A partial discharge positioning and identification method and system based on multi-modal fusion

CN121784485BActive Publication Date: 2026-06-19ZHEJIANG HONGPU TECH CORP LTD
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
ZHEJIANG HONGPU TECH CORP LTD
Filing Date
2026-03-05
Publication Date
2026-06-19

AI Technical Summary

Technical Problem

Existing partial discharge detection methods struggle to balance high-precision positioning with anti-interference capabilities. Multimodal data fusion suffers from signal characteristic differences and positioning model accuracy issues, and discharge type identification relies on human experience, resulting in low levels of automation.

Method used

Signals are acquired using UHF and AE sensor arrays. The signal starting point is calculated using the AIC signal criterion, a discharge position coordinate model is established, and the discharge type is identified by combining a convolutional neural network, thereby achieving weighted fusion positioning and identification of multimodal signals.

Benefits of technology

It achieves high-precision three-dimensional positioning and automated discharge type identification, improves the reliability of detection and the ability to resist false alarms, solves the scale contradiction that cannot be addressed by a single method, and improves the anti-interference ability of the system.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121784485B_ABST
    Figure CN121784485B_ABST
Patent Text Reader

Abstract

This invention provides a method and system for partial discharge localization and identification based on multimodal fusion. The method includes: acquiring ultra-high frequency signals from a UHF sensor array and ultrasonic signals from an AE sensor array; calculating the signal start point of the ultra-high frequency signal in each UHF sensor, using the UHF sensor with the smallest signal start point as reference sensor one, calculating the relative time difference with other UHF sensors to obtain coarse localization of the discharge potential, and calculating a signal time window based on the position of the AE sensor array; extracting ultrasonic signals within the signal time window, calculating the relative time difference between other AE sensors and reference sensor two to establish a localization model of the discharge site and obtain fine localization of the discharge potential; extracting corresponding ultra-high frequency feature vectors and ultrasonic feature vectors, and performing weighted fusion to identify the discharge type of the discharge site.
Need to check novelty before this filing date? Find Prior Art