RGV Dynamic Scheduling Strategy Based on Network Cellular Automaton and Marko Model

2019 2nd International Conference on Advanced Materials, Intelligent Manufacturing and Automation

Yin, J.Y.^1 ; Chen, N.^1 ; Zhang, Z.T.^2 ; Chen, S.S.^3

Department of Management, Wuhan University of Technology, Wuhan, Hubei

430070, China^1

Economic and Management School, Xidian University, Xi'an, Shanxi

710126, China^2

Department of Science, Wuhan University of Technology, Wuhan, Hubei

430070, China^3

关键词: Automated guide vehicles;    Dynamic scheduling;    Intelligent processing;    Job shop scheduling problems;    Local optimal solution;    Markov transition probability matrix;    Optimal solutions;    Transition probability matrix;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/569/3/032026/pdf
DOI  :  10.1088/1757-899X/569/3/032026

来源: IOP

【 摘 要 】

In an intelligent processing system, if a Rail Guide Vehicle (RGV), also known as automated guide vehicle, is provided with the optimal dynamic scheduling strategy, the work efficiency and economic profit of the workshop can be greatly improved. This paper considers the variable number as well as the types of Computer Number Controller (CNC) and regards the real problem as the Job Shop Scheduling Problem (JSSP). To solve JSSP, this paper use Network Cellular Automaton (NCA) to abstract the flexible workshop system and apply the rule of one-step trial-and-error for the core link between the network cellular automaton and the Markov Transition Probability Matrix. Further this system is simulated using Markov chain in probabilities to expand the solution space with the optimal solution among according to the Monte Carlo experimental principle. Finally, the result can jump out of the local optimal solution and approximate the global optimal dynamic scheduling strategy by trial-and-error rule and Transition Probability Matrix. To verify the NCA-Markov model, this paper use an intelligent flexible workshop which produces two-process materials. By simulating this system with the model, the efficiency of the intelligent processing system can be greatly improved.