Fault Diagnosis of Wind Turbine Blades Based on One-Dimensional Convolutional Neural Network-Bidirectional Long Short-Term Memory-Adaptive Boosting and Multi-Source Data Fusion

Applied Sciences, Journal Year: 2025, Volume and Issue: 15(7), P. 3440 - 3440

Published: March 21, 2025

To prevent wind turbine blade accidents and improve fault detection accuracy, a hybrid deep learning model based on 1D CNN-BiLSTM-AdaBoost for turbine-blade classification is proposed. Fault data are first preprocessed by segmenting labeling the patterns. Features extracted through convolutional layers, followed dimensionality reduction denoising using pooling feature fusion. The multi-source sensor features then fed into BiLSTM layer further processing of time-series characteristics. processed classified fully connected layer. Finally, multiple weak classifiers combined to generate final result. Experimental results show that outperforms models use only CNN, BiLSTM, CNN-BiLSTM, achieving an accuracy 96.88%, precision 97.22%, recall 96.92%, F1 score 96.86%, with maximum 100%. These validate model’s effectiveness classification.

Language: Английский

Source-free universal domain adaptation for compressor component fault diagnosis guided by hybrid clustering strategy

Mechanical Systems and Signal Processing, Journal Year: 2025, Volume and Issue: 232, P. 112771 - 112771

Published: April 21, 2025

Language: Английский