A general particle modeling method for complex geometries

Abstract

Particle modeling for complex geometries is a challenge for the wide application of particle methods in engineering fields. The traditional modeling method with Cartesian coordinates faces difficulties in accurately representing boundary shapes and would lose flow details near the slender structure. The modeling method with the signed distance field (SDF) and particle shifting technique can obtain a uniform boundary-fitting particle distribution. However, the accuracy and efficiency of SDF construction, as well as the conservation of geometry volume after discretizing the model into particles, need to be further improved. In this paper, a general particle modeling method is proposed for arbitrary geometries. A double search technique is proposed to quickly construct the narrowband signed distance field (NSDF) near the geometry boundary. A scanning method is developed for the NSDF to determine the inner/outer relationship between the non-narrowband grids and the geometry. In addition, a volume compensation technique is proposed to ensure the volume conservation of the particle model. A modeling evaluation system is established, and three evaluation indicators are proposed to evaluate the quality of particle distribution and total volume conservation for particle models. Complex geometries such as the Stanford bunny, the Stanford dragon, and the centrifugal impeller are modeled to validate the accuracy and convergence of the proposed method. The results show that the proposed method can achieve a more uniform and accurate boundary-fitting particle distribution for complex geometries, and it can also effectively model tiny structures while significantly reducing total geometry volume error.