EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multi-algorithm fusion-based intelligent monitoring and condition evaluation for high-voltage equipment in HVDC converter stations

Danhui Hu, Zeqi Huang, Haiming Liu, Bingke Yan, Tianru Shi, Peng Li

AIP Advances · 01.11.2026 · 16 (11)

DOI: 10.1063/5.0361989 ↗

Kurz gefasst

Fachartikel in der Zeitschrift AIP Advances, online erschienen am 11.11.2026. Verfasst von Danhui Hu und 5 weiteren Autor:innen. Die Arbeit nennt 16 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Special Topic Research Project on Defect-Free Substation Management.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To tackle the drawbacks of traditional manual periodic inspection for converter-station equipment, such as delayed data acquisition, insufficient monitoring precision, and poor early warning capacity for latent defects, this paper develops a full-station defect-free intelligent management and control system. Integrating sensing technology, optical-fiber communication, big-data analytics, and intelligent diagnosis algorithms, the system establishes nine professional monitoring modules covering converter transformers, gas-insulated switchgear, DC fields, AC fields, valve halls, and wall bushings. Targeted monitoring strategies are formulated according to the structural characteristics and failure mechanisms of key equipment to implement online monitoring of insulation status, mechanical performance, temperature, gas leakage, and electrical parameters. An intelligent fault diagnosis and condition evaluation model is constructed by combining backpropagation neural networks, fault tree analysis, and matter–element theory to classify equipment operating states. Supported by an optical-fiber backbone network, the system achieves unified data collection, transmission, and centralized management, with panoramic display and remote monitoring enabled. Co-simulation and field application results show that the latent-defect recognition accuracy reaches 98.2%. Early hidden defects can be detected within 5–10 min, while severe faults are judged and located within 1 s. The system eliminates monitoring blind spots, improves operation-maintenance efficiency and operational safety, and realizes digitization, visualization, and intelligence of full-station equipment management. This study provides reliable technical support for the intelligent retrofitting of high-voltage converter stations and smart power grid construction.

Förderung

  • Special Topic Research Project on Defect-Free Substation Management

Zitieren

APA

Hu, D., Huang, Z., Liu, H., Yan, B., Shi, T., & Li, P. (2026). Multi-algorithm fusion-based intelligent monitoring and condition evaluation for high-voltage equipment in HVDC converter stations. AIP Advances, 16(11). https://doi.org/10.1063/5.0361989

Vancouver

Hu D, Huang Z, Liu H, Yan B, Shi T, Li P. Multi-algorithm fusion-based intelligent monitoring and condition evaluation for high-voltage equipment in HVDC converter stations. AIP Advances. 2026;16(11). doi:10.1063/5.0361989

BibTeX
@article{Hu2026,
  author = {Hu, Danhui and Huang, Zeqi and Liu, Haiming and Yan, Bingke and Shi, Tianru and Li, Peng},
  title = {Multi-algorithm fusion-based intelligent monitoring and condition evaluation for high-voltage equipment in HVDC converter stations},
  journal = {AIP Advances},
  year = {2026},
  volume = {16},
  number = {11},
  doi = {10.1063/5.0361989}
}
Kostenlos starten →