A power metering method based on big data self-diagnosis

By constructing a virtual standard metering unit through big data self-diagnosis methods, hardware drift in the power metering system is decoupled and compensated, solving the problem of tracing the source of metering errors, realizing real-time accurate diagnosis and self-healing capabilities, and improving the management level of the power system.

CN122310186APending Publication Date: 2026-06-30ZHEJIANG JINGHE ELECTRONICS TECH
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
ZHEJIANG JINGHE ELECTRONICS TECH
Filing Date
2026-05-29
Publication Date
2026-06-30

AI Technical Summary

Technical Problem

Existing electricity metering systems struggle to achieve accurate diagnosis and dynamic compensation in the face of aging hardware and complex operating conditions, making it difficult to trace metering errors and easily misdiagnosing environmental interference as metering faults, lacking self-healing capabilities.

Method used

A big data-based self-diagnosis method is adopted. A virtual standard measurement unit is constructed through a spatiotemporal graph convolutional network. Combined with variational mode decomposition and independent component analysis, load characteristics, environmental disturbances and hardware drift components are decoupled in real time. Error correction coefficients are calculated and digital compensation is performed to generate a health diagnosis report.

Benefits of technology

It enables real-time self-detection and online correction of measurement accuracy, improves the service life and maintenance efficiency of measurement equipment, and ensures the fairness of trade settlement and the system's self-healing capability.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122310186A_ABST
    Figure CN122310186A_ABST
Patent Text Reader

Abstract

This invention belongs to the field of data processing, specifically relating to a power metering method based on big data self-diagnosis. The invention discloses a power metering method based on big data self-diagnosis, which includes: real-time acquisition of multi-dimensional heterogeneous sensing data; training a dynamic floating baseline for metering using a spatiotemporal graph convolutional network; applying variational mode decomposition and independent component analysis algorithms to decouple the metering data stream into load characteristics, environmental disturbances, and hardware drift components; comparing the hardware drift components with the floating baseline in real time to calculate an error correction coefficient; and converting this coefficient into a digital compensation factor applied to the data processing module to achieve online correction of the metering results and synchronously generate a health diagnosis report. This invention, by constructing a dynamic baseline model and feature decoupling algorithms, achieves real-time self-detection of metering accuracy and digital closed-loop self-healing, eliminating external environmental interference and improving the robustness, management level, and operation and maintenance efficiency of the power metering system.
Need to check novelty before this filing date? Find Prior Art