An Ancillary Decision-Making Method for Hydropower Station Failure Handling Based on Case-Based Reasoning and Knowledge Graph

This paper proposes an ancillary decision-making method for hydropower station failure handling based on knowledge graph and case-based reasoning. The proposed method assists the power station dispatcher to carry out accurate and timely failure handling after an accident. First, the main steps of case-based reasoning are introduced. The main difficulties and their corresponding solutions when applying case-based reasoning to hydropower station failure handling are discussed. Then, an ancillary decision-making method for hydropower station failure handling is proposed. Key steps such as case construction, case retrieval, and case revision are designed. In the proposed method, each case is represented in the form of multiple knowledge graphs, i.e., a system topology knowledge graph, a dispatching regulation knowledge graph, and an accident case knowledge graph. The flexibility of case knowledge extraction, management, and retrieval is greatly enhanced. Finally, the simulation analysis is carried out on a large-scale cascade hydropower station in China. The simulation results show that the proposed method can provide reasonable and reliable ancillary decision-making for the power station dispatcher in the failure handling process, and greatly improve the intelligence level of emergency management at a hydropower station.