A hybrid methodology for classifying degradation stages and estimating a relative RUL-related degradation indicator for bearings is proposed by integrating synthetic data modeling, feature selection, and a combined unsupervised–supervised learning approach, offering a reliable and scalable solution for predictive maintenance and assessment of degradation progression in wind turbine bearings.
Abstract
The increasing demand for reliability in wind turbine systems makes early bearing fault detection under variable-speed conditions a persistent challenge. This paper proposes a hybrid methodology for classifying degradation stages and estimating a relative RUL-related degradation indicator for bearings by integrating synthetic data modeling, feature selection, and a combined unsupervised–supervised learning approach. Synthetic vibration signals are generated through logistic-curve interpolation with pink noise, enabling controlled degradation simulation. Features from time, frequency, and time–frequency domains were ranked using Mutual Information, and Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN) was employed to identify progressive wear stages. Cluster centers serve as anchors for mapping degradation into RUL percentages, while classification ensures stage consistency. Experimental results demonstrate six well-defined clusters for inner-race faults (Silhouette 0.5190), three moderate clusters for outer-race faults (0.2339), and overlapping patterns for rolling element faults (–0.1527), with zero RUL deviation in the best case. The proposed framework combines real and synthetic data to enhance generalization while reducing computational cost, offering a reliable and scalable solution for predictive maintenance and assessment of degradation progression in wind turbine bearings.
This study investigates the consistency and impact of feature selection methods on deterministic and probabilistic normal behaviour models (NBMs) for estimating rear generator bearing temperature in wind farms using SCADA data. Rigorous NBM development enables the transfer of key features, enhances anomaly detection comparability and facilitates potential portability across wind farms. The rise of machine learning and a vast range of statistical methods available for anomaly detection or estimation with SCADA data further emphasizes the need for investigating consistent NBMs. This paper evaluates four feature selection methods—Pearson's correlation coefficient (PCC), decision tree weights (DTW), mutual information (MI) and Shapley values of a neural network (SHAP)—for two wind farms to assess consistency in identified influential features and their impact on estimation algorithms. The results highlight the importance of prioritizing features consistently identified across datasets and methods over merely optimizing deterministic estimation performance. Temperature‐related sensors dominated the key features, but their specific locations were also ranked consistently. Probabilistic interval estimations demonstrated superior estimation performance and to identify whether a significant difference in feature can be attributed to the model or to an anomaly in the measured data.
Daragh O'Connnor, V. Pakrashi, Bidisha Ghosh· Wind Energy· 0 citations
The findings affirm the efficacy of XGBoost in bearing fault classification and emphasise the diagnostic value of carefully selected time-domain features, as well as suggesting strong potential for deploying such models in real-time condition monitoring and predictive maintenance systems.
A. Bhende· Insight - Non-Destructive Te...· 0 citations
Results show that using statistical vibration features with ensemble classifiers is a good way to diagnose multi-class bearing faults and establishes a comprehensive benchmark for ML- and DL-based rolling bearing FDD.
M. I. Quamar, Abdulrazaq Nafiu Abubakar, Ali Nasir· Journal of Vibration Enginee...· 0 citations
Accurate diagnosis of rolling bearing faults is critical to the reliability of industrial equipment. However, rolling bearings often operate under complex operating conditions, and with data imbalances and noise interference, fault diagnosis of them remains extremely challenging. To address these issues, a novel mode entropy knowledge machine (MEKM) framework for robust bearing fault diagnosis is proposed in this study. For MEKM, the mode entropy space is firstly constructed to decompose the vibration signal into intrinsic mode components, and the noise-resistant feature extraction and dimensionality reduction are realized by principal component analysis. Secondly, a fast classifier based on extreme learning machines is introduced, and its parameters are automatically adjusted through a particle swarm optimization to establish an adaptive extreme learning machine diagnosis model, ensuring optimal generalization under different load and speed levels. Then, a collaborative optimization paradigm is developed to coordinate mode entropy features and classifier parameters through fully automated learning, in which entropy-driven feature characterization guides the iterative refinement of decision boundaries, while classifier feedback dynamically improves the selectivity of entropy features. Finally, validation is performed on bearings with multiple operating conditions, and the results indicated that the MEKM outperformed conventional deep learning methods in terms of diagnostic accuracy and generalization ability. The work provides a theoretical basis and an industrially feasible solution for health monitoring of mechanical equipment.
Hongchuang Tan, Yiheng Su, Jiang Ding et al.· Journal of Dynamics Monitori...· 0 citations
Wind turbine blade failures, such as icing and damage, risk safety and efficiency, but limited fault data hinders diagnosis. This study proposes a hybrid framework combining ResNet50-SVM and transfer learning for small-sample fault diagnosis. A coupled simulation model first generates comprehensive dynamic fault data. Vibration signals are converted into time-frequency images via frequency-sliced wavelet transform, then classified by the ResNet50-SVM model. Next, transfer learning adapts simulated pre-trained models to target turbines using minimal samples. Results show the ResNet50-SVM model outperforms LSTM approaches, achieving up to 95.24% accuracy and improving precision and recall by 15–30%. Furthermore, transfer learning improved recall by 20–40% using only 4 to 6 target samples. Ultimately, this scalable simulation-to-reality approach enhances wind farm maintenance efficiency and reduces economic losses.
Tianyu Zhang, Naichao Chen, Qiu-Jie Xu et al.· Wind Engineering : The Inter...· 0 citations
Wind turbine blade faults, such as surface erosion, cracks, mass imbalance, and twist deformation, significantly compromise operational efficiency and reliability, thereby increasing maintenance costs. This research presents an artificial neural network (ANN)-based diagnostic approach for identifying five distinct fault states in wind turbine blades using vibration signal data collected at a constant operational speed of 1.3 m/s. The dataset, which encapsulates real-world vibration responses under varying fault conditions, was analyzed to extract amplitude features for classification. A balanced dataset of 500 samples per class was used to ensure robust training and evaluation. The ANN model achieved highly reliable performance, with classification accuracies (CA) of 96.21% (crack), 97.12% (erosion), 95.47% (healthy), 96.04% (twist deformation), and 94.38% (mass imbalance). Corresponding F1-scores were 95.32%, 96.51%, 94.45%, 95.18%, and 93.36%, respectively. These results confirm the model's effectiveness in distinguishing between common wind turbine blade faults and healthy conditions. This study demonstrates the potential of ANN-based systems for intelligent fault detection in wind energy systems, aiding in the advancement of condition-based maintenance and operational safety.
Z. Khan, Shabbir Ahmad, A. Askar· Terra Joule Journal· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
