In-Situ Melt Pool Characterization via Thermal Imaging for Defect Detection in Directed Energy Deposition Using Vision Transformers

TL;DR

This paper introduces a self-supervised Vision Transformer-based framework for in-situ melt pool defect detection in Directed Energy Deposition, achieving high accuracy with limited labeled data for improved manufacturing quality control.

Contribution

The study presents a novel self-supervised learning approach using Vision Transformers and transfer learning for defect detection in DED, reducing reliance on large labeled datasets.

Findings

Achieved 95.44% to 99.17% accuracy in defect classification.

Outperformed traditional methods with minimal labeled data.

Demonstrated scalable and cost-effective defect detection.

Abstract

Directed Energy Deposition (DED) offers significant potential for manufacturing complex and multi-material parts. However, internal defects such as porosity and cracks can compromise mechanical properties and overall performance. This study focuses on in-situ monitoring and characterization of melt pools associated with porosity, aiming to improve defect detection and quality control in DED-printed parts. Traditional machine learning approaches for defect identification rely on extensive labeled datasets, often scarce and expensive to generate in real-world manufacturing. To address this, our framework employs self-supervised learning on unlabeled melt pool data using a Vision Transformer-based Masked Autoencoder (MAE) to produce highly representative embeddings. These fine-tuned embeddings are leveraged via transfer learning to train classifiers on a limited labeled dataset, enabling the effective identification of melt pool anomalies. We evaluate two classifiers: (1) a Vision Transformer (ViT) classifier utilizing the fine-tuned MAE Encoder's parameters and (2) the fine-tuned MAE Encoder combined with an MLP classifier head. Our framework achieves overall accuracy ranging from 95.44% to 99.17% and an average F1 score exceeding 80%, with the ViT Classifier slightly outperforming the MAE Encoder Classifier. This demonstrates the scalability and cost-effectiveness of our approach for automated quality control in DED, effectively detecting defects with minimal labeled data.