A Deformation Defect Detection Method of Pole Tower Based on UAV Laser Point Cloud Modeling

Abstract

The invention discloses a method for detecting deformation defects of towers based on UAV laser point cloud modeling. Calculate the point cloud data and build a 3D model; 3. Divide the 3D model into spatial regions, and count the number of marked small cubes in each region; 4. Laser scan the transmission tower again for subsequent inspections And send to the data analysis system; 5. Build the three-dimensional model again, and compare the spatial coordinates with step 2; 6. Count the number of marked small cube spaces in each area in step 5, and compare it with the set threshold to judge whether Service is required. This method can quickly inspect and find the damage and missing of insulators and fittings that are most likely to occur in actual line operation, and has good practical value for timely detection of deformation defects of transmission poles and towers.

Description

technical field [0001] The invention relates to the technical field of electric power inspection, in particular to a method for detecting deformation defects of towers based on UAV laser point cloud modeling. Background technique [0002] During the "13th Five-Year Plan" period, my country's power grid construction has experienced a stage of rapid development, and its scale has leapt to the first place in the world. At present, my country has built six power grids across provinces and regions, namely the South, Northwest, East China, Central China, North China, and Northeast China. The total length of transmission lines exceeds 1.15 million kilometers, and transmission lines of 500kV and above have become the main power grids in various regions. Power grid transmission main force. And according to the plan of the State Grid Corporation, the total planned investment of the State Grid Corporation will reach 522.2 billion yuan in the new round of rural power grid transformation...

AI Technical Summary

Problems solved by technology

[0008] 2. The defect finding work is complicated

The workload of manual screening is too large, and the efficiency of all processes is not much higher than that of ordinary manual inspection; the recognition rate of AI recognition is still difficult to reach a practical level, mainly because there are too few materials available for training and the reliability of AI training itself The accuracy is low, resulting in poor AI recognition effect, low detection rate and high false alarm rate. After the recognition is completed, manual review is required, which further increases the workload.

Images