Sep 2026· 2026 International Conference on Intelligent Computing and Sustainable Innovations in Technology (IC-SIT)· pp. 1-6· 0 citations· 19 references
Abstract
This work presents a machine learning-based framework for condition monitoring and fault diagnosis of wind turbine blades using vibration signals, analysed at varying rotational speeds. The raw vibration signals are pre-processed using denoising, normalization, and structuring. From this preprocessed vibration signal, both the time-domain and frequency-domain features are extracted. To reduce redundant features and improve classification accuracy, a meta-heuristic approach i.e., Genetic Algorithm (GA) based feature selection method is used for this purpose. The optimized features are then fed into five different supervised classifiers: Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Decision Tree, Random Forest, and a Stacked Ensemble model. Experiments are conducted for four different blade conditions, i.e., Good, Loose, Erosion, and Bend, under multiple operating speeds ranging from 400 to 600 RPM. The results show that the hybrid features from the time and frequency domains are able to perform better, achieving an accuracy of 95.83% compared to individual domain results.
During the operation of wind turbine bearings, the rotational speed continuously fluctuates with changes in wind intensity. At different rotational speeds, bearing faults exhibit distinct characteristic patterns and the accuracy of intelligent diagnostic methods significantly decreases.
Regarding this challenge, a mul...
Ding-Ding Zhang, Rui-Xia Shi, Zhong-Tang Huo et al.· Insight - Non-Destructive Te...· 0 citations
Structural health monitoring of jacket-type substructures of offshore wind turbines is key to ensuring their availability under limited access and combined wind–wave loading. This work presents a functional horizontal-axis wind turbine prototype on a modular, demountable A36-steel jacket substructure inspired by the OW...
José Eligio Moisés Gutiérrez Arias, Benito Pérez Hernández, Gabriela Pérez Osorio et al.· Engineering Research Express· 0 citations
This study investigates advanced diagnostic techniques for predicting bearing faults in industrial turbogenerators using Artificial Neural Networks (ANNs) and Support Vector Regression (SVR). Real-world data were collected from a 58 MW steam-driven turbogenerator over a two-year period, including vibration and rotation...
Soumaya Zaroual, Erroumayssae Sabani, H. Mastouri et al.· Engineer· 0 citations
The proposed method combines redundancy suppression, stable feature selection, deep feature learning, and ensemble classification, providing an effective approach for wind turbine fault warning and condition-based maintenance.
Yin-Long Han, Ai-Min An, Zhi-Peng Luo et al.· Processes· 0 citations
To address diagnostic challenges in feature extraction and parameter tuning for wind turbine gearboxes, this study proposes a diagnostic model that integrates the Gramian angular field, a convolutional neural network, and a least-squares support vector machine optimized by the dream optimization algorithm. First, Grami...
Zhi-Hao Fan, Mi-Nan Tang, Han-Ting Li et al.· Transactions of the Institut...· 0 citations
This study proposes a comprehensive framework for automated diagnostics of rotating machinery using vibration signals. The methodology integrates the stages of dataset selection and preparation, signal processing, feature extraction, dimensionality reduction and training and testing of supervised machine learning algor...
A. Ignjatovska, Z. Petreski, Dejan Shishkovski et al.· Journal of Vibroengineering· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.