ISSN 1004-4140
CN 11-3017/P
| Citation: |
HUANG Y F, LI X, CHEN P. A Three-dimensional BGA Solder Ball Defect Detection Method Based on YOLOv8 and Metric Analysis[J]. CT Theory and Applications, 2025, 34(2): 235-243. DOI: 10.15953/j.ctta.2024.237. (in Chinese).
|
With the increasing integration and miniaturization of electronic devices, the detection of solder ball defects in ball grid array (BGA) packaging has become extremely important. In this study, a three-dimensional (3D) defect detection method for BGA solder balls was proposed. Computed tomography (CT) scanning was used to reconstruct internal 3D images of BGA chips. The YOLOv8 algorithm was utilized to develop a 3D target detection model. The void size ratio in the training dataset was adjusted to enhance sensitivity to void defects. This method identified void defects in 3D BGA images and generated candidate targets. A defect size measurement algorithm was designed to segment the internal voids in the solder balls. The void ratio was calculated to identify defects that met predefined criteria. The measurement algorithm was integrated into the dataset construction process. This integration of automated defect labeling reduced the workload of 3D annotation. Experiments were conducted on a 3D BGA chip image dataset. This method achieved high detection rates and low false detection rates. These results validate the effectiveness and reliability of the proposed method.
| [1] |
OU X Y, CHEN X, XU X N, et al. Recent development in X-ray imaging technology: Future and challenges[J]. Research, 2021, 20219892152-9892152.
|
| [2] |
李井元. 基于X射线图像的BGA焊球气泡缺陷检测技术研究[D]. 成都: 电子科技大学, 2019.
LI J Y. Research on voids detection technology in BGA solder balls based on X-ray image[D]. Chengdu: University of Electronic Science and Technology of China, 2019. (in Chinese).
|
| [3] |
TERRA N M, SANTIAGO S B, VIEIRA A K, et al. Advancing surface mount technology quality: A computer-assisted approach for enhanced X-ray inspection of solder joints[J/OL]. The International Journal of Advanced Manufacturing Technology, 2024, 131(12): 5897-5904.
|
| [4] |
AKDENIZ C T, DOKUR Z, ÖLMEZ T. Detection of BGA solder defects from X-ray images using deep neural network[J/OL]. Turkish Journal of Electrical Engineering & Computer Sciences, 2020, 28(4): 2020-2029.
|
| [5] |
曹鹏娟. 基于深度学习的球栅阵列焊点空洞缺陷检测方法研究[D]. 太原: 中北大学, 2023. DOI: 10.27470/d.cnki.ghbgc.2023.000467.
CAO P J. Deep learning-based method for detecting void defects in solder joints of ball grid array[D]. Taiyuan: North University of China, 2023. DOI:10.27470/d.cnki.ghbgc.2023.000467. (in Chinese).
|
| [6] |
刘永斌. 基于深度学习的BGA焊球空洞缺陷检测技术研究[D]. 沈阳: 沈阳建筑大学, 2020. DOI: 10.27809/d.cnki.gsjgc.2020.000578.
LIU Y B. Research on detection technology of BGA solder void defect based on deep learning[D]. Shenyang: Shenyang Jianzhu University, 2020. DOI:10.27809/d.cnki.gsjgc.2020.000578. (in Chinese).
|
| [7] |
SUMIMOTO T, MARUYAMA T, AZUMA Y, et al. Detection of defects of BGA by tomography imaging[J]. Journal on Systemics, Cybernetics and Informatics, 2005, 3: 10-14.
|
| [8] |
KHAN U, YASIN A, ABID M, et al. A methodological review of 3D reconstruction techniques in tomographic imaging[J/OL]. Journal of Medical Systems, 2018, 42(10): 190.
|
| [9] |
潘光勇, 张敏霞, 鲍熠朗, 等. 工业CT在电磁线圈缺陷检测中的应用[J]. CT理论与应用研究, 2019, 28(2): 205-212. DOI: 10.15953/j.1004-4140.2019.28.02.06.
PAN G Y, ZHANG M X, BAO Y L, et al. Application of industrial computerized tomography in testing of fault magnetic coil[J]. CT Theory and Applications, 2019, 28(2): 205-212. DOI: 10.15953/j.1004-4140.2019.28.02.06. (in Chinese).
|
| [10] |
张婷婷, 钟朝辉, 张奥博, 等. 股前外侧穿支皮瓣术前CT血管成像扫描及重建方案研究[J]. CT理论与应用研究(中英文), 2024, 33(6): 661-668. DOI: 10.15953/j.ctta.2024.156.
ZHANG T T, ZHONG C H, ZHANG A B, et al. Study on preoperative ct angiography scanning and reconstruction plan for anterolateral thigh perforator flap[J]. CT Theory and Applications, 2024, 33(6): 661-668. DOI: 10.15953/j.ctta.2024.156. (in Chinese).
|
| [11] |
WALSH K, GORJI N E. 3D CT scan metrology for solder void formation analysis in ball grid array electronic chips[J/OL]. Results in Physics, 2024, 56: 107233.
|
| [12] |
RIHAK P, VALA R, SZENDIUCH I. Detection of defects on BGA solder balls using 2D and 3D methods[C/OL]//2015 38th International Spring Seminar on Electronics Technology (ISSE). Eger, Hungary: IEEE, 2015: 245-249[2024-10-23].
|
| [13] |
EOM K Y, MIN B. Automated X-ray defect inspection on occluded bga balls using hybrid algorithm[J/OL]. Computers, Materials & Continua, 2023, 75(3): 6337-6350.
|
| [14] |
ZHANG Q, ZHANG M, GAMANAYAKE C, et al. Deep learning based solder joint defect detection on industrial printed circuit board X-ray images[J/OL]. Complex & Intelligent Systems, 2022, 8(2): 1525-1537.
|
Supported by: Beijing Renhe Information Technology Co. Ltd 
DownLoad: