An Axis Orbit Reconstruction Method for Rotating Machinery Based on Machine Vision

In this paper, a three-dimensional axis orbit reconstruction method based on machine vision is proposed for rotating machinery. Firstly, the center of rotor is marked and its motion is videotaped. Secondly, the local phase of captured image sequences is extracted, which is linear with the axis orbit displacement. Combined with the binocular stereo vision, three-dimensional axis orbit is reconstructed. According to the linear relation between phase and displacement, the actual axis orbit can be obtained. Finally, the experiment is performed on a permanent magnet synchronous motor, and the experimental results verify the effectiveness of the proposed method.