双启发动态规划在水泥煅烧优化控制中的应用  

Dual heuristic dynamic programming based on optimal control for cement burning system

作　　者：杨宝生[1] 马修水[2] 

机构地区：[1]宿州学院智能信息处理实验室,安徽宿州234000 [2]浙江大学宁波理工学院,浙江宁波315100

出　　处：《计算机工程与应用》2012年第4期222-224,共3页Computer Engineering and Applications

基　　金：安徽省自然科学基金(No.10040606Q64);宿州学院智能信息处理实验室开放课题资助项目(No.2010YKF13;2011YKF09;2011YKF11)

摘　　要：为克服动态规划方法在解决高维问题优化存在的维数灾问题,利用函数近似方法来取得代价函数,通过自学习的方法得到近似动态规划解,适用于复杂、非线性系统的决策优化或控制问题。采用双启发动态规划(DHP)算法用于水泥烧成系统的控制,用神经网络建立评价模块和动作模块对该系统进行优化控制。寻找合适的优化目标函数,由评价模块判断动作的好坏并反馈给动作模块,动作模块给出各参数的调整量。仿真结果显示,系统状态量能够被稳定控制在合理的范围。In order to overcome curse of dimensionality of dynamic programming method on solving the high-dimensional optimiza- tion problem, it uses function approximation method to approximate the cost function and gets approximate dynamic programming solution through self-learning method. This method is suitable for complex, nonlinear systems optimization or control of the decision-making problems. Dual Heuristic dynamic Programming（DHP） algorithm is used to control the cement burning system. It establishes the critic and action module using neural network to optimize the control of the system. By finding a suitable objective fimction, the critic mod- ule determines good or bad actions and feeds back to the action module, action module for adjusting the amount of each parameter is given. Simulation results show that the system state variables can be stable at a reasonable range.

关 键 词：双启发动态规划 烧成系统 建模 控制 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]