图博弈下具有未知动态的供应链系统变更设计

Change design of supply chain system with unknown dynamics under graph game

为了研究具有未知动态的供应链系统变更一致性问题,将供应链系统建模为多智能体系统,针对多智能体系统图博弈问题,提出一种自适应最优分布式算法,该算法基于数值迭代启发式动态规划,无需系统动力学知识即可求解耦合的Hamilton-Jacobi-Isaacs(HJI)方程。此外,使用神经网络来识别每个子链的未知动态,证明了所提对策的闭环系统稳定性。仿真结果表明,该方法可以保证供应链变更系统的稳定性与一致性。

In order to study the change consistency of supply chain system with unknown dynamics, the supply chain system is modeled as a multi-agent system.For the multi-agent system graph game problem, an adaptive optimal distributed algorithm is proposed.The algorithm is based on numerical iterative heuristic dynamic programming and can solve the coupled HJI equation without system dynamics knowledge.In addition, the neural network is used to identify the unknown dynamics of each sub chain, and the stability of the closed-loop system is proved.Simulation results show that the proposed method can ensure the stability and consistency of supply chain change system.