双启发动态规划在水泥煅烧优化控制中应用.pdfVIP

网络出版时间：2011-7-25 16:32 网络出版地址：/kcms/detail/11.2127.tp1632.108.html 2011-4-2 双启发动态规划在水泥煅烧优化控制中的应用 1 2 杨宝生 , 马修水 1 2 YANG Bao-sheng , MA Xiu-shui 1.宿州学院 智能信息处理实验室，宿州 234000 2.浙江大学 宁波理工学院，宁波 310058 1.Laboratory of Intelligent Information Processing, Suzhou University, Suzhou 234000, China 2.Ningbo Institute of Technology ，Zhejiang University ，Ningbo 315100, China E-mail : bsyang@ Dual Heuristic Dynamic Programming Based Optimal Control for Cement Burning System Abstract ：In order to overcome curse of dimensionality of dynamic programming method on solving the high-dimensional optimization problem, using function approximation method to approximate the cost function and through self-learning method to get approximate dynamic programming solution. 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. Establish the critic and action module using neural network to optimize the control of the system. By finding a suitable objective function, the critic module to determine good or bad actions and feedback 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. Key words ：DHP; Burning system; Modeling; Control 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