Deep Learning Training Model Construction and Optimization of Cable Size Features in 3D Point Cloud Data

Cables are widely used in power transmission, and the measurement of key dimensions of cables is an indispensable part of the cable preparation process to help ensure their quality. In this article, a handheld laser 3D scanner is used to collect 3D point cloud data of cable dimensions, and the point cloud is denoised by bilateral filtering algorithm and combined with the direct method of coarse alignment and the ICP method of fine alignment to realize the alignment of 3D point cloud data of cables. Then, the cable diameter coordinates are obtained by fitting the cylindrical surface of the cable size to realize the calculation of the cable diameter, and a residual network-based edge detection model of the cable insulation layer is proposed to improve the feature extraction capability of the cable 3D point cloud data through the hollow convolutional residuals and the spatial attention mechanism. For the effectiveness of the above method, the cable 3D point cloud data is quantitatively verified. The average accuracy of the cable diameter calculation based on cylindrical surface fitting is 0.025 m. The AP value of the cable insulation layer edge detection model constructed based on residual network is 0.816, and the error range of the calculation results is between -1.46% and 1.44% when the cable insulation layer thickness is calculated based on the cable insulation layer edge detection results. Learning and analyzing dimensional features of cable 3D point cloud data by deep learning training model can significantly improve the measurement accuracy and measurement efficiency of cable dimensional features, which can provide a guarantee for improving the safety of cable operation.