Volume monitoring of the milling tool tip wear and breakage based on multi-focus image three-dimensional reconstruction

In precision machining, the milling tool’ geometry has a great influence on milled surface quality. The research tool state monitoring was mainly based one-dimensional signals and two-dimensional images, which could indirectly obtain wear area, but it not provide volume of breakage thereby making difficult to achieve quantitative analysis wear. This paper proposed three-dimensional (3D) reconstruction method tip, build 3D model then region tip extracted by model. Firstly, focusing degree image sequence’s pixels calculated non-subsampled discrete shearlet transform (NSST) Laplace algorithm, completed according shape-from-focus (SFF) principle; secondly, depth values were optimized fitting curve in sequence with Gaussian function; finally, point cloud Simpson double numerical integration method, material loss damaged be obtained. experiment comparing different focus evaluation operators SFF, least noise best performance root-mean-square error, correlation, smoothness indexes.