Hydropower_generator_abnormality_detection

Solemnly declare: If you use this open source content in papers, books, academic reports and other works, please quote the following documents(The original link has the latest citation format):ZHANG Chunxiang, SUN Ying, GAO Kexin, GAO Xueyao. Combine the Pre-trained Model with Bidirectional Gated Recurrent Units and Graph Convolutional Network for Adversarial Word Sense Disambiguation[J]. Journal of Electronics & Information Technology, 2025, 47(11): 4549-4559. doi: 10.11999/JEIT250386URL:结合预训练模型的双向门控图卷积对抗词义消歧This repository presents an unsupervised acoustic anomaly detection framework for hydropower generating units. It leverages pretrained audio foundation models and a density-estimation-based k-nearest neighbors (k-NN) algorithm.Due to data confidentiality, the original raw dataset cannot be publicly released. However, the full algorithm is open-sourced. The main program is pretrainMutiLayerBEATs.py.To apply this framework to your own dataset, simply change the data paths in the configuration.