Method for acquiring the multi-surface three-dimensional shape of moving abrasive particles

Abstract

The invention discloses a method for acquiring the multi-surface three-dimensional shape of moving abrasive particles. An existing moving abrasive particle video acquisition platform is used; automatic tracking of the moving abrasive particles is realized; acquiring image sequences of the same moving abrasive particle under different visual angles; feature points on the surfaces of the abrasive particles are extracted through an SIFT algorithm; the position corresponding to the feature point is positioned at the adjacent frame; then, the establishment of a spatial point cloud model is realizedby calculating the three-dimensional coordinates of the feature points; meanwhile, the surface morphology of the abrasive particles is reconstructed through an SFS algorithm, finally, the surface morphology, reconstructed through the SFS algorithm, of the abrasive particles is fused with the space point cloud model through a fusion algorithm, dense reconstruction is achieved, and the three-dimensional morphology, with the sense of reality, of multiple surfaces of the moving abrasive particles is reconstructed through a texture mapping method; According to the method, an automatic tracking technology and a three-dimensional reconstruction technology are effectively combined, the problem that static abrasive particles can only be analyzed from a single surface in an existing abrasive particle analysis technology is solved, and accurate extraction of three-dimensional surface total information of the abrasive particles is achieved.

Description

technical field [0001] The invention belongs to the abrasive particle analysis technology in the field of machine wear state monitoring, and in particular relates to a method for acquiring three-dimensional shapes of multiple surfaces of moving abrasive particles. Background technique [0002] Wear between friction pairs is one of the main causes of mechanical equipment failures. According to statistics, failures caused by wear account for about 75% of mechanical equipment failures. Wear status monitoring provides failure prediction and maintenance strategies for mechanical equipment by analyzing the operating status of mechanical equipment, which can improve the safety and reliability of mechanical equipment, fully extend the service life, and minimize maintenance costs and downtime losses of mechanical equipment. With the rapid development of modern industry, the requirements for the safety and reliability of mechanical equipment are getting higher and higher, so it is of ...

AI Technical Summary

Problems solved by technology

The main application of two-dimensional wear particle analysis is ferrographic image processing. This method can extract the plane two-dimensional features of wear particles, such as concentration, equivalent size, shape parameters, etc., but cannot obtain the spatial feature information of wear particles, making it unable to 2D image reflecting wear particles with irregularities

This method is complex to operate, expensive to use, and limited in scope

In addition, whether it is two-dimensional wear particle analysis or three-dimensional wear particle analysis technology, there are always the following deficiencies in the current application: ① only wear particles under static conditions can be analyzed, but the wear particles obtained under static conditions The characteristic parameters will produce different results due to the conditions of taking the image of the wear particles and the aggregation of the wear particles, etc.

②The characteristics of abrasive grains can only be extracted from a single perspective, but the shape of abrasive grains is irregular, and a single surface cannot truly reflect the properties of abrasive grains

[0004] In general, wear particle analysis technology to achieve wear state characterization has become an important means of monitoring the wear state of mechanical equipment, and has been widely used in industrial fields such as aviation, ships, wind power, etc., but due to the shortcomings of its method , such as static wear particle analysis, can only extract the characteristic information of wear particles on a single surface, but cannot comprehensively and accurately extract the information of wear particles

Images