A Comprehensive Review of Multi-Modal Data Fusion-Driven Systematic Knowledge Construction Technologies for HVDC Operation and Maintenance

Large-scale UHVDC and flexible DC projects accumulate scattered multi-modal O&M data across independent platforms, fragmenting domain knowledge and reducing the efficiency of intelligent fault diagnosis and disposal. Unstructured data typically account for more than 70% of converter-station O&M data volume, which intensifies fragmentation across SCADA, inspection media, fault recordings and documents. Distinct from prior HVDC intelligent O&M surveys, this review critically synthesizes the closed-loop knowledge construction chain via multi-modal data fusion—covering data governance, cross-modal semantic mapping, DIKW modeling, hybrid storage and knowledge graph development—and compares three fusion paradigms regarding latency, scalability and industrial deployment. It also addresses renewable-integrated O&M uncertainty, practical feature extraction, and why deep learning black-box behavior limits field practicality. Key gaps remain small-sample generalization, control-and-protection logic formalization, explainability and cross-system integration; future directions include few-shot cross-modal learning, LLM-driven knowledge evolution and digital twin coupling.