CONSTRUCTION OF PLATFORM FOR DEFECT DETECTION AND ALGORITHM RESEARCH ON INNER WALL OF QUARTZ CRUCIBLES

Zhao Qian; Xu Dongwei; Miao Zhengli; Zheng Xuan; Zhao Man

doi:10.19912/j.0254-0096.tynxb.2023-1923

PDF(2389 KB)

Acta Energiae Solaris Sinica ›› 2025, Vol. 46 ›› Issue (3) : 421-427. DOI: 10.19912/j.0254-0096.tynxb.2023-1923

CONSTRUCTION OF PLATFORM FOR DEFECT DETECTION AND ALGORITHM RESEARCH ON INNER WALL OF QUARTZ CRUCIBLES

Zhao Qian¹, Xu Dongwei¹, Miao Zhengli¹, Zheng Xuan^1,2, Zhao Man²

Author information +

History +

Abstract

At present, the defects of quartz crucible mainly use manual eye inspection, which can not complete the accurate classification and full count only by manual. In this paper, a set of quartz crucible defect detection platform was built by using a 6-DOF manipulator and a rotating table, and high resolution images of crucible defects were obtained by combining backlight source and high speed camera. Simultaneously, the paper proposes an improved YOLOv5 algorithm for detecting crucible defects, capable of identifying various defect types such as impurity black spots, bubbles, and white spots. Firstly, K means clustering algorithm is used to generate anchor box suitable for crucible defect data sets, and then small target detection layer is added to improve the detection effect of small targets. Finally, omni-Dimensional dynamic convolution （ODConv） and the efficient channel attention （ECA） are used to make the network pay more attention to the targets to be detected without increasing too much computation. The experimental results show that in the self-built quartz crucible defect data set, the improved algorithm mAP@0.5 is 98.88% and the detection speed reaches 138 fps, which can meet the requirements of industrial detection.

Key words

monocrystal silicon / crucibles / defects / deep learning / YOLOv5s / small object detection

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

Zhao Qian, Xu Dongwei, Miao Zhengli, Zheng Xuan, Zhao Man. CONSTRUCTION OF PLATFORM FOR DEFECT DETECTION AND ALGORITHM RESEARCH ON INNER WALL OF QUARTZ CRUCIBLES[J]. Acta Energiae Solaris Sinica. 2025, 46(3): 421-427 https://doi.org/10.19912/j.0254-0096.tynxb.2023-1923

References

[1] WARDEN G K, JUEL M, GAWEŁ B A, et al.Recent developments on manufacturing and characterization of fused quartz crucibles for monocrystalline silicon for photovoltaic applications[J]. Open ceramics, 2023, 13: 100321.
[2] BETEKBAEV A A, MUKASHEV B N, PELISSIER L, et al.Comparison of the characteristics of solar cells fabricated from multicrystalline silicon with those fabricated from silicon obtained by the monolike technology[J]. Semiconductors, 2016, 50(8): 1085-1091.
[3] 韩博. 结构厚度和工艺参数对多晶硅缺陷形成的数值分析[D]. 银川: 宁夏大学, 2022.
HAN B.Numerical analysis of structural thickness and process parameters on defect formation of polysilicon[D]. Yinchuan: Ningxia University, 2022.
[4] 史珺, 宗卫峰. 铸锭炉热场对坩埚可靠性影响的机理研究: 硅液对于石英坩埚的侵蚀及其与温度、坩埚材质和热场的关系分析[J]. 太阳能学报, 2014, 35(3): 502-507.
SHI J, ZONG W F.Research on mechanism of impact of casting furnace thermal field on crucible reliability: analysis of the crucible corrotion by liquid silicon and its relationship to temperature, materials and thermal field[J]. Acta energiae solaris sinica, 2014, 35(3): 502-507.
[5] 王飞, 崔凤奎, 刘建亭, 等. 基于机器视觉的玻璃表面缺陷检测系统的研究[J]. 玻璃与搪瓷, 2009, 37(5): 6-10.
WANG F, CUI F K, LIU J T, et al.A study on the glass surface defect inspection system based on machine vision[J]. Glass & enamel, 2009, 37(5): 6-10.
[6] 姜乐兵, 宋飞虎, 裴永胜, 等. 基于粒子群优化Gabor滤波器的钢板表面缺陷检测[J]. 传感器与微系统, 2023, 42(11): 135-138.
JIANG L B, SONG F H, PEI Y S, et al.Surface defect detection of steel plate based on PSO-Gabor filter[J]. Transducer and microsystem technologies, 2023, 42(11): 135-138.
[7] 王昌书, 黄沿江, 张宪民, 等. 一种基于机器视觉的曲面玻璃划痕缺陷检测方法[J]. 自动化技术与应用, 2020, 39(1): 134-139.
WANG C S, HUANG Y J, ZHANG X M, et al.A method of scratch defects detection for curved glass based on machine vision[J]. Techniques of automation and applications, 2020, 39(1): 134-139.
[8] 喻宾扬, 王召巴, 金永. 玻璃缺陷检测新方法的研究[J]. 传感器与微系统, 2008, 27(8): 60-62.
YU B Y, WANG Z B, JIN Y.Research on new method of glass-defect detection[J]. Transducer and microsystem technologies, 2008, 27(8): 60-62.
[9] 刘国华, 孙宝佳. 基于机器人视觉的坩埚缺陷检测系统[J]. 机械设计, 2019, 36(2): 40-45.
LIU G H, SUN B J.Crucible defect detection system based on robot vision[J]. Journal of machine design, 2019, 36(2): 40-45.
[10] 孙维康, 刘曰涛, 黄浩, 等. 模糊识别算法在坩埚缺陷检测系统的应用[J]. 组合机床与自动化加工技术, 2019(12): 98-102.
SUN W K, LIU Y T, HUANG H, et al.Application of fuzzy recognition algorithm in crucible defect detection system[J]. Modular machine tool & automatic manufacturing technique, 2019(12): 98-102.
[11] 周颖, 毛立, 张燕, 等. 改进CNN的太阳电池缺陷识别方法研究[J]. 太阳能学报, 2020, 41(12): 69-76.
ZHOU Y, MAO L, ZHANG Y, et al.Research on defect detection and classification for solar cells based on improved convolutional neural network[J]. Acta energiae solaris sinica, 2020, 41(12): 69-76.
[12] 王道累, 李明山, 姚勇, 等. 改进SSD的光伏组件热斑缺陷检测方法[J]. 太阳能学报, 2023, 44(4): 420-425.
WANG D L, LI M S, YAO Y, et al.Method of hotspot detection of photovoltaic panels modules on improved SSD[J]. Acta energiae solaris sinica, 2023, 44(4): 420-425.
[13] 蒋兴群, 刘波, 宋力, 等. 基于改进YOLO-v3的风力机叶片表面损伤检测识别[J]. 太阳能学报, 2023, 44(3): 212-217.
JIANG X Q, LIU B, SONG L, et al.Surface damage detection and recognition of wind turbine blade based on improved YOLO-v3[J]. Acta energiae solaris sinica, 2023, 44(3): 212-217.