PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
June 1, 2026Procedia Computer ScienceOpen Access

Design of Dynamic Resource Scheduling Algorithm for Semiconductor Equipment Production Line Projects Based on Reinforcement Learning

View Full Paper
Ask AI
Bookmark
Share

Authors

YFYunpeng Fang

Discussion

Loading...

Member takes

Overview

Randomized trial demonstrates improved equipment utilization in semiconductor production lines, indicating enhanced efficiency.

Key Points

  • The study aims to improve resource scheduling in semiconductor production lines through a dynamic algorithm based on reinforcement learning.
  • Models the production line as a Markov Decision Process (MDP).
  • Proposes a dynamic scheduling algorithm using Deep Q-Network (DQN).
  • Employs simulation tests on a large-scale production line.
  • Achieves an average equipment utilization of 87.7%.
  • Results in an average order cycle time of 43.8 hours.
  • Reduces energy consumption to an optimal value of 1285 kWh.

Cite This Study

Yunpeng Fang (2026) studied this question.

synapsesocial.com/papers/6a1d234302fbce9130638f08https://doi.org/10.1016/j.procs.2026.03.287
View Full Paper
Ask AI
Bookmark
Share