Knowledge Graph-Based Intelligent Fault Diagnosis for Special Vehicle Diesel Engines: a Review

Fault diagnosis of special vehicle diesel engines is crucial for ensuring equipment reliability and operational performance. Traditional diagnostic methods relying on expert experience struggle to address complex fault patterns effectively. As a structured knowledge representation approach, Knowledge Graph (KG) can effectively integrate multi-source data to enhance the intelligence level of fault diagnosis. This paper reviews recent advances in KG-based fault diagnosis for special vehicle diesel engines, with a focus on three key aspects: application of association rule mining in correlation analysis of diesel engine parameters; methodologies for constructing diesel engine knowledge graphs; and KG-based fault diagnosis and recommendation strategies. The study summarizes current research challenges and future development directions, providing theoretical references for intelligent fault diagnosis.