English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Additive manufacturing (AM) is gaining attention across various industrieslike healthcare, aerospace, and automotive. However, identifying defects earlyin the AM process can reduce production costs and improve productivity - a keychallenge. This study explored the effectiveness of machine learning (ML)approaches, specifically transfer learning (TL) models, for defect detection in3D-printed cylinders. Images of cylinders were analyzed using models includingVGG16, VGG19, ResNet50, ResNet101, InceptionResNetV2, and MobileNetV2.Performance was compared across two datasets using accuracy, precision, recall,and F1-score metrics. In the first study, VGG16, InceptionResNetV2, andMobileNetV2 achieved perfect scores. In contrast, ResNet50 had the lowestperformance, with an average F1-score of 0.32. Similarly, in the second study,MobileNetV2 correctly classified all instances, while ResNet50 struggled withmore false positives and fewer true positives, resulting in an F1-score of0.75. Overall, the findings suggest certain TL models like MobileNetV2 candeliver high accuracy for AM defect classification, although performance variesacross algorithms. The results provide insights into model optimization andintegration needs for reliable automated defect analysis during 3D printing. Byidentifying the top-performing TL techniques, this study aims to enhance AMproduct quality through robust image-based monitoring and inspection.

Defect Analysis of 3D Printed Cylinder Object Using Transfer Learning Approaches