1
Return

Digital twin-driven disturbance recognition and adaptive scheduling for discrete manufacturing workshops

delete2026-05-05
delete0
PRE
AI
陈
陈洁 (Jie Chen)
Y
Yiwen Hu
D
Dunbing Tang *
C
Changchun Liu
Z
Zequn Zhang
L
Liping Wang
L
Lingfei Qian
Q
Qixiang Cai
DOI：10.1016/j.rcim.2026.103323delete
deleteOriginal
deleteOriginal request for help
deleteShare
deleteSave
Abstract

Abstract

En 中文
• A DT-driven framework is proposed for self-detection, self-diagnosis, self-optimization, and autonomous execution. • A Twin-DGAN is developed to accurately identify both explicit and implicit disturbances. • An MOE-DGAN extracts disturbance-specific features to construct enhanced state representations. • Operation and machine agents, trained with PPO and SAC, collaboratively optimize scheduling decisions.
Keywords:
Digital twin
Disturbance recognition
Adaptive scheduling
Discrete manufacturing
Machine learning

Journal

R
Robotics and Computer-Integrated Manufacturing
IF:
11.4
Papers:
3.3K
Citations:
1.3W

Organization

N
nanjing university of aeronautics and astronautics
Scholars:
2.4K
Papers: 859
Citations: 1
Cited Papers

Cited Papers

Citing Papers

Citing Papers