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.
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
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.
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.
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.
Smart Images

Figure CN122310186A_ABST