Fault Diagnosis with BERT Bi-LSTM-assisted Knowledge Graph Aided by Attention Mechanism for Hydro-Power Plants
摘要
To minimize the risk of Hydro-Power Plant failure, it’s crucial to detect and precisely repair the damaged components. In this paper, we propose a knowledge graph-based fault diagnosis method for Hydro-Power Plants. Then, the improved BiLSTM-CRF algorithm is developed to recognize entities for fault diagnosis, and the BERT relationship extraction algorithm is designed to construct a fault diagnosis knowledge graph for the Hydro-Power Plant. The real experimental test results validate the proposed methodology.