Application of Deep Learning in Defect Detection During Metal Casting Processes

DOI: https://doi.org/10.63345/ijrmeet.org.v10.i10.2

Prof. Dr. Sanjay Kumar Bahl

Indus Intenational University

Haroli,  Una, Himachal Pradesh – 174301, India

Abstract

Metal casting is a widely utilized process in manufacturing, where defects such as cracks, voids, and porosity can significantly impact the quality and reliability of the final product. Traditional defect detection methods often rely on manual inspection or basic imaging techniques, which can be both time-consuming and prone to human error. Recent advancements in deep learning have provided powerful tools for automated, accurate defect detection in various manufacturing processes, including metal casting. This paper explores the application of deep learning techniques for defect detection in metal casting processes. Traditional defect detection methods, such as manual inspection, ultrasonic testing, and X-ray inspection, often suffer from limitations, including high costs, subjectivity, and time consumption. Recent advancements in deep learning, particularly convolutional neural networks (CNNs), have revolutionized automated defect detection, enabling more accurate, efficient, and scalable solutions.

This paper explores the application of deep learning for defect detection during metal casting processes. It highlights various architectures, datasets, and methodologies that can be utilized to improve the accuracy of defect identification. A case study on the application of CNNs demonstrates how this technique can outperform traditional methods, improving both defect detection rates and overall manufacturing efficiency. The research also addresses challenges such as the need for large annotated datasets and the model’s ability to generalize to different casting conditions. The results from this study show that deep learning has the potential to optimize manufacturing processes, reduce operational costs, and ensure product quality with higher consistency.It examines different architectures, datasets, and methodologies that enable high-performance defect identification. Furthermore, the manuscript discusses challenges, such as dataset quality and model generalization, while presenting a case study on the application of convolutional neural networks (CNNs) in metal casting defect detection. The results show significant improvements in defect detection accuracy and computational efficiency compared to traditional methods. The findings demonstrate the potential of deep learning in enhancing manufacturing processes, reducing costs, and improving product quality.

Keywords

Deep learning, defect detection, metal casting, convolutional neural networks, manufacturing, automated inspection, porosity, cracks, voids, computer vision.

References

1. https://www.google.com/url?sa=i&url=https%3A%2F%2Fwww.mdpi.com%2F2071-1050%2F14%2F5%2F2697&psig=AOvVaw3x5OE9ke9hUeVBeNXkBdF1&ust=1745170631751000&source=images&cd=vfe&opi=89978449&ved=0CBQQjRxqFwoTCLC4yILT5IwDFQAAAAAdAAAAABAE
2. https://www.google.com/url?sa=i&url=https%3A%2F%2Flink.springer.com%2Farticle%2F10.1007%2Fs10462-023-10475-7&psig=AOvVaw3x5OE9ke9hUeVBeNXkBdF1&ust=1745170631751000&source=images&cd=vfe&opi=89978449&ved=0CBQQjRxqFwoTCLC4yILT5IwDFQAAAAAdAAAAABAJ

1. Ahmed, M., & Yousuf, M. (2021). Deep learning-based automated defect detection for metal casting: A review. Journal of Manufacturing Processes, 61, 97-110. https://doi.org/10.1016/j.jmapro.2021.02.023
2. Barros, S., & Costa, P. (2020). Application of convolutional neural networks for defect detection in metal castings. International Journal of Advanced Manufacturing Technology, 108(7), 2213-2225. https://doi.org/10.1007/s00170-020-05123-x
3. Chen, G., & Liu, Z. (2020). Deep learning approaches for defect detection in industrial manufacturing systems. Journal of Intelligent Manufacturing, 31(2), 447-460. https://doi.org/10.1007/s10845-019-01471-2
4. Chetan, R., & Ravi, K. (2021). AI and deep learning in industrial defect detection: A case study of metal casting. Journal of Materials Science, 56(12), 9876-9889. https://doi.org/10.1007/s10853-021-05728-2
5. Dong, Y., & Zhao, W. (2021). Defect detection and classification in casting using deep convolutional networks. Journal of Manufacturing Science and Engineering, 143(3), 031011. https://doi.org/10.1115/1.4049589
6. Feng, X., & Zhang, H. (2020). Deep learning models for the prediction of casting defects: A review of methodologies and challenges. Materials & Design, 187, 108334. https://doi.org/10.1016/j.matdes.2019.108334
7. Ghosal, S., & Pal, S. (2019). Application of machine learning techniques in defect detection for metal casting processes. Journal of Materials Processing Technology, 271, 58-67. https://doi.org/10.1016/j.jmatprotec.2019.03.020
8. Gupta, A., & Kumar, S. (2020). Automated defect detection in metal casting using deep learning: An experimental study. Journal of Manufacturing Science and Technology, 24(2), 198-210. https://doi.org/10.1007/s11837-020-04339-0
9. He, X., & Wu, Y. (2019). Using deep learning for defect detection in metal casting and its applications in manufacturing industries. Journal of Materials Science & Technology, 35(8), 1590-1601. https://doi.org/10.1016/j.jmst.2019.03.045
10. Hong, J., & Sun, M. (2021). Application of CNNs for defect detection in industrial casting. International Journal of Computer Integrated Manufacturing, 34(9), 963-974. https://doi.org/10.1080/0951192X.2021.1908876
11. Li, S., & Liu, B. (2020). Development of deep learning-based approaches for defect detection in casting production. Procedia CIRP, 89, 151-156. https://doi.org/10.1016/j.procir.2020.04.025
12. Liu, W., & Zhang, J. (2020). Convolutional neural networks for defect detection in metal casting images. Materials Science and Engineering: A, 773, 138784. https://doi.org/10.1016/j.msea.2019.138784
13. Martin, R., & Wang, Q. (2019). A survey on applications of deep learning for defect detection in manufacturing. Journal of Manufacturing Systems, 52, 51-65. https://doi.org/10.1016/j.jmsy.2019.02.002
14. Niu, Y., & Li, X. (2020). Application of deep learning in defect detection of die-casting production: A practical approach. Materials, 13(6), 1314. https://doi.org/10.3390/ma13061314
15. Park, T., & Kim, M. (2021). Real-time defect detection in metal casting using deep neural networks. Journal of Computer-Aided Design & Applications, 18(3), 431-442. https://doi.org/10.14733/cadaps.2021.431-442
16. Patel, R., & Shah, A. (2020). Deep learning in industrial quality control: Applications in metal casting. International Journal of Advanced Manufacturing Technology, 108(1), 71-85. https://doi.org/10.1007/s00170-019-04333-1
17. Zhang, Q., & Huang, Z. (2020). Defect detection in metal casting using convolutional neural networks: A case study. Journal of Manufacturing Processes, 56, 167-178. https://doi.org/10.1016/j.jmapro.2020.03.020
18. Zhang, Y., & Li, J. (2021). Convolutional neural network-based defect classification for metal castings: A comparative study. Engineering Applications of Artificial Intelligence, 99, 104167. https://doi.org/10.1016/j.engappai.2021.104167
19. Zhou, X., & Li, H. (2020). Defect detection for metal casting using deep learning: A new framework and its application. Materials Science and Engineering: R: Reports, 143, 100523. https://doi.org/10.1016/j.mser.2020.100523
20. Zhuang, F., & He, Q. (2021). Automated defect detection using deep learning in manufacturing processes: The case of metal casting. Robotics and Computer-Integrated Manufacturing, 68, 102007. https://doi.org/10.1016/j.rcim.2020.102007