Skip to main content
Articles | Advanced Mechanical and Mechatronic Systems | Volume 2 - Issue 2 - 2026 | 88–105 | https://doi.org/10.53623/amms.v2i2.995
© 2026 by the author(s), and is licensed under the Creative Commons Attribution 4.0 International (CC BY 4.0) License Creative Commons Attribution 4.0 International (CC BY 4.0) License

Machine Vision Lab Experiment Based Convolutional Neural Network for Potential Intelligent Manufacturing Applications

Author(s): Ardian Webi Kirda 1 , Kamil Gatnar 2 , Khairul Muzaka 3 ORCID https://orcid.org/0000-0003-1320-1998 , Nur Arifin Akbar 4 ORCID https://orcid.org/0000-0002-3305-2187
Author(s) information:
1 Faculty of Integrated Technologies, Universiti Brunei Darusalam, Jalan Tungku Link, BE1410, Brunei Darussalam
2 Faculty of Mechanical Engineering, Opole University of Technology, 76 Proszkowska St., 45-758 Opole, Poland
3 Department of Mechanical Engineering, State Polytechnic of Banyuwangi, Indonesia
4 Department of Mathematic and Computational Sciences, University of Messina, Italy

Corresponding author

Advanced Mechanical and Mechatronic Systems

Volume 2 - Issue 2 - 2026

 About the journal
Submit your article

This study developed a deep learning-based image classification method for the automated assessment of aluminum edge quality after machining processes. The proposed approach classified edge conditions into three categories: Normal Edge, Burr Edge, and Sharp Edge. A Convolutional Neural Network (CNN) based on the VGG16 architecture was employed as the feature extraction backbone, with modifications to the final fully connected layers to accommodate the three-class classification task. The model was trained and evaluated on a dataset of 660 aluminum edge images captured under controlled laboratory conditions at the Robotic Manufacturing Laboratory, University of Brunei Darussalam. The training strategy employed a stratified split with 360 training images, 240 testing images, and 60 validation images. Data augmentation techniques (horizontal flip, rotation ±15°, brightness adjustment) were applied to enhance model generalization. The optimized model achieved an overall classification accuracy of 98.75% on the test set. Precision, recall, and F1-scores for all three classes exceeded 0.97. For practical deployment, the trained model was deployed on an NVIDIA Jetson Nano embedded platform, achieving an average inference time of 47 ms per image at an input resolution of 500×500 pixels (approximately 21 FPS). These results demonstrated the feasibility of real-time edge quality assessment for intelligent manufacturing applications.

Read Full-Text
Previous article
Next article
Read Full-Text
About this article

SUBMITTED: 15 January 2026
ACCEPTED: 09 May 2026
PUBLISHED: 8 June 2026
SUBMITTED to ACCEPTED: 114 days
DOI: https://doi.org/10.53623/amms.v2i2.995

Cite this article
Kirda, A. W. ., Gatnar, K. ., Muzaka, K. ., & Akbar, N. A. (2026). Machine Vision Lab Experiment Based Convolutional Neural Network for Potential Intelligent Manufacturing Applications. Advanced Mechanical and Mechatronic Systems, 2(2), 88–105. https://doi.org/10.53623/amms.v2i2.995
Citations
0
Share this article