58‐4: Real‐Time Consumption Scheduling Engine with Reinforcement Learning for Display Manufacturing
SID Symposium Digest of Technical Papers · 2026-06 · 57 (1) · 816-819
DOI: 10.1002/sdtp.70001_223 ↗Kurz gefasst
Fachartikel in der Zeitschrift SID Symposium Digest of Technical Papers, online erschienen am 11.09.2026. Verfasst von Yanzuo Lin und 5 weiteren Autor:innen. Die Arbeit nennt 7 Literaturangaben.
Abstract (Originalsprache)
This paper proposes a novel reinforcement learning algorithm as a low‐level module deeply integrated into the Real Time Scheduling (RTS) engine for display manufacturing. The use of Hybrid Proximal Policy Optimization (HPPO) enables the system engine to balance production capacity and material usage optimally in scheduling. Comparative wet etching experiments validate the proposed method's significant reduction in acid consumption, confirming a paradigm shift towards AI‐driven control.
Zitieren
APA
Lin, Y., Ji, X., Wu, H., Qin, Y., She, B., & Yu, D. (2026). 58‐4: Real‐Time Consumption Scheduling Engine with Reinforcement Learning for Display Manufacturing. SID Symposium Digest of Technical Papers, 57(1), 816-819. https://doi.org/10.1002/sdtp.70001_223
Vancouver
Lin Y, Ji X, Wu H, Qin Y, She B, Yu D. 58‐4: Real‐Time Consumption Scheduling Engine with Reinforcement Learning for Display Manufacturing. SID Symposium Digest of Technical Papers. 2026;57(1):816-819. doi:10.1002/sdtp.70001_223
BibTeX
@article{Lin2026,
author = {Lin, Yanzuo and Ji, Xiaodong and Wu, Houfei and Qin, Yikun and She, Bihai and Yu, Dahai},
title = {58‐4: Real‐Time Consumption Scheduling Engine with Reinforcement Learning for Display Manufacturing},
journal = {SID Symposium Digest of Technical Papers},
year = {2026},
volume = {57},
number = {1},
pages = {816--819},
doi = {10.1002/sdtp.70001_223}
}
EUVIMED