Trans GAN-WT: A Feature Extraction and Interactive Learning-Based Anomaly Detection Model for Wind Turbine Time Series Data
Researchers have developed a new anomaly detection model called TransGAN-WT, designed to improve the reliability and reduce maintenance costs for wind turbines. This model combines a Transformer with a generative adversarial network to effectively model relationships in complex time-series data and extract multimodal features. Experiments on real-world wind turbine datasets show TransGAN-WT achieves a 96.10% F1 score, outperforming existing methods by a significant margin and demonstrating a low false positive rate. AI
IMPACT Enhances operational efficiency and reliability in industrial applications through advanced anomaly detection.