Year: 2025
Type: conference-paper
Abstract: Aiming at the problem of 3D plane fitting of the three-dimensional point cloud data of the inner plane of the wheelset, a new fitting method is proposed. The improved bat algorithm is used to fit the three-dimensional data point cloud of the inner side of the wheelset. The adaptive threshold is used as the critical point of the iterative optimization of the bat algorithm, and some error points are screened and eliminated to make the point cloud data more observable. The adaptive threshold improves the reliability of the algorithm, so that the bat algorithm can avoid falling into the local optimal problem to a certain extent during the iteration process, and improves the iteration accuracy, and further improves the computing power. Through experimental demonstration, the use of the bat algorithm with an adaptive threshold to fit the plane has good effect and high accuracy. Compared with the three-coordinate measurement results, the error is within 0.1mm, which meets the measurement requirements.
Authors: Litao Wang, Boao Wang, Shaoke Huang, Shuang Zhang, Ru Chen
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
OpenAlex ID: W4414931880