N/A

The thin-film-transistor liquid-crystal display (TFT-LCD) manufacturing industry is capital-intensive and increasingly competitive. In order to maintain competitive advantages, the manufacturing industry needs to increase the accuracy of defect pattern detection and classification to improve the yield of TFT-LCD. However, current solutions of automatic optical inspection (AOI) for TFT-LCD often lack a comprehensive framework that can integrate domain knowledge, analyze different defect patterns, and incorporate effective technologies. The construction and innovation of the TFT-LCD manufacturing industry facing a huge challenge. Thus, the critical issue is to integrate advanced technologies such as big data, artificial intelligence, and human domain knowledge to support decision-making.
This study aims to propose a UNISON-ADC framework of decision-making under uncertainty defect patterns schema to break the limitations of traditional AOI approaches, combining artificial intelligence with domain knowledge to enhance defect detection and classification accuracy and strengthen industrial competitiveness. Following the proposed framework of our research, the company can more efficiently develop and validate suitable image-based defect classification. An empirical study for image-based defect classification for TFT-LCD array was validated in a leading TFT-LCD manufacturing facility in Taiwan. The empirical results demonstrate the superior classification performance of the CNN-based approach over traditional methods such as Random Forest and Support Vector Machine. The developed framework offers decision makers to understand the implementation status of each decision-making unit, and effective support to engineers in defect analysis and improve the yield of TFT-LCD.

Chien, C.-F., Chen, Y.-H., & Lo, M.-F. (2020). Advanced quality control (AQC) of silicon wafer specifications for yield enhancement for smart manufacturing. IEEE Transactions on Semiconductor Manufacturing, 33(4), 569-577.
Chien, C.-F., & Chuang, S.-C. (2014). A framework for root cause detection of sub-batch processing system for semiconductor manufacturing big data analytics. IEEE Transactions on Semiconductor Manufacturing, 27(4), 475-488.
Chien, C.-F., Hung, W.-T., & Liao, E. T.-Y. (2022). Redefining Monitoring Rules for Intelligent Fault Detection and Classification via CNN Transfer Learning for Smart Manufacturing. IEEE Transactions on Semiconductor Manufacturing, 35(2), 158-165.
Chien, C.-F., Ling, Y.-M., Kao, S.-X., & Lin, C.-H. (2022). Image-Based Defect Classification for TFT-LCD Array via Convolutional Neural Network. IEEE Transactions on Semiconductor Manufacturing, 35(4), 650-657.
Chou, C.-W., Chien, C.-F., & Gen, M. (2014). A multiobjective hybrid genetic algorithm for TFT-LCD module assembly scheduling. IEEE Transactions on Automation Science and Engineering, 11(3), 692-705.
Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., & Gelly, S. (2020). An image is worth 16x16 words: Transformers for image recognition at scale.
Fritsch, L., Mandle, R. J., Cowling, S. J., & Goodby, J. W. (2021). Carbosilane terminated alkoxycyanobiphenyls for bistable scattering mode LCDs. Journal of Materials Chemistry C, 9(2), 714-718.
Guo, M.-H., Xu, T.-X., Liu, J.-J., Liu, Z.-N., Jiang, P.-T., Mu, T.-J., Zhang, S.-H., Martin, R. R., Cheng, M.-M., & Hu, S.-M. (2022). Attention mechanisms in computer vision: A survey. Computational visual media, 8(3), 331-368.
He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,
Hong, T.-Y., & Chien, C.-F. (2020). A simulation-based dynamic scheduling and dispatching system with multi-criteria performance evaluation for Industry 3.5 and an empirical study for sustainable TFT-LCD array manufacturing. International Journal of Production Research, 58(24), 7531-7547.
Huang, S.-H., & Pan, Y.-C. (2015). Automated visual inspection in the semiconductor industry: A survey. Computers in Industry, 66, 1-10.
Jana, M. R., & Ramsankar, P. (2020). Development of technology for fabrication of prototype ion extraction grid for fusion research. Fusion Engineering and Design, 161, 112066.
Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., & Darrell, T. (2014). Caffe: Convolutional architecture for fast feature embedding. Proceedings of the 22nd ACM International Conference on Multimedia,
Khakifirooz, M., Chien, C.-F., & Chen, Y.-J. (2019). Dynamic support vector regression control system for overlay error compensation with stochastic metrology delay. IEEE Transactions on Automation Science and Engineering, 17(1), 502-512.
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017). Imagenet classification with deep convolutional neural networks. Communications of the ACM, 60(6), 84-90.
Kuo, C.-F., Hsu, C.-T. M., Fang, C.-H., Chao, S.-M., & Lin, Y.-D. (2013). Automatic defect inspection system of colour filters using Taguchi-based neural network. International Journal of Production Research, 51(5), 1464-1476.
LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436-444.
Li, T., Bo, W., Hu, C., Kang, H., Liu, H., Wang, K., & Fu, H. (2021). Applications of deep learning in fundus images: A Review. Medical Image Analysis, 69, 101971.
Lu, H.-P., & Su, C.-T. (2021). CNNs combined with a conditional GAN for mura defect classification in TFT-LCDs. IEEE Transactions on Semiconductor Manufacturing, 34(1), 25-33.
Nitish, S. (2014). Dropout: a simple way to prevent neural networks from overfitting. The journal of Machine Learning Research, 15(1), 1929-1958.
Perez, L., & Wang, J. (2017). The effectiveness of data augmentation in image classification using deep learning.
Shorten, C., & Khoshgoftaar, T. M. (2019). A survey on image data augmentation for deep learning. Journal of Big Data, 6(1), 1-48.
Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition.
Song, J., Gao, S., Zhu, Y., & Ma, C. (2019). A survey of remote sensing image classification based on CNNs. Big Earth Data, 3(3), 232-254.
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015). Going deeper with convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,
Tan, M., & Le, Q. (2019). Efficientnet: Rethinking model scaling for convolutional neural networks. International Conference on Machine Learning,
Yang, H., Mei, S., Song, K., Tao, B., & Yin, Z. (2017). Transfer-learning-based online Mura defect classification. IEEE Transactions on Semiconductor Manufacturing, 31(1), 116-123.
Yang, S.-W., Lin, C.-S., Lin, S.-K., & Chiang, H.-T. (2014). Automatic defect recognition of TFT array process using gray level co-occurrence matrix. Optik, 125(11), 2671-2676.
Yang, Y., Pan, L., Ma, J., Yang, R., Zhu, Y., Yang, Y., & Zhang, L. (2020). A high-performance deep learning algorithm for the automated optical inspection of laser welding. Applied Sciences, 10(3), 933.
Zhan, X., Xu, F. F., Zhou, Z., Yan, Y., Yao, J., & Zhao, Y. S. (2021). 3D laser displays based on circularly polarized lasing from cholesteric liquid crystal arrays. Advanced Materials, 33(37), 2104418.
Zhu, H., Huang, J., Liu, H., Zhou, Q., Zhu, J., & Li, B. (2021). Deep-Learning-Enabled Automatic Optical Inspection for Module-Level Defects in LCD. IEEE Internet of Things Journal, 9(2), 1122-1135.
林俊輝. (2017). 卷積神經網絡之自動缺陷識別之製造智慧_TFT-LCD陣列製程之實證研究.