Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Era, Israt Zarin, Zhou, Fan, Raihan, Ahmed Shoyeb, Ahmed, Imtiaz, Abul-Haj, Alan, Craig, James, Das, Srinjoy, Liu, Zhichao
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2411.12028
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916607871156224
author Era, Israt Zarin
Zhou, Fan
Raihan, Ahmed Shoyeb
Ahmed, Imtiaz
Abul-Haj, Alan
Craig, James
Das, Srinjoy
Liu, Zhichao
author_facet Era, Israt Zarin
Zhou, Fan
Raihan, Ahmed Shoyeb
Ahmed, Imtiaz
Abul-Haj, Alan
Craig, James
Das, Srinjoy
Liu, Zhichao
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2411_12028
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle In-Situ Melt Pool Characterization via Thermal Imaging for Defect Detection in Directed Energy Deposition Using Vision Transformers
Era, Israt Zarin
Zhou, Fan
Raihan, Ahmed Shoyeb
Ahmed, Imtiaz
Abul-Haj, Alan
Craig, James
Das, Srinjoy
Liu, Zhichao
Computer Vision and Pattern Recognition
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.
title In-Situ Melt Pool Characterization via Thermal Imaging for Defect Detection in Directed Energy Deposition Using Vision Transformers
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.12028