1297

2 views
Download
  • Share
Create Account or Sign In to post comments

Abstract—By means of intelligent decision algorithms and cloud integration paradigm, intelligent manufacturing organizes distributed and heterogeneous resource models organically to realize the process scheduling of complex products. To this end, this paper focuses on the heterogeneous models integration problems in complex production scheduling with machine failure. Specifically, a message bus is constructed to uniformly describe the labeled transmission message models to integrate distributed and heterogeneous cloud resources which include process scheduling rules, meta production process and process execution facilities etc. During the whole process scheduling, an virtual intelligent integration agent based on dual deep reinforcement learning is introduced to composite scheduling rules from multiple experts when successively dispatching available process to appropriate machine. Last, the integration method based on dual deep Q-learning agent is tested in process scheduling including heterogeneous described and distributed models. Compared with integration framework for complete models, this proposed integration paradigm focused on interactive models can control system complexity more efficiently. Furthermore, message simulation bus allows for asynchronous communication and log tracking. Compared with the mechanical combination of expert rules, compatible learning algorithm in this paradigm enhances the intelligence of integration.

An Deep Q-Learning Agent based Integration Method of Heterogeneous Models for Process Scheduling Wenzheng Liu Shuangfei Wu Hongguang Zhu Heming Zhang

Next Up

00:07:22
00:13:11
00:12:50
00:09:18
00:12:48
00:08:36