Convolutional Twin Point Network Blade Contour Stitching System Based on Multiple Spatial Similarity

Abstract

The invention discloses a convolutional twin point network leaf profile splicing system based on multi-space similarity, including a data acquisition module, a convolutional twin point network and a data splicing module. The convolutional twin point network includes a network module that iterates several times, and a network module Including feature extraction module, matching matrix module, attention mechanism module and singular value decomposition module; feature extraction module uses edge convolution network structure to extract high-dimensional spatial features in source point cloud and target point cloud, and then uses high-dimensional spatial features and The coordinate space calculates the feature space matching matrix and the coordinate space matching matrix respectively, and then handles the conflict between the feature space matching matrix and the coordinate space matching matrix through the attention mechanism to obtain the final matching matrix, and calculates the source point cloud through the final matching matrix The corresponding relationship with the midpoint of the target point cloud, and finally the rigid body transformation is obtained through singular value decomposition, and the optimal rigid body transformation is obtained based on multiple iterations.

Description

technical field [0001] The invention relates to the field of blade profile detection, in particular to a multi-space similarity-based convolution twin point network blade profile splicing system. Background technique [0002] Blades are known as the jewel in the crown of modern industry and are widely used in aero engines, steam turbines and wind turbines. To ensure perfect and stable aerodynamic performance at high speeds, blades require extremely high dimensional accuracy and surface integrity. Accurate measurement of blade profile is an important means to guide blade production. However, thin-walled, twisted and mirror-like free-form surfaces increase the difficulty of blade surface measurement. At present, the acquisition of blade profile is done by three-coordinate measurement, which is a high-precision and easy-to-implement method. However, the efficiency of three-coordinate measurement is low, which hinders the production efficiency of blades. The increased focus ...

AI Technical Summary

Problems solved by technology

Because there must be mechanical errors in the four-axis detection system, there is a certain error between the rigid body transformation directly given by the system and the real rigid body transformation, which in turn causes errors between the spliced ​​blade outline and the actual blade

The existing point cloud registration algorithms include traditional splicing algorithm (ICP) and deep learning-based splicing algorithm (DCP), but there are still the following problems: the thin wall of the blade, the distorted space free-form surface and the two fields of view The small overlapping part of the lower point cloud increases the difficulty of extracting features with rotation and translation invariance; and under different fields of view, the point cloud density in the overlapping part is inconsistent, and it is difficult to find point correspondences

Images