Measurement-Informed Deep Learning for Real-Time Monitoring of Hydrodynamic Drying Dynamics in Inkjet-Printed Display Pixels via Low-Resolution Imaging
ACS Applied Materials & Interfaces · 05.08.2026 · 18 (30) · 42223-42235
DOI: 10.1021/acsami.6c12267 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACS Applied Materials & Interfaces, online erschienen am 27.07.2026. Verfasst von Sung Jun Park und 10 weiteren Autor:innen. Beteiligte Einrichtung: Department of Semiconductor Engineering, Gyeongsang National University, Jinjudae-ro 501 Beon-gil, Jinju-si, Gyeongsangnam-do52828, Republic of Korea. Die Arbeit nennt 44 Literaturangaben. Gefördert von: Ministry of Trade, Industry and Energy, National Research Foundation of Korea.
Abstract (Originalsprache)
Real-time monitoring of drying dynamics is critical for ensuring high-quality thin-film fabrication in inkjet printing. Here, we present a classification framework for the drying stages of ZnO nanoparticle inks on 200-PPI patterned substrates using low-resolution optical images. By correlating 3D surface profiles with visual textures, we show how the volatility mismatch and viscosity contrast of binary solvents govern hydrodynamic evolution, generating distinct image textures for each stage. Based on this, we define three drying stages for binary mixed-solvent inks and two for single-solvent systems. A lightweight convolutional neural network, trained on grayscale images downsampled to 115 × 40 pixels, achieved a 99.4% test accuracy. Explainable AI analyses, utilizing input gradient saliency and gradient-weighted class activation mapping (Grad-CAM), revealed that the model autonomously learns to focus on the central pixel region—where physical variations are most pronounced—without any spatial supervision. Furthermore, the lightweight model requires only 0.64 ms per image for inference on a GPU, representing a 16.4-fold reduction in theoretical computational cost compared to the baseline. This image-only approach enables reliable, computationally efficient process monitoring, establishing a practical pathway for real-time quality control specifically for the tested ZnO nanoparticle inkjet printing configuration.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Semiconductor Engineering, Gyeongsang National University, Jinjudae-ro 501 Beon-gil, Jinju-si, Gyeongsangnam-do52828, Republic of Korea.
- Department of Mechanical Engineering, Korea Advanced Institute of Science and Technology, 291, Daehak-ro, Yuseong-gu, Daejeon34141, Republic of Korea.
- Autonomous Manufacturing Process R&D Department, Korea Institute of Industrial Technology (KITECH), Sangnok-gu, Ansan-si15588, Republic of Korea.
- Ingram School of Engineering, Texas State University, San Marcos, Texas78666, United States.
- Materials Science, Engineering, and Commercialization, Texas State University, San Marcos, Texas78666, United States.
- Department of Mechanical Engineering, Sejong University, 209 Neungdong-ro, Gwangjin-gu, Seoul05006, Republic of Korea.
ORCID-Profile: Donggeun Park, Jin Hong Park, Seunghwa Ryu, Jun Young Kim
Förderung
- Ministry of Trade, Industry and Energy
- National Research Foundation of Korea
Zitieren
APA
Park, S. J., Park, D., Park, J. H., Jeong, J. Y., Jang, S. H., Shin, D. Y., Kim, G. W., Kim, N., Ryu, S., An, K., & Kim, J. Y. (2026). Measurement-Informed Deep Learning for Real-Time Monitoring of Hydrodynamic Drying Dynamics in Inkjet-Printed Display Pixels via Low-Resolution Imaging. ACS Applied Materials & Interfaces, 18(30), 42223-42235. https://doi.org/10.1021/acsami.6c12267
Vancouver
Park SJ, Park D, Park JH, Jeong JY, Jang SH, Shin DY, et al. Measurement-Informed Deep Learning for Real-Time Monitoring of Hydrodynamic Drying Dynamics in Inkjet-Printed Display Pixels via Low-Resolution Imaging. ACS Applied Materials & Interfaces. 2026;18(30):42223-42235. doi:10.1021/acsami.6c12267
BibTeX
@article{Park2026,
author = {Park, Sung Jun and Park, Donggeun and Park, Jin Hong and Jeong, Jae Yeong and Jang, Seok Hwan and Shin, Dong Yeol and Kim, Gun Woong and Kim, Namwon and Ryu, Seunghwa and An, Kunsik and Kim, Jun Young},
title = {Measurement-Informed Deep Learning for Real-Time Monitoring of Hydrodynamic Drying Dynamics in Inkjet-Printed Display Pixels via Low-Resolution Imaging},
journal = {ACS Applied Materials & Interfaces},
year = {2026},
volume = {18},
number = {30},
pages = {42223--42235},
doi = {10.1021/acsami.6c12267}
}
EUVIMED