Support Vector Machine Guided Reproducing Kernel Particle Method for Image-Based Modeling of Microstructures

TL;DR

This paper introduces a novel image-based modeling approach for microstructures using SVM-guided discretization and an interface-modified RKPM, improving accuracy and efficiency in representing complex composite microstructures.

Contribution

It combines SVM classification with a modified RKPM to accurately discretize and approximate microstructural interfaces without additional degrees of freedom.

Findings

Effective segmentation of micro-CT images using SVM.

Accurate approximation of interfaces with IM-RKPM reduces oscillations.

Validated on polymer-ceramic composites with promising results.

Abstract

This work presents an approach for automating the discretization and approximation procedures in constructing digital representations of composites from Micro-CT images featuring intricate microstructures. The proposed method is guided by the Support Vector Machine (SVM) classification, offering an effective approach for discretizing microstructural images. An SVM soft margin training process is introduced as a classification of heterogeneous material points, and image segmentation is accomplished by identifying support vectors through a local regularized optimization problem. In addition, an Interface-Modified Reproducing Kernel Particle Method (IM-RKPM) is proposed for appropriate approximations of weak discontinuities across material interfaces. The proposed method modifies the smooth kernel functions with a regularized heavy-side function concerning the material interfaces to alleviate Gibb's oscillations. This IM-RKPM is formulated without introducing duplicated degrees of freedom associated with the interface nodes commonly needed in the conventional treatments of weak discontinuities in the meshfree methods. Moreover, IM-RKPM can be implemented with various domain integration techniques, such as Stabilized Conforming Nodal Integration (SCNI). The extension of the proposed method to 3-dimension is straightforward, and the effectiveness of the proposed method is validated through the image-based modeling of polymer-ceramic composite microstructures.