Abstract
In the process of preparing heavily doped silicon crystals for power electronics and solar power by the Czochralski(CZ) method, dislocations occur due to the presence of impurities and other factors. The presence of dislocations can affect the quality of single-crystal silicon crystalline columns. Therefore, we proposed the improved Yolov4-tiny model (Yolo-SPI) for detecting the occurrence of dislocations. For resolving the problem of low detection accuracy of the original model, we improve the neck part of the model by referring to the structure of the Path Aggregation Network (PAnet). Furthermore, we propose a feature enhancement module to improve the feature extraction ability of the model and introduce depthwise separable convolution to reduce the parameters. We produced the single-crystal silicon habit line dataset by using the industrial camera. The experimental results on our dataset show that the Yolo-SPI model outperforms Ghostnet-Yolov4, Mobilenetv3-Yolov4, EfficientDet-v0, and Nanodet. The Yolo-SPI model improves the Precision from 73.28% to 98.01% compared to the original Yolov4-tiny model and the Recall is also improved to 97.51%. At the same time, the number of parameters in the Yolo-SPI model is decreased from 5.87M to 2.05M compared to the Yolov4-tiny model. Our model also beats other models in the speed of detection, reaching 133FPS. In practical applications, our model achieves higher accuracy and faster detection speed.
Similar content being viewed by others
Data Availability
The processed data required to reproduce these findings cannot be shared at this time as the data also forms part of an ongoing study.
References
Voronkov V, Dai B, Kulkarni M (2011) Fundamentals and engineering of the czochralski growth of semiconductor silicon crystals. In: Comprehensive semiconductor science and technology, pp 81–169
Smirnova O, Durnev N, Shandrakova K, Mizitov E, Soklakov V (2008) Optimization of furnace design and growth parameters for si cz growth, using numerical simulation. J Cryst Growth 310(7-9):2185–2191
Su W, Zuo R, Mazaev K, Kalaev V (2010) Optimization of crystal growth by changes of flow guide, radiation shield and sidewall insulation in cz si furnace. J Cryst Growth 312(4):495– 501
Kamada K, Kurosawa S, Prusa P, Nikl M, Kochurikhin VV, Endo T, Tsutumi K, Sato H, Yokota Y, Sugiyama K (2014) Cz grown 2-in. size ce: Gd3 (al, ga) 5o12 single crystal; relationship between al, ga site occupancy and scintillation properties. Opt Mater 36(12):1942–1945
Sueoka K, Ikeda N, Yamamoto T, Kobayashi S (1993) Morphology and growth process of thermally induced oxide precipitates in czochralski silicon. J Appl Phys 74(9):5437–5444
Nakao S, Ando T, Shikida M, Sato K (2007) Effect of temperature on fracture toughness in a single-crystal-silicon film and transition in its fracture mode. J Micromech Microeng 18(1):015026
Minor A, Lilleodden E, Jin M, Stach E, Chrzan D, Morris J (2005) Room temperature dislocation plasticity in silicon. Phil Mag 85(2-3):323–330
Tan T, Tice W (1976) Oxygen precipitation and the generation of dislocations in silicon. The Philosophical Magazine: A Journal of Theoretical Experimental and Applied Physics 34(4):615– 631
Zhang J, Liu H, Cao J, Zhu W, Jin B, Li W (2020) A deep learning based dislocation detection method for cylindrical crystal growth process. Appl Sci 10(21):7799
Demant M, Virtue P, Kovvali AS, Yu SX, Rein S (2018) Deep learning approach to inline quality rating and mapping of multi-crystalline si-wafers. In: 35th European photovoltaic solar energy conference, p 5
Girshick R, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 580–587
Girshick R (2015) Fast r-cnn. In: Proceedings of the IEEE international conference on computer vision, pp 1440–1448
Ren S, He K, Girshick R, Sun J (2015) Faster r-cnn: towards real-time object detection with region proposal networks. Adv Neural Inf Process Syst 28:91–99
Dai J, Li Y, He K, Sun J (2016) R-fcn: object detection via region-based fully convolutional networks. In: Advances in neural information processing systems, pp 379–387
He K, Gkioxari G, Dollár P, Girshick R (2017) Mask r-cnn. In: Proceedings of the IEEE international conference on computer vision, pp 2961–2969
Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu C-Y, Berg AC (2016) Ssd: single shot multibox detector. In: European conference on computer vision. Springer, pp 21–37
Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: unified, real-time object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 779–788
Bochkovskiy A, Wang C-Y, Liao H-YM (2020) Yolov4: optimal speed and accuracy of object detection. arXiv:2004.10934
Wang C-Y, Bochkovskiy A, Liao H-Y M (2021) Scaled-yolov4: scaling cross stage partial network. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 13029–13038
Redmon J, Farhadi A (2018) Yolov3: an incremental improvement. arXiv:1804.02767
Xu D, Wu Y (2021) Fe-yolo: a feature enhancement network for remote sensing target detection. Remote Sens 13(7):1311
Redmon J, Farhadi A (2017) Yolo9000: better, faster, stronger. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7263–7271
Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3431–3440
Wang C-Y, Liao H-YM, Wu Y-H, Chen P-Y, Hsieh J-W, Yeh I-H (2020) Cspnet: a new backbone that can enhance learning capability of cnn. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition workshops, pp 390– 391
Lin T-Y, Dollár P, Girshick R, He K, Hariharan B, Belongie S (2017) Feature pyramid networks for object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2117–2125
Jiang Z, Zhao L, Li S, Jia Y (2020) Real-time object detection method based on improved yolov4-tiny
Zheng Z, Wang P, Ren D, Liu W, Ye R, Hu Q, Zuo W (2021) Enhancing geometric factors in model learning and inference for object detection and instance segmentation. IEEE Trans Cybern
Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z (2016) Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2818–2826
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778
Szegedy C, Ioffe S, Vanhoucke V, Alemi AA (2017) Inception-v4, inception-resnet and the impact of residual connections on learning. In: Thirty-first AAAI conference on artificial intelligence
Liu S, Qi L, Qin H, Shi J, Jia J (2018) Path aggregation network for instance segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 8759– 8768
Chollet F (2017) Xception: deep learning with depthwise separable convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1251–1258
Lu Y, Zhang L, Xie W (2020) olo-compact: an efficient yolo network for single category real-time object detection. In: 2020 Chinese control and decision conference (CCDC). IEEE, pp 1931–1936
Tan M, Le Q (2019) Efficientnet: rethinking model scaling for convolutional neural networks. In: International conference on machine learning. PMLR, pp 6105–6114
Xiong Y, Liu H, Gupta S, Akin B, Bender G, Kindermans PJ, Tan M, Singh V, Chen B (2020) Mobiledets: searching for object detection architectures for mobile accelerators. arXiv
Han K, Wang Y, Tian Q, Guo J, Xu C (2020) Ghostnet: More features from cheap operations. In: 2020 IEEE/CVF conference on computer vision and pattern recognition (CVPR)
RangiLyu (2021) Nanodet-plus: super fast and high accuracy lightweight anchor-free object detection model. https://github.com/RangiLyu/nanodet
Bao Y, Song K, Liu J, Wang Y, Yan Y, Yu H, Li X (2021) Triplet-graph reasoning network for few-shot metal generic surface defect segmentation. IEEE Trans Instrum Meas 70:1–11. https://doi.org/10.1109/TIM.2021.3083561
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Yuting, S., Hongxing, L. A deep learning based dislocation detection method for cylindrical silicon growth process. Appl Intell 53, 9188–9203 (2023). https://doi.org/10.1007/s10489-022-03800-0
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-022-03800-0