Optimized and autonomous machine learning framework for characterizing pores, particles, grains and grain boundaries in microstructural images

TL;DR

This paper presents an optimized machine learning framework that efficiently characterizes microstructural features like pores, particles, grains, and grain boundaries in additively manufactured metals, reducing analysis time and computational resources.

Contribution

The work introduces an integrated, optimized ML framework combining CNNs, CEDNs, and object detection for autonomous microstructure analysis, with significant improvements in speed and resource efficiency.

Findings

Reduced training time and GPU usage with the optimized RGB segmentation network.

Achieved high accuracy in defect recognition and segmentation.

Significantly faster analysis compared to conventional methods.

Abstract

Additively manufactured metals exhibit heterogeneous microstructure which dictates their material and failure properties. Experimental microstructural characterization techniques generate a large amount of data that requires expensive computationally resources. In this work, an optimized machine learning (ML) framework is proposed to autonomously and efficiently characterize pores, particles, grains and grain boundaries (GBs) from a given microstructure image. First, using a classifier Convolutional Neural Network (CNN), defects such as pores, powder particles, or GBs were recognized from a given microstructure. Depending on the type of defect, two different processes were used. For powder particles or pores, binary segmentations were generated using an optimized Convolutional Encoder-Decoder Network (CEDN). The binary segmentations were used to used obtain particle and pore size and bounding boxes using an object detection ML network (YOLOv5). For GBs, another optimized CEDN was developed to generate RGB segmentation images, which were used to obtain grain size distribution using two regression CNNS. To optimize the RGB CEDN, the Deep Emulator Network SEarch (DENSE) method which employs the Covariance Matrix Adaptation - Evolution Strategy (CMA-ES) was implemented. The optimized RGB segmentation network showed a substantial reduction in training time and GPU usage compared to the unoptimized network, while maintaining high accuracy. Lastly, the proposed framework showed a significant improvement in analysis time when compared to conventional methods.