Metering device polarity test method and system suitable for high-noise environment

By applying excitation signals controlled by algorithms, preprocessing multi-dimensional signals, and using AI fusion judgment algorithms, the problems of anti-interference and judgment accuracy in polarity testing of measuring devices under high noise environments have been solved, achieving high-precision and stable polarity testing.

CN122085183APending Publication Date: 2026-05-26国网江西省电力有限公司九江供电分公司
0 Cites 0 Cited by

Patent Information

Application Number
CN202511943239.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-12-22
Publication Date
2026-05-26

AI Technical Summary

Technical Problem

Existing polarity testing methods for metrology devices have weak anti-interference capabilities, low judgment accuracy, and poor stability in high-noise environments, making them difficult to meet the testing needs of complex noise environments such as industrial sites and substations.

Method used

By employing algorithm-controlled excitation signal application, multi-dimensional signal preprocessing, and AI fusion judgment algorithm, combined with Hall current sensor and improved convolutional neural network (CNN) model, accurate and stable testing of the polarity of measuring devices can be achieved.

Benefits of technology

It achieves high accuracy and stability in polarity determination of measuring devices in high-noise environments, has strong anti-interference ability, wide adaptability, and is suitable for a variety of measuring devices, thus reducing testing costs.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses a metering device polarity testing method suitable for a high-noise environment, and belongs to the technical field of metering device detection. Comprising the steps of generating a square wave excitation signal of a preset parameter based on algorithm control and applying to a primary side of a metering device; secondary side induction response signals are collected, and are synchronously transmitted after being subjected to filtering, baseline drift correction and amplitude scaling preprocessing; integrating excitation and pre-processing signals, extracting phase difference, delay time and amplitude characteristic parameters, and sequentially executing polarity, phase sequence and on-off judgment to obtain a preliminary comprehensive result; based on the preliminary result and the feature parameters, outputting a determination result and confidence through an improved CNN model, and obtaining a final polarity conclusion through weight distribution fusion; and visually outputting the final conclusion. Through collaborative design of precise excitation, anti-interference preprocessing, multi-dimensional preliminary judgment and AI fusion final judgment, noise interference is effectively suppressed, polarity judgment precision and stability are improved, and the method is adaptive to high-noise scenes such as industrial sites and transformer substations.
Need to check novelty before this filing date? Find Prior Art