Multi-dimensional feature fusion and dimension reduction method for transmission line data used for unmanned aerial vehicle maintenance route map setting and storage medium

By using multi-dimensional feature fusion and dimensionality reduction methods on transmission line data, two-dimensional and multi-dimensional features are identified and processed. Nonlinear weighted fusion and attenuation accumulation functions are used to generate UAV maintenance route maps, which solves the problems of high computational complexity and high misjudgment rate in existing technologies, and achieves more accurate fault diagnosis and safer UAV inspection.

CN122087669BActive Publication Date: 2026-07-14NANJING SATURN INFORMATION TECH CO LTD

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
NANJING SATURN INFORMATION TECH CO LTD
Filing Date
2026-04-23
Publication Date
2026-07-14

Smart Images

  • Figure CN122087669B_ABST
    Figure CN122087669B_ABST
Patent Text Reader

Abstract

The application provides a power transmission line data-oriented multi-dimensional feature fusion and dimension reduction method and a storage medium, relates to data processing technology, and performs standardization processing on the multi-dimensional influence data to obtain standard data; determines that the feature structure is a two-dimensional feature, takes the standard data as first data, counts first frequencies of each sub-item category in the first data, performs nonlinear weighted fusion processing on the first frequencies to obtain a first fusion value; when the feature type is a multi-dimensional feature, takes the standard data as second data, performs hierarchical processing on the second data based on a preset condition logic and counts second frequencies of each risk level, performs nonlinear weighted fusion processing according to the risk level and the second frequency to obtain a second fusion value; obtains a risk value of a monitoring target according to the first fusion value and the second fusion value, determines an abnormal target based on the risk value, and determines a maintenance route map of a UAV according to a target area of the abnormal target.
Need to check novelty before this filing date? Find Prior Art