Improving Water Tap Production Lines: A Proof of Concept for Deep Learning-Based Defect Detection System Development Improving Water Tap Production Lines: A Proof of Concept for Deep Learning-Based Defect Detection System Development
Article Sidebar
Main Article Content
บทคัดย่อ
This paper presents the development of a deep learning model designed to identify two classes of object images: the work-in-process of a certain copper-based alloy water tap. The dataset consisted of 316 images of good parts and 320 images of defective parts. Both classes of images underwent processing using oversampling techniques for data augmentation to increase the number of images to 1,000 images per class, before transformation. Subsequently, the processed data were used to train six transfer learning models, including ResNet50, MobileNet, Xception, InceptionV3, EfficientNetB0, and DenseNet121. The results demonstrate 100% accuracy, precision, recall, and F1-score for ResNet50 and EfficientNetB0 when evaluated on the validation and test sets. However, considering the size of the models, it was found that EfficientNetB0 is only 15.48 MB, whereas ResNet50 is 90.03 MB. Therefore, EfficientNetB0 emerges as the optimal deep learning model for the development of an automatic detection and rejection station in the production line of water tap manufacturers in the future. One of the contributions of this study is providing proof of concept for using image processing and deep learning to enhance productivity within a manufacturing environment.
Article Details
References
W. A. E. L. Tayel, A. E. D. Z. Ali, H. F. A. E. Maksoud, S. H. Darwish and M. E. Morsy. (2023, 18 - 20 Jul). Productivity Improvement Based on Measuring the Overall Equipment Effectiveness in Metal Formation Production Stages. In 2023 International Telecommunications Conference (ITC-Egypt) (pp. 715-718). Alexandria, Egypt. doi: 10.1109/ITC-Egypt58155.2023.10206071
A. Piyasinchart, P. Boonpoor, T. Thammachai and T. Daengsi. (2023, 11 - 12 December). Detection of Defects in Work-in-Process Products Using Deep Learning: A Case of a Water Tap Production Line. In 2023 6th INTERNATIONAL SEMINAR ON RESEARCH OF INFORMATION TECHNOLOGY AND INTELLIGENT SYSTEMS (ISRITI), Indonesia.
T. Daengsi, K. Cheevanichapan, U. Soteyome and T. Thimthong. (2022, 8 - 9 December). Irrigation Management: A Pilot Study for Automatic Water Level Measurement and Report System Development Using Machine Learning Associated with Modified Images. In 2022 5th INTERNATIONAL SEMINAR ON RESEARCH OF INFORMATION TECHNOLOGY AND INTELLIGENT SYSTEMS (ISRITI) (pp. 543-547). Yogyakarta, Indonesia. doi: 10.1109/ISRITI56927.2022.10052826
T. Prabaharan et al. (2020, 18 – 23 July). Studies on application of image processing in various fields: An overview. In International Conference on Advanced Materials Behavior & Characterization (ICAMBC_2020). Chennai, India. doi:10.1088/1757-899X/961/1/012006
K.G. Dhal, A. Das, J. Gálvez, S. Ray, and S. Das. (2020). An Overview on Nature-Inspired Optimization Algorithms and Their Possible Application in Image Processing Domain. Pattern Recognition and Image Analysis, 30, 614–631. https://doi.org/10.1134/S1054661820040100
Gartner. (2024, 20 January). What Is Artificial Intelligence?. https://www.gartner.com/en/topics/artificial-intelligence
H. Ismail Fawaz, G. Forestier, J. Weber, L. Idoumghar and P. -A. Muller. (2018, December 10 – 13). Transfer learning for time series classification. In 2018 IEEE International Conference on BIG DATA (pp. 1367-1376). Seattle, WA, USA. doi: 10.1109/BigData.2018.8621990.
M. Y. Ansari and M. Qaraqe. (2023). MEFood: A Large-Scale Representative Benchmark of Quotidian Foods for the Middle East. IEEE Access, 11, 4589-4601. doi: 10.1109/ACCESS.2023.3234519
F. Zhuang et al. (2021). A Comprehensive Survey on Transfer Learning. In Proceedings of the IEEE, 109(1),
-76. doi: 10.1109/JPROC.2020.3004555.
D. Yang and Z. Luo. (2023). A Parallel Processing CNN Accelerator on Embedded Devices Based on Optimized MobileNet. IEEE Internet of Things Journal, 10(21), 18844-18852. doi: 10.1109/JIOT.2023.3277869
M. S. H. Shovon, S. J. Mozumder, O. K. Pal, M. F. Mridha, N. Asai and J. Shin. (2023). PlantDet: A Robust Multi-Model Ensemble Method Based on Deep Learning For Plant Disease Detection. IEEE Access, 11, 34846–34859. doi: 10.1109/access.2023.3264835
Tasci, E. (2020, 15 August). Voting combinations-based ensemble of fine-tuned convolutional neural networks for food image recognition. Multimedia Tools and Applications An International Journal, 79, 30397–30418. doi: 10.1007/s11042-020-09486-1
T. T. Tai, D. N. H. Thanh and N. Q. Hung. (2022). A Dish Recognition Framework Using Transfer Learning. IEEE Access, 10, 7793–7799. doi: 10.1109/access.2022.3143119
Y. Soullard, P. Tranouez, C. Chatelain, S. Nicolas and T. Paquet. (2020). Multi-scale gated fully convolutional DenseNets for semantic labeling of historical newspaper images. Pattern Recognition Letters, 131, 435–441. https://doi.org/10.1016/j.patrec.2020.01.026
K. -W. Lee, D. -K. Ko and S. -C. Lim. (2021, October). Toward Vision-Based High Sampling Interaction Force Estimation with Master Position and Orientation for Teleoperation. IEEE Robotics and Automation Letters, 6(4), 6640-6646. doi: 10.1109/LRA.2021.3094848
X. Dong, M. A. Garratt, S. G. Anavatti and H. A. Abbass. (2022, November). MobileXNet: An Efficient Convolutional Neural Network for Monocular Depth Estimation. IEEE Transactions on Intelligent Transportation Systems, 23(11), 20134-20147. doi: 10.1109/TITS.2022.3179365
D. Saini et al. (2023). MBAHIL: Design of a Multimodal Hybrid Bioinspired Model for Augmentation of Hyperspectral Imagery via Iterative Learning for Continuous Efficiency Enhancements. IEEE Access, 11, 47781-47793. doi: 10.1109/ACCESS.2023.3273529
Jang and U. -H. Kim. (2023, September). On the Study of Data Augmentation for Visual Place Recognition. IEEE Robotics and Automation Letters, 8(9), 6052-6059. doi: 10.1109/LRA.2023.3301778
A. Anaya-Isaza and L. Mera-Jiménez. (2022). Data Augmentation and Transfer Learning for Brain Tumor Detection in Magnetic Resonance Imaging. IEEE Access, 10, 23217-23233. doi: 10.1109/ACCESS.2022.3154061
T. Makkawal, S. Duangsupa and R. Panthong. (2022, December). Development of Web Application for Classification of Variegated Banana with Machine Learning. Journal of Applied Information Technology, 8(2), 56-66. https://ph02.tci-thaijo.org/index.php/project-journal/article/view/246980
P. SriboonruangSoftware, P. TananchaiSign, K. Khaggathog, W. Vijitkunsawat and P. Anunvrapong. (2022, December). Software Sign Language Translator to Text and Speech by Using the Landmarks Technique of MediaPipe. The Journal of Industrial Technology : Suan Sunandha Rajabhat University, 10(2), 66-76. https://ph01.tci-thaijo.org/index.php/fit-ssru/article/view/249506/170217
H. Benbrahim and A. Behloul. (2021). Fine-tuned Xception for Image Classification on Tiny ImageNet. In 2021 International Conference on Artificial Intelligence for Cyber Security Systems and Privacy (AI-CSP) (pp. 1-4). El Oued, Algeria. doi: 10.1109/AI-CSP52968.2021.9671150
J. Yang, Z. Zeng, K. Wang, H. Zou, and L. Xie. (2021, AugustGarbageNet: A Unified Learning Framework for Robust Garbage Classification. IEEE Transactions on Artificial Intelligence, 2(4), 372–380. doi: 10.1109/TAI.2021.3081055
B. Fu, S. Li, J. Wei, Q. Li, Q. Wang and J. Tu. (2021). A Novel Intelligent Garbage Classification System Based on Deep Learning and an Embedded Linux System. IEEE Access, 9, 131134–131146. doi: 10.1109/ACCESS.2021.3114496
S. Chatterjee, D. Hazra, and Y.-C. Byun. (2022). IncepX-Ensemble: Performance Enhancement Based on Data Augmentation and Hybrid Learning for Recycling Transparent PET Bottles. IEEE Access, 10, 52280–52293. doi: 10.1109/ACCESS.2022.3174076
P. Zhou, B. Gao, S. Wang, and T. Chai. (2022, March). Identification of Abnormal Conditions for Fused Magnesium Melting Process Based on Deep Learning and Multisource Information Fusion. IEEE Transactions on Industrial Electronics, 69(3), 3017–3026. doi: 10.1109/TIE.2021.3070512
N. Chen et al. (2022, December). Data Augmentation and Intelligent Recognition in Pavement Texture Using a Deep Learning. IEEE Transactions on Intelligent Transportation Systems, 23(12), 25427–25436. doi: 10.1109/TITS.2022.3140586
X. Ke, G. Zeng and W. Guo. (2023, May). An Ultra-Fast Automatic License Plate Recognition Approach for Unconstrained Scenarios. IEEE Transactions on Intelligent Transportation Systems, 24(5), 5172–5185. doi: 10.1109/TITS.2023.3237581
J. Sha, M. Fan, B. Cao and B. Ye. (2023). Deep Transfer Learning-Enabled Hardness Classification of Bearing Rings Using Pulsed Eddy Current Testing. IEEE Transactions on Instrumentation and Measurement, 72, 1–9. doi: 10.1109/TIM.2023.3293881
F. G. Bloedorn and C. G. Webber. (2023, March). Transfer Learning applied to a Classification Task: a Case Study in the Footwear Industry. IEEE Latin America Transactions, 21(3), 427–433. doi: 10.1109/TLA.2023.10068846