Abstract: CAFS plays an important role in critical facilities such as UHV converter stations. However, with the improvement of its fire extinguishing capability, the difficulty of management and control has also increased, posing higher requirements for health status monitoring, fault diagnosis, and reliability analysis of fire protection facilities. Given the complexity of the functional structure and diverse fault modes of CAFS, this paper integrates three typical fault diagnosis methods, including time-series monitoring data, knowledge graph, and grey relational analysis, to construct a fault knowledge graph model. By querying the knowledge graph with specified fault keywords and combining with the grey relational analysis algorithm, the fault points can be precisely located, providing decision support for maintenance and management personnel. Three typical fault simulation experiments were conducted, and the experimental results show that the proposed meta-synthetic method can effectively improve the efficiency and accuracy of fault diagnosis, which is of great significance for ensuring the reliability and effectiveness of the CAFS system.

Key words: compressed air foam system, meta-synthetic approach, fault knowledge graph, grey relational analysis