A method for identifying icing type of power transmission line and calculating load

By employing cross-modal feature fusion and perspective distortion correction techniques, the problems of low identification accuracy and complex, time-consuming calculations in transmission line icing monitoring have been solved, achieving high-precision icing type identification and load calculation, and supporting real-time icing prevention and disaster mitigation early warning for smart grids.

CN122336723APending Publication Date: 2026-07-03TAIYUAN UNIVERSITY OF TECHNOLOGY
View PDF 3 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN Β· China
Patent Type
Applications(China)
Current Assignee / Owner
TAIYUAN UNIVERSITY OF TECHNOLOGY
Filing Date
2026-04-14
Publication Date
2026-07-03

AI Technical Summary

Technical Problem

Existing methods for monitoring icing on transmission lines suffer from low identification accuracy, neglect of the impact of different icing types on loads, and complex and time-consuming calculations, making it difficult to meet the needs of real-time online monitoring and rapid early warning.

Method used

Implicit visual features are extracted using a visual flow based on the Swin Transformer, and meteorological semantic features are extracted using a meteorological perception-assisted flow based on a multilayer perceptron. Cross-modal cascade fusion is performed through a soft target supervision mechanism to identify icing types. The equivalent icing thickness is calculated using perspective distortion adaptive affine correction and morphological skeleton extraction, and the load is calculated by combining the icing density.

Benefits of technology

It improves the accuracy of icing type identification and load calculation, has strong robustness and adaptability to harsh environments, and can provide intuitive quantitative mechanical parameter support for smart grids.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122336723A_ABST
    Figure CN122336723A_ABST
Patent Text Reader

Abstract

This invention belongs to the field of power transmission line condition monitoring technology, specifically relating to a method for identifying icing types and calculating loads on power transmission lines. The method includes the following steps: S1: Acquiring icing image data of power transmission lines and micro-meteorological data collected synchronously with the icing image data, constructing an icing image dataset and a micro-meteorological dataset; S2: Performing semantic segmentation on the icing image data and extracting the binarized mask of the icing area of ​​the power transmission cable; S3: Extracting explicit physical features, implicit visual features, and meteorological semantic features, fusing them across modalities, and optimizing the network through a soft target supervision mechanism to output the icing type identification result; S4: Calculating the equivalent icing thickness of the power transmission cable; S5: Calculating the icing gravity load per unit length of the power transmission cable. This invention solves the problems of existing power transmission line icing monitoring methods being complex to implement, having high model calculation difficulty, and neglecting the impact of icing loads on power transmission lines.
Need to check novelty before this filing date? Find Prior Art