Control chart-integrated machine learning models for incipient fault detection in wind turbine main bearing

Abstract Wind farm operators traditionally rely on SCADA temperature alarms for early signs of main bearing degradation. However, these alarms are sometimes delayed due to slow propagation of temperature in the main bearing. This study proposes the use of turbine multi-sensor vibration data as a via...

Full description

Saved in:
Bibliographic Details
Main Authors: Samuel M. Gbashi, Obafemi O. Olatunji, Paul A. Adedeji, Nkosinathi Madushele
Format: Article
Language:English
Published: Springer 2025-07-01
Series:Discover Artificial Intelligence
Subjects:
Online Access:https://doi.org/10.1007/s44163-025-00409-3
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849764257454882816
author Samuel M. Gbashi
Obafemi O. Olatunji
Paul A. Adedeji
Nkosinathi Madushele
author_facet Samuel M. Gbashi
Obafemi O. Olatunji
Paul A. Adedeji
Nkosinathi Madushele
author_sort Samuel M. Gbashi
collection DOAJ
description Abstract Wind farm operators traditionally rely on SCADA temperature alarms for early signs of main bearing degradation. However, these alarms are sometimes delayed due to slow propagation of temperature in the main bearing. This study proposes the use of turbine multi-sensor vibration data as a viable alternative. Anomaly detection models including One-class support vector machine (OCSVM) and isolation forest (IF) models are first employed to compute anomaly scores from the dataset. An exponentially weighted moving average (EWMA) control chart receives the anomaly scores for fault prognosis. The study developed a methodology for identifying the optimal contamination fraction of the anomaly detection models and an index called the “anomaly model evaluation index (AMEI)” for evaluating the performance of the anomaly detection models. The optimal contamination fraction for the anomaly detection models was 4%. The IF model outperformed the OCSVM model, with an AMEI index of 5.84, in contrast to the OCSVM model’s score of 5.32. However, the OCSVM computed 18 times faster than the IF model. Furthermore, EWMA-IF achieved a higher True Positive Rate of 79.8% compared to 59.94% for EWMA-OCSVM, indicating a better ability to correctly identify abnormal observations. The EWMA-IF model alerted for an approaching main bearing fault six hours earlier than the EWMA-OCSVM control chart. The persistence of the anomaly scores above the threshold of the control charts provides evidence to suggest that a potential main bearing failure is imminent.
format Article
id doaj-art-ba3af3a056d14af1a1944d5fcaa860fa
institution DOAJ
issn 2731-0809
language English
publishDate 2025-07-01
publisher Springer
record_format Article
series Discover Artificial Intelligence
spelling doaj-art-ba3af3a056d14af1a1944d5fcaa860fa2025-08-20T03:05:10ZengSpringerDiscover Artificial Intelligence2731-08092025-07-015112310.1007/s44163-025-00409-3Control chart-integrated machine learning models for incipient fault detection in wind turbine main bearingSamuel M. Gbashi0Obafemi O. Olatunji1Paul A. Adedeji2Nkosinathi Madushele3Department of Mechanical Engineering Science, University of JohannesburgDepartment of Mechanical Engineering Science, University of JohannesburgDepartment of Mechanical Engineering Science, University of JohannesburgDepartment of Mechanical Engineering Science, University of JohannesburgAbstract Wind farm operators traditionally rely on SCADA temperature alarms for early signs of main bearing degradation. However, these alarms are sometimes delayed due to slow propagation of temperature in the main bearing. This study proposes the use of turbine multi-sensor vibration data as a viable alternative. Anomaly detection models including One-class support vector machine (OCSVM) and isolation forest (IF) models are first employed to compute anomaly scores from the dataset. An exponentially weighted moving average (EWMA) control chart receives the anomaly scores for fault prognosis. The study developed a methodology for identifying the optimal contamination fraction of the anomaly detection models and an index called the “anomaly model evaluation index (AMEI)” for evaluating the performance of the anomaly detection models. The optimal contamination fraction for the anomaly detection models was 4%. The IF model outperformed the OCSVM model, with an AMEI index of 5.84, in contrast to the OCSVM model’s score of 5.32. However, the OCSVM computed 18 times faster than the IF model. Furthermore, EWMA-IF achieved a higher True Positive Rate of 79.8% compared to 59.94% for EWMA-OCSVM, indicating a better ability to correctly identify abnormal observations. The EWMA-IF model alerted for an approaching main bearing fault six hours earlier than the EWMA-OCSVM control chart. The persistence of the anomaly scores above the threshold of the control charts provides evidence to suggest that a potential main bearing failure is imminent.https://doi.org/10.1007/s44163-025-00409-3Anomaly detectionExponentially weighted moving average control chartFault prognosisIsolation forestOne-class support vector machineVibration
spellingShingle Samuel M. Gbashi
Obafemi O. Olatunji
Paul A. Adedeji
Nkosinathi Madushele
Control chart-integrated machine learning models for incipient fault detection in wind turbine main bearing
Discover Artificial Intelligence
Anomaly detection
Exponentially weighted moving average control chart
Fault prognosis
Isolation forest
One-class support vector machine
Vibration
title Control chart-integrated machine learning models for incipient fault detection in wind turbine main bearing
title_full Control chart-integrated machine learning models for incipient fault detection in wind turbine main bearing
title_fullStr Control chart-integrated machine learning models for incipient fault detection in wind turbine main bearing
title_full_unstemmed Control chart-integrated machine learning models for incipient fault detection in wind turbine main bearing
title_short Control chart-integrated machine learning models for incipient fault detection in wind turbine main bearing
title_sort control chart integrated machine learning models for incipient fault detection in wind turbine main bearing
topic Anomaly detection
Exponentially weighted moving average control chart
Fault prognosis
Isolation forest
One-class support vector machine
Vibration
url https://doi.org/10.1007/s44163-025-00409-3
work_keys_str_mv AT samuelmgbashi controlchartintegratedmachinelearningmodelsforincipientfaultdetectioninwindturbinemainbearing
AT obafemioolatunji controlchartintegratedmachinelearningmodelsforincipientfaultdetectioninwindturbinemainbearing
AT paulaadedeji controlchartintegratedmachinelearningmodelsforincipientfaultdetectioninwindturbinemainbearing
AT nkosinathimadushele controlchartintegratedmachinelearningmodelsforincipientfaultdetectioninwindturbinemainbearing