A Review of Automatic Casting Defect Recognition Methods Based on Deep Learning

Shiyun  Wang; Xinhuan Bi

doi:10.62051/ijmee.v7n1.04

Authors

Shiyun Wang
Xinhuan Bi

DOI:

https://doi.org/10.62051/ijmee.v7n1.04

Keywords:

Industrial Application, Casting Defect Detection, Deep Learning, YOLO, Semantic Segmentation

Abstract

Casting defect detection is a crucial link in industrial production, directly affecting product quality and safety. Traditional manual inspection methods, due to their low efficiency, strong subjectivity, and high missed detection rates, can no longer meet the demands of modern intelligent manufacturing. In recent years, the breakthrough progress of deep learning technology in the field of image recognition has provided new solutions for automated casting defect detection. This paper systematically reviews automatic casting defect recognition methods based on deep learning, focusing on aspects such as algorithm improvements, practical applications, and future development directions. It discusses in detail the optimization strategies of object detection algorithms (such as the YOLO series, Mask R-CNN) and semantic segmentation algorithms (such as U-Net, Retina Net), and summarizes the latest achievements in industrial inspection system development. Finally, it prospects future research directions including self-supervised learning, unsupervised learning, and real-time quantitative analysis, aiming to promote the development of casting inspection technology towards intelligence and automation.

References

[1] Ma Yuchao, Fu Hualiang, Wu Peng, et al. Application Research of Mask R-CNN Model with Deep Network Adaptive Optimization in Casting Surface Defect Detection [J]. Modern Manufacturing Engineering, 2022(4):112-118.

[2] Yang Ke, Fang Cheng, Duan Liming. Automatic Detection of Casting Defects Based on Deep Learning Model Fusion [J]. Journal of Instrumentation, 2021, 42(11):150-159.

[3] Bao Chunsheng, Xie Gang, Wang Yin, et al. Casting Defect Detection Based on Deep Learning [J]. Special Casting & Nonferrous Alloys, 2021, 41(5):580-584.

[4] Liming D, Ke Y, Lang R. Research on Automatic Recognition of Casting Defects Based on Deep Learning [J]. IEEE ACCESS, 2021, 9:12209-12216.

[5] Mu Chunyang, Li Chuang, Ma Hang, et al. Lightweight Large Casting Weld Defect Detection Using Improved YOLOv7-tiny [J]. Modular Machine Tool & Automatic Manufacturing Technique, 2024, 32(7):1-5.

[6] Ge Qianfeng, Yuan Hao, Wang Yuan, et al. Defect Detection in Small Aluminum Casting Turbines Based on YOLOv5 [J]. Special Casting & Nonferrous Alloys, 2024, 44(06):760-765.

[7] Yan Zhilin, Zhong Shoucheng, Sun Jin, et al. Casting Surface Defect Detection Model Based on CCD-YOLOv5 Algorithm [J]. Special Casting & Nonferrous Alloys, 2024, 34(8):1-7.

[8] Chen Zihao, Zhang Long, Miao Jianhui, et al. TAE-YOLO: An Efficient Lightweight Algorithm for Casting Defect Detection [J]. Special Casting & Nonferrous Alloys, 2025, 35(3):1-6. (Note: Year 2025 seems prospective, kept as per original)

[9] Cai Biao, Shen Kuan, Fu Jinlei, et al. Research on Casting X-ray DR Image Defect Detection Based on Mask R-CNN [J]. Journal of Instrumentation, 2020, 41(3):1-8.

[10] [10] Cong Ming, Sun Xinhai, Wu Xiaoxuan. Defect Detection Method in Aluminum Alloy Casting X-ray Images Based on RetinaNet-AACIDD [J]. Modular Machine Tool & Automatic Manufacturing Technique, 2023, 31(12):1-8.

[11] Li Sha, Wang Yongxiong, Wang Zhe, et al. Casting Defect Detection by Fusing Local and Global Features [J]. Journal of Applied Sciences, 2024, 42(05):757-768.

[12] Li Chuang, Ma Hang, Mu Chunyang, et al. Lightweight Casting Weld Surface Defect Detection Using Improved YOLOv3 [J]. Modular Machine Tool & Automatic Manufacturing Technique, 2024, (01):156-159+163.

[13] Cai Zhenlin, Liu Bin, Wen Jinsong. Die-casting Defect Detection Based on ShuffleNetv2-plus-YOLOX Algorithm [J]. Special Casting & Nonferrous Alloys, 2024, 44(01):21-25.

[14] Lin J, Yao Y, Ma L, et al. Detection of a casting defect tracked by deep convolution neural network [J]. The International Journal of Advanced Manufacturing Technology, 2018, 97(1-4):573-581.

[15] Mery D. Aluminum Casting Inspection Using Deep Learning: A Method Based on Convolutional Neural Networks [J]. Journal of Nondestructive Evaluation, 2020, 39(10):14-18. (Note: Original had "39(10):14-18.", kept)

[16] Ekambaram D, Ponnusamy V. Identification of Defects in Casting Products by using a Convolutional Neural Network [J]. IEIE Transactions on Smart Processing & Computing, 2022, 11(3): [Incomplete citation in original]

[17] Wu Bo. Research on Key Technologies for Automatic Recognition of Internal Defects in Aerospace Titanium Alloy Castings [D]. Huazhong University of Science and Technology, 2022.

[18] Xue Lin, Wang Yunsen, Lu Yao, et al. Casting DR Image Defect Detection Based on Deep Learning [J]. Instrument Technique and Sensor, 2023, 33(3):1-5.

[19] Yang Kai. Research and Application of Precision Casting Defect Detection Method Based on Deep Learning [D]. Taiyuan University of Science and Technology, 2020.

[20] Wang Yuan. Research on Key Technologies and System Development for Surface Defect Detection of Small Aluminum Casting Turbines Based on Machine Vision [D]. Jiangsu University, 2023.

[21] Jing Peng. Research on Identification, Detection, and Localization Methods for Casting and Forging Burrs Based on Deep Learning [D]. Anhui University of Science and Technology, 2024.

[22] Zhou Leyao, Wang Donghong, Liu Shumei, et al. Development of Casting Process Data Management Software Based on PyQt5 [J]. Computer Era, 2023, (01):70-73+77.