-Based Gear Fault Detection for Wind Turbine Gearboxes
Energies
gears
deep learning
autoencoders
neural networks
fault detection
anomaly detection
title Exploration of Unsupervised Deep Learning-Based Gear Fault Detection for Wind Turbine Gearboxes
title_full Exploration of Unsupervised Deep Learning-Based Gear Fault Detection for Wind Turbine Gearboxes
title_fullStr Exploration of Unsupervised Deep Learning-Based Gear Fault Detection for Wind Turbine Gearboxes
title_full_unstemmed Exploration of Unsupervised Deep Learning-Based Gear Fault Detection for Wind Turbine Gearboxes
title_short Exploration of Unsupervised Deep Learning-Based Gear Fault Detection for Wind Turbine Gearboxes
title_sort exploration of unsupervised deep learning based gear fault detection for wind turbine gearboxes
topic gears
deep learning
autoencoders
neural networks
fault detection
anomaly detection
url https://www.mdpi.com/1996-1073/18/14/3630
work_keys_str_mv AT bartłomiejkiczek explorationofunsuperviseddeeplearningbasedgearfaultdetectionforwindturbinegearboxes
AT michałbatsch explorationofunsuperviseddeeplearningbasedgearfaultdetectionforwindturbinegearboxes