Intelligent arc fault determination method for low-voltage switch cabinet

By constructing photoelectric phase cluster offset coefficient and voltage-current coupling hysteresis discrete factor, a micro-arc evolution trajectory vector sequence is generated. Combined with the counterfactual reconstruction model and voltage drop characteristics, the problem of misjudgment of metastable micro-arc faults in low-voltage switchgear is solved, achieving more accurate arc fault judgment, reducing the misjudgment rate and improving safety.

CN122173911APending Publication Date: 2026-06-09JUNLANG ELECTRICAL CO LTD
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
CN202610636364.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-05-11
Publication Date
2026-06-09

AI Technical Summary

Technical Problem

Existing technologies cannot effectively distinguish between extremely low-probability but highly concealed metastable micro-arc faults in low-voltage switchgear, leading to misjudgment as normal disturbances and creating a risk of cumulative insulation degradation.

Method used

By collecting light intensity, current and voltage sequences in the switch cabinet, a synchronous phase reference axis is constructed, the photoelectric phase cluster offset coefficient and the voltage-current coupling hysteresis dispersion factor are extracted, a micro-arc evolution trajectory vector sequence is generated, and potential unstable arc processes are identified by nonlinear trajectory continuity criteria. Multi-layer verification is performed by combining the counterfactual reconstruction model and voltage drop characteristics, and finally the arc fault is determined.

Benefits of technology

It improves the accuracy of identifying micro-arc faults in low-voltage switchgear, reduces the false judgment rate, and can detect potential weak arcing hazards at an early stage, avoiding fault expansion and power outage losses. It is suitable for scenarios with high requirements for power supply continuity and protection accuracy.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122173911A_ABST
    Figure CN122173911A_ABST
Patent Text Reader

Abstract

This invention discloses an intelligent method for determining arc faults in low-voltage switchgear, specifically relating to the field of intelligent arc fault determination technology. It constructs an initial multi-physics time-series dataset by collecting light intensity, current, and voltage sequences. A phase coupling feature set is generated by extracting the photoelectric phase clustering offset coefficient and the voltage-current coupling hysteresis dispersion factor through short-window sliding. Based on the phase coupling feature set, a micro-arc evolution trajectory vector sequence is generated to identify candidate events. A counterfactual reconstruction model under the arc-free assumption is introduced for the candidate events to generate a set of control signals and calculate the deviation index. The fractal dimension and energy dispersion are combined to form the determination feature, obtaining the arc occurrence probability. A secondary verification is performed using voltage drop characteristics, and the final determination result is output. This invention can improve the accuracy of identifying weak, short-duration, and intermittent arc faults and reduce the false judgment rate.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Arc light fault identification device and method based on panoramic information

    CN109298291A

  • Battery cluster short circuit rapid identification method and device based on voltage sag

    CN121208690A

  • Switch cabinet arc light detection method and system based on multispectral fusion

    CN121899583A

  • Systems, methods and apparatuses of elastic light scattering spectroscopy and low coherence enhanced backscattering spectroscopy

    US20090009759A1

  • It system fault analysis technique based on configuration management database

    US20190056983A1