Article Details

Title · Authors · Abstract · Keywords · DOI · References

A Review of Research on Magnetic Tile Defect Detection Techniques

HOU Zhi, LIU Xin

(College of Mechanical Engineering, Chongqing University of Technology, Chongqing 400054, China)

Section：Intelligent Manufacturing · Vol. 2026, Issue 15 · Pages：171-177 · 2096-4706（2026）15-0171-07 · CLC number：TP391.4；TM303 · Document code：A · DOI：10.19850/j.cnki.2096-4706.2026.15.032

Abstract

Addressing prominent challenges in magnetic tile defect detection, such as uneven arc surface illumination, strong texture interference, limited and imbalanced samples, and low-computational-power deployment, this paper systematically reviews and analyzes key technologies and methods in magnetic tile defect detection. First, it clarifies the important role of magnetic tiles in permanent magnet motors and the impact of magnetic tile defects on motor performance and operational safety, and systematically analyzes manufacturing processes and defect formation mechanisms of magnetic tiles. On this basis, it compares and analyzes main methods of two technical paths: traditional machine vision and Deep Learning. Finally, it summarizes characteristics of the two technical paths in terms of accuracy, speed, and deployment difficulty, and points out the future development trend of magnetic tile defect detection towards multimodal and flexible detection.

Keywords

magnetic tile defect detection; traditional machine vision; Deep Learning; lightweight deployment; review

References

  1. [1] Ma Bao, Xiang Chunsheng, Yang Chong, etc Research on Key Production Process Technology of Strontium Permanent Ferrite Magnetic Tile for External Rotor Fan [J]. Modern Mining, 2023, 39 (11): 245-248
  2. [2] Li Mingrong Causes and rapid detection of capillary cracks in the blank of permanent ferrite tile shaped magnets [J]. Magnetic Materials and Devices, 2006 (6): 57-58
  3. [3] Zhu Guiying, Shen Junmin Design of Automated Production Equipment for Automotive Motor Magnetic Tile [J]. Micro Motor, 2021, 54 (6): 103-106
  4. [4] Liu Song, Wang Yingang Analysis of Cracks in Strontium Permanent Ferrite Magnetic Tile [J]. Failure Analysis and Prevention, 2015, 10 (5): 301-304
  5. [5] Chen Wanqiong How to improve the grinding quality of permanent magnet ferrite tiles [J]. Mechanical and Electrical Engineering Technology, 2002 (S1): 147-148
  6. [6] Liu Guoping, Chang Zhen, Hu Lihua Curve fitting defect extraction method for magnetic tile surface image [J]. Mechanical Design and Manufacturing, 2015 (9): 107-110
  7. [7] Liu Guoping, Chang Zhen, Hu Xiuhua Gray contrast defect detection algorithm for the lower envelope of magnetic tile surface image [J]. Mechanical Science and Technology, 2017, 36 (2): 269-272
  8. [8] Zhu Zhixun, Li Heng, Zhao Lei, etc Research on image enhancement algorithm for magnetic tile surface defects based on improved homomorphic filtering combined with SMQT [J]. Optoelectronics and Laser, 2021, 32 (8): 818-825
  9. [9] Zhang Dunli, Zhou Guodong Surface defect detection method for magnetic tiles based on improved diffusion model [J]. China Testing, 2024, 50 (6): 28-34
  10. [10] Li Xueqin, Jiang Honghai, Liu Peiyong, etc Non downsampling Contourlet domain adaptive threshold surface magnetic tile surface defect detection [J]. Journal of Computer Aided Design and Graphics, 2014, 26 (4): 553-558
  11. [11] Yang Jianli, Yin Ming, Xiang Zhaowei, etc Surface defect detection of magnetic tiles based on non downsampling Shearlet transform [J]. Engineering Science and Technology, 2017, 49 (2): 217-224
  12. [12] Yang C L，Liu P Y，Yin G F，et al. Crack Detection in Magnetic Tile Images Using Nonsubsampled Shearlet Transform and Envelope Gray Level Gradient [J/OL].Optics & Laser Technology，2017，90：7-17
  13. [13] Zhong Z Y，Wang H X，Xiang D. Small Defect Detection Based on Local Structure Similarity for Magnetic Tile Surface [J/OL].Electronics，2022，12（1）：185.https://doi.org/10.3390/electronics12010185.
  14. [14] Zhang Lubin, Li Junfeng, Shen Junmin Research on Visual Inspection Method for Surface Line Defects of Micro Magnetic Tile [J]. Optoelectronics and Laser, 2019, 30 (9): 951-959
  15. [15] Zhang Zhenyao, Bai Ruilin, Guo Zhiqiang, etc Machine vision detection method for surface defects of magnetic tiles [J]. Optical Technology, 2014, 40 (5): 434-439
  16. [16] Zhang Zhenyao, Li Xin, Bai Ruilin Classification of Surface Defect Bias of Magnetic Tile Based on LSSVM [J]. Optoelectronic Engineering, 2013, 40 (8): 78-83
  17. [17] Zhang Jingai, Wang Jiangtao Magnetic tile surface quality recognition based on multi-scale convolutional neural network and intra class mixup operation [J]. Computer Applications, 2021, 41 (1): 275-279
  18. [18] Zhang Jin, Xie Jun, Liang Fengmei, etc Research on an Improved Method for Generating Magnetic Tile Defect Images in DCGANs Networks [J]. Small Microcomputer Systems, 2021, 42 (3): 589-594
  19. [19] Li Haoxuan, Liu Haixia Magnetic tile defect classification method based on transfer learning [J]. Journal of Testing Technology, 2022, 36 (4): 314-319
  20. [20] Wang Chunze, Lin Rongtai, Zhu Shidong, etc Surface defect detection of magnetic tiles based on small sample learning [J]. Industrial Control Computer, 2025, 38 (4): 12-13, 16
  21. [21] Tang J Y，Ao Z，Liu W A. A Novel Dual-student Reverse Knowledge Distillation Method for Magnetic Tile Defect Detection [J/OL].Scientific Reports，2025，15（1）：27279.https://doi.org/10.1038/s41598-025-12339-2.
  22. [22] Tang Shancheng, Lu Jianhui, Zhang Ying, etc Unsupervised surface defect detection of magnetic tiles for repairing suspected defect areas [J]. Journal of Zhejiang University (Engineering Edition), 2024, 58 (4): 718-728
  23. Liu Peiyong, Dong Jie, Xie Luofeng, etc Magnetic tile surface defect detection algorithm based on multi branch convolutional neural network [J]. Journal of Jilin University (Engineering Edition), 2023, 53 (5): 1449-1457
  24. [24] Xie L F，Xiang X，Xu H N，et al. FFCNN: A Deep Neural Network for Surface Defect Detection of Magnetic Tile [J].IEEE Transactions on Industrial Electronics，2021，68（4）：3506-3516.
  25. [25] Luo F，Cui Y，Wang X，et al. Adaptive Rotation Attention Network for Accurate Defect Detection on Magnetic Tile Surface [J].Mathematical Biosciences and Engineering: MBE，2023，20（9）：17554-17568.
  26. [26] Zhu Y Y，Xie L F，Yin M，et al. Convolution With Rotation Invariance for Online Detection of Tiny Defects on Magnetic Tile Surface [J].IEEE Transactions on Instrumentation and Measurement，2023，72：1-12.
  27. [27] Liang W，Sun Y. ELCNN: A Deep Neural Network for Small Object Defect Detection of Magnetic Tile [J].IEEE Transactions on Instrumentation and Measurement，2022，71：1-10.
  28. [28] Li J，Zhang Y，Liu H. Attention-based Convolution Neural Network for Magnetic Tile Surface Defect Classification and Detection [J/OL].Applied Soft Computing，2024，159：111631.https://doi.org/10.1016/j.asoc.2024.111631.
  29. [29] Zou Yihang, Zhu Shunmao, Huang Zhicai Improved YOLOv5s magnetic tile surface defect detection algorithm [J]. Journal of Xiamen University of Technology, 2023, 31 (5): 58-65
  30. [30] Luo Shoupu, Fu Changyou, Li Baobing, etc Magnetic tile defect detection algorithm based on YOLOv8n [J]. Journal of Ningxia Normal University, 2024, 45 (10): 64-73
  31. Guo Longyuan, Duan Houyu, Zhou Wuwei, etc Magnetic tile surface defect detection algorithm based on Mask R-CNN [J]. Computer Integrated Manufacturing Systems, 2022, 28 (5): 1393-1400
  32. Li Ming, Wei Lisheng Surface defect segmentation of magnetic tiles based on improved Deeplabv3+[J]. Journal of Electronic Measurement and Instrumentation, 2025, 39 (1): 50-56
  33. [33] Dong L，Zhu H J，Ren H P，et al. A Novel Lightweight MT-YOLO Detection Model for Identifying Defects in Permanent Magnet Tiles of Electric Vehicle Motors [J/OL].Expert Systems with Applications，2025，257：128247.https://doi.org/10.1016/j.eswa.2025.128247.
  34. [34] Shang X，Liu C，Wang Y. Surface defect detection of magnetic tiles based on an improved lightweight GhostNet network [J/OL].Engineering Research Express，2025，7（4）：045255.https://doi.org/10.1088/2631-8695/ad78c6.
  35. [35] Jiang C Z，Zhang X D，Xu B L，et al. MT-U2Net: Lightweight Detection Network for High-precision Magnetic Tile Surface Defect Localization [J/OL].Materials Today Communications，2024，41：110480.https://doi.org/10.1016/j.mtcomm.2024.110480.
  36. [36] Ma C，Pan Y R，Chen J F.Surface Defect Detection of Magnetic Tiles Based on YOLOv8-AHF [J/OL].Electronics，2025，14（14）：2857.https://doi.org/10.3390/electronics14142857.

About the authors

Hou Zhi (1977-), male, Han ethnicity, from Yunyang, Chongqing, associate professor, master's student, research direction: quality inspection and control.