• Optics and Precision Engineering
  • Vol. 32, Issue 1, 43 (2024)
Yuchao YAO1, Rui ZHOU1,2,*, Xing YAN1, Zhenzhong WANG3, and Na GAO4,5
Author Affiliations
  • 1Pen-Tung Sah Institute of Micro-Nano Science and Technology, Xiamen University, Xiamen36005,China
  • 2Innovation Laboratory for Sciences and Technologies of Energy Materials of Fujian Province (IKKEM), Xiamen361005, China
  • 3School of Aerospace Engineering, Xiamen University, Xiamen61102, China
  • 4College of Physical Science and Technology, Xiamen University, Xiamen361005, China
  • 5Jiujiang Research Institute of Xiamen University, Jiujiang332000, China
  • show less
    DOI: 10.37188/OPE.20243201.0043 Cite this Article
    Yuchao YAO, Rui ZHOU, Xing YAN, Zhenzhong WANG, Na GAO. Micron-level processing technology of microlens array (MLA) photolithography based on convolutional neural network[J]. Optics and Precision Engineering, 2024, 32(1): 43 Copy Citation Text show less
    One-step laser microlens array exposure
    Fig. 1. One-step laser microlens array exposure
    Exposure point judgement feature
    Fig. 2. Exposure point judgement feature
    Structure of Yolov5 network
    Fig. 3. Structure of Yolov5 network
    Module structure of Yolov5 network
    Fig. 4. Module structure of Yolov5 network
    Network module structure
    Fig. 5. Network module structure
    Indentify of exposure images
    Fig. 6. Indentify of exposure images
    Fitting curves between level of energy density during laser scanning and qualification rate
    Fig. 7. Fitting curves between level of energy density during laser scanning and qualification rate
    Dip angle of photoresist profile
    Fig. 8. Dip angle of photoresist profile
    Different platform moving speeds correspond to circularity of circle pattern
    Fig. 9. Different platform moving speeds correspond to circularity of circle pattern
    置信度类型原始YOLO算法改进YOLO算法
    召回率精确率召回率精确率
    0.45过曝点1008010098
    欠曝点956810067
    合格点989010096
    0.65过曝点1009610098
    欠曝点86739079
    合格点989210097
    0.85过曝点7710098100
    欠曝点5010027100
    合格点8510085100
    Table 1. Comparison of recognition effect

    速度/

    (μm·s-1

    功率/mV线能量密度/(kJ·m-1合格率/%
    1090990.6
    201708.589.2
    30240891.2
    403007.588.7
    Table 2. Statistics of qualified rate of multiple parameter combinations in optimal level of energy density region during laser scanning
    Yuchao YAO, Rui ZHOU, Xing YAN, Zhenzhong WANG, Na GAO. Micron-level processing technology of microlens array (MLA) photolithography based on convolutional neural network[J]. Optics and Precision Engineering, 2024, 32(1): 43
    Download Citation