Fault diagnosis method for hydro-power plants with Bi-LSTM knowledge graph aided by attention scheme

In hydro-power systems, the fault of equipment is an important potential threat for safe production electricity. Therefore, automation and intelligence diagnosis becomes popular issue in research on system. this paper, a knowledge graph-based method put forth to diagnose faults occurred since graph can store structured unstructured data better intelligently search reasons faults. First, we model plants, where rational path reason formulated. Then, bi-directional long short-term memory (Bi-LSTM) with conditional random field (CRF) used extract entities relations given documents, which record phenomenon Moreover, attention scheme employed Bi-LSTM weigh closer relationships improve accuracy. An automatic algorithm developed diagnosing efficiency by constructing paths, directive in-directive factors occurring be traced. Simulation results reveal that intelligent effectively find reason, locate position, provide useful suggestions