Casting Defect Detection and Recognition Technology Based on Deep Learning

Ziqing Song; Yupeng Yao; Jingbin Yang

doi:10.62051/ijcsit.v7n1.03

Authors

Ziqing Song
Yupeng Yao
Jingbin Yang

DOI:

https://doi.org/10.62051/ijcsit.v7n1.03

Keywords:

Deep learning, Casting defects, Defect detection, Machine vision

Abstract

Aiming at the existing casting defect detection and recognition technology based on deep learning, the limitations of traditional manual detection methods and the advantages of machine vision technology in improving detection accuracy and efficiency are discussed. The research status of casting defect detection is analyzed, including surface defect and internal defect detection technology, as well as image preprocessing, algorithm framework optimization and design innovation direction. By reviewing a variety of deep learning models and algorithms, such as CNN, transfer learning, lightweight models, and improved U-Net models, the potential of these techniques in improving the efficiency and accuracy of defect detection is demonstrated. In addition, this paper discusses the three key modules of visual defect detection technology: image acquisition, image preprocessing and image analysis, and compares the characteristics of one-stage and two-stage object detection algorithms. Finally, the main research directions of casting defect detection are summarized to provide directions for future research.

Downloads

Download data is not yet available.

References

[1] Keerthana B. Chigateri, Sanath Poojary, Sambhram Padmashali, Recognition and classification of casting defects using the CNN algorithm, Materials Today: Proceedings, Volume 92, Part 1, 2023, Pages 121-130, ISSN 2214-7853.

[2] Rupesh Gupta, Vatsala Anand, Sheifali Gupta, Deepika Koundal, Deep learning model for defect analysis in industry using casting images, Expert Systems with Applications, Volume 232, 2023, 120758, ISSN 0957-4174.

[3] Rohit Lal, Bharath Kumar Bolla, E Sabeesh, Efficient Neural Net Approaches in Metal Casting Defect Detection, Procedia Computer Science, Volume 218, 2023, Pages 1958-1967, ISSN 1877-0509.

[4] Haoyue Liu, Xiyang Wu, Ning Yan, Shuaipeng Yuan, Xiaodong Zhang,A novel image registration-based dynamic photometric stereo method for online defect detection in aluminum alloy castings, Digital Signal Processing, Volume 141, 2023, 104165, ISSN 1051-2004.

[5] Liang, W., Wang, S., & Wang, H. (2023). Named entity recognition for magnesium alloy casting defects based on BERT pre-training model. Journal of Heilongjiang University of Science and Technology, *33*(2), 191–195.

[6] Xue, L., Wang, Y., Lu, Y., et al. (2023). Casting defect detection in DR images based on deep learning. Instrument Technique and Sensors, (3), 94–97+103.

[7] Liu, X.J., Zhou, P.F., Chen, J.H., et al. (2023). Research on automatic identification technology of casting defects based on Relief algorithm and Adaboost-SVM. In China Foundry Association & Foundry Engineering Journal (Eds.), Proceedings of the 19th Annual Conference of China Foundry Association (p. 6). Shanghai Aerospace Precision Machinery Research Institute.

[8] Liu, T. (2023). Research on rapid recognition technology for turning edge contour of aluminum alloy die castings [Master's thesis, Yanshan University].

[9] Wei, B. (2023). Casting defect detection based on laser ultrasound and convolutional neural network [Master's thesis, Xi'an Shiyou University].

[10] Wang, F., & Zhang, S. (2023). Research on automatic detection and identification of casting defects based on improved deep learning algorithm. Automation & Instrumentation, 38(9), 82–86.

[11] Li, C., Ma, X., Mu, C., et al. (2024). Lightweight detection of surface defects in casting welds based on improved YOLOv3. Modular Machine Tool & Automatic Manufacturing Technique, (1), 156–159, 163.

[12] Hongquan Jiang, Xinguang Zhang, Chenyue Tao, Song Ai, Yonghong Wang, Jicheng He, He Yang, Deyan Yang, Casting defect region segmentation method based on dual-channel encoding–fusion decoding network, Expert Systems with Applications, Volume 247, 2024, 123254, ISSN 0957-4174.

[13] Zhao, X., Feng, P., Shen, K., et al. (2022, October). Research on defect detection algorithm in railway casting DR images based on deep learning. In Proceedings of the 17th Chinese Conference on Stereology and Image Analysis (p. 2). Key Laboratory of Optoelectronic Technology and Systems, Ministry of Education, Chongqing University; Engineering Research Center of Industrial Computed Tomography Nondestructive Testing, Ministry of Education, Chongqing University.

[14] Yan, X., Wang, D., & Wu, W., et al. (2023). Image defect detection of aluminum alloy wheel hub castings based on deep learning. Special Casting & Nonferrous Alloys, 43(4), 457–463.

[15] İsmail Enes Parlak, Erdal Emel, Deep learning-based detection of aluminum casting defects and their types, Engineering Applications of Artificial Intelligence, Volume 118, 2023, 105636, ISSN 0952-1976.