High-Throughput Unsupervised Profiling of the Morphology of 316L Powder Particles for Use in Additive Manufacturing

2025-12-03

AI Summary

To address the challenge of efficiently characterizing morphological heterogeneity in metal powders used in selective laser melting (SLM), this paper introduces the first high-throughput, unsupervised morphological clustering framework tailored for industrial batch processing. The method integrates high-throughput imaging, Fourier descriptors, and k-means clustering to enable automated, single-particle shape analysis at sub-millisecond speed (<1 ms per particle). Clustering validity is rigorously assessed using the Davies–Bouldin index and Calinski–Harabasz score to ensure statistical robustness. Evaluated on a dataset of 126,000 images of 316L stainless steel powder, the framework significantly outperforms conventional qualitative assessment methods, demonstrating superior efficiency, scalability, and reproducibility. It establishes a novel paradigm for powder quality tracking, reuse decision-making, and process–property prediction in additive manufacturing.

Technology Category

• Machine Learning: Clustering
• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

• Web Mining and Content Analysis: Normalization, clustering, classification, and summarization of Web text
• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success
• Security and Privacy: Large-scale security measurements

Abstract

Selective Laser Melting (SLM) is a powder-bed additive manufacturing technique whose part quality depends critically on feedstock morphology. However, conventional powder characterization methods are low-throughput and qualitative, failing to capture the heterogeneity of industrial-scale batches. We present an automated, machine learning framework that couples high-throughput imaging with shape extraction and clustering to profile metallic powder morphology at scale. We develop and evaluate three clustering pipelines: an autoencoder pipeline, a shape-descriptor pipeline, and a functional-data pipeline. Across a dataset of approximately 126,000 powder images (0.5-102 micrometer diameter), internal validity metrics identify the Fourier-descriptor + k-means pipeline as the most effective, achieving the lowest Davies-Bouldin index and highest Calinski-Harabasz score while maintaining sub-millisecond runtime per particle on a standard desktop workstation. Although the present work focuses on establishing the morphological-clustering framework, the resulting shape groups form a basis for future studies examining their relationship to flowability, packing density, and SLM part quality. Overall, this unsupervised learning framework enables rapid, automated assessment of powder morphology and supports tracking of shape evolution across reuse cycles, offering a path toward real-time feedstock monitoring in SLM workflows.

Problem

• Automated profiling of 316L powder particle morphology for additive manufacturing
• High-throughput unsupervised clustering to replace low-throughput qualitative methods
• Framework enables rapid assessment and tracking of powder shape evolution

Innovation

• Automated machine learning framework for powder morphology profiling
• High-throughput imaging with shape extraction and clustering
• Fourier-descriptor and k-means pipeline for efficient particle analysis