《计算机应用研究》|Application Research of Computers

基于CARLA-PSO组合模型的智能控制器参数学习优化

Parameter learning optimization of intelligent controller based on CARLA-PSO composite model

免费全文下载 (已被下载 次)  
获取PDF全文
作者 谷学静,张明儒,王志良,郭宇承
机构 1.华北理工大学 a.电气工程学院;b.轻工学院,河北 唐山 063009;2.北京科技大学 计算机与通信工程学院,北京 100083
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2019)03-007-0677-04
DOI 10.19734/j.issn.1001-3695.2017.09.0927
摘要 对连续动作强化学习自动机(CARLA)进行了改进,应用改进后的CARLA结合粒子群优化算法(PSO)优化PID参数。以CARLA为基础,建立了CARLA和PSO的组合优化学习模型CARLA-PSO,该模型包含CARLA学习环路和PSO学习环路两个部分,通过优化策略选择器进行学习环路的选择,通过与环境进行相互作用,获得最优控制。对连铸结晶器液位控制进行了仿真实验,实验结果表明,CARLA-PSO在进行PID参数优化时寻优效率高,全局搜索能力强,能够达到理想的控制效果,具有较好的应用前景。
关键词 连续动作学习强化自动机;粒子群优化算法;智能PID控制器;结晶器液位
基金项目 国家自然科学基金资助项目(61170117)
国家重点研发计划资助项目(2016YFB1001404)
河北省自然科学基金高端钢铁冶金联合研究基金专项项目(F2017209120)
本文URL http://www.arocmag.com/article/01-2019-03-007.html
英文标题 Parameter learning optimization of intelligent controller based on CARLA-PSO composite model
作者英文名 Gu Xuejing, Zhang Mingru, Wang Zhiliang, Guo Yucheng
机构英文名 1.a.SchoolofElectricalEngineering,b.CollegeofLightIndustry,NorthChinaUniversityofScience&Technology,TangshanHebei063009,China;2.SchoolofComputer&CommunicationEngineering,UniversityofScience&TechnologyBeijing,Beijing100083,China
英文摘要 This paper presented a hybrid approach involving continuous action reinforcement learning automata (CARLA) and particle swarm optimization (PSO) to design a optimal and intelligent proportiona-lintegral-derivative (PID) controller of an mould level control system. The proposed method is CARLA which is able to explore and learn to improve control performance without the knowledge of the analytical system model. CARLA-PSO is composed of two sections which are the CARLA learning loop, and the PSO learning loop, and select learning loop according to the optimal policy selector. CARLA-PSO is a method that combines the features of PSO and CARLA in order to improve the optimize operation through interaction with the environment. The experimental results show that CARLA-PSO was indeed more efficient in improving the step response of an mould level control system.
英文关键词 continuous action reinforcement learning automata; particle swarm optimization; intelligent PID controller; mould level
参考文献 查看稿件参考文献
  [1] 李祖林. 结晶器液位专家系统控制研究[J] . 计算机工程与应用, 2009, 45(10):199-201, 234. (Li Zulin. Research on expert system for mould level control[J] . Computer Engineering and Applications, 2009, 45(10):199-201, 234. )
[2] Passenbrunner T’Ortner P, Colaneri P, et al. Mold level control of a continuous casting plant by switching control strategies[J] . IFAC Proceedings Volumes, 2010, 43(14):1350-1355.
[3] 童朝南, 肖磊, 彭开香, 等. 基于遗传算法的结晶器液位约束广义预测控制[J] . 控制与决策, 2009, 24(11):1735-1739. (Tong Chao-nan, Xiao Lei, Peng Kaixiang, et al. Constrained generalized predictive control of mould level based on genetic algorithm[J] . Control and Decision, 2009, 24(11):1735-1739. )
[4] 曹光明, 吴迪, 张殿华. 基于模糊自适应PID的铸轧机结晶器液位控制系统[J] . 控制与决策, 2007, 22(4):399-402, 407. (Cao Guangming, Wu Di, Zhang Dianhua. Design of mold liquid level control system in roll caster based on fuzzy control regulation[J] . Control and Decision, 2007, 22(4):399-402, 407. )
[5] 房启超, 徐林, 王建辉, 等. 改进的PSO及其在结晶器液位控制中的应用[J] . 仪器仪表学报, 2006, 27(11):1399-1402. (Fang Qichao, Xu Lin, Wang Jianhui, et al. Improved PSO and its application in crystallizer liquid level control system[J] . Chinese Journal of Scientific Instrument, 2006, 27(11):1399-1402. )
[6] Delgarm N, Sajadi B, Kowsary F, et al. Multi-objective optimization of the building energy performance:a simulation-based approach by means of particle swarm optimization (PSO)[J] . Applied Energy, 2016, 170(5):293-303.
[7] 熊伟丽, 徐保国, 周其明. 基于改进粒子群算法的PID参数优化方法研究[J] . 计算机工程, 2005, 31(24):41-43. (Xiong Weili, Xu Baoguo, Zhou Qiming. Study on optimization of PID parameter based on improved PSO[J] . Computer Engineering, 2005, 31(24):41-43. )
[8] 黄为勇, 徐晓菊, 潘晓博, 等. 量子粒子群优化算法的收缩—扩张系数控制策略研究[J] . 计算机应用研究, 2016, 33(9):2592-2595. (Huang Weiyong, Xu Xiaoju, Pan Xiaobo, et al. Control strategy of contraction-expansion coefficient in quantum-behaved particle swarm optimization[J] . Application Research of Computers, 2016, 33(9):2592-2595. )
[9] 刘晓. 基于连续动作学习自动机的联想强化学习[J] . 山西大学学报:自然科学版, 2015, 38(3):426-431. (Liu Xiao . Associative reinforcement learning based on continuous-action learning automata[J] . Journal of Shanxi University :Natural Science Edition, 2015, 38(3):426-431. )
[10] 周锐, 陈宗基. 强化学习在导弹制导中的应用[J] . 控制理论与应用, 2001, 18(5):748-750. (Zhou Rui, Chen Zongji. Application of reinforcement learning in missile guidance[J] . Control Theory & Applications, 2001, 18(5):748-750. )
[11] 钟宇平, 王丽丹, 段书凯, 等. 基于神经网络及强化学习的智能控制系统[J] . 西南大学学报:自然科学版, 2013, 35(11):172-179. (Zhong Yuping, Wang Lidan, Duan Shukai, et al. An intelligent control system based on neural networks and reinforcement learning[J] . Journal of Southwest Agricultural University:Natural Scie-nce Edition, 2013, 35(11):172-179. )
[12] Shah H, Gopal M. A reinforcement learning algorithm with evolving fuzzy neural networks[J] . IFAC Proceedings, 2014, 47(1):1161-1165.
[13] Mirsaleh M R, Meybodi M R. A learning automata-based memetic algorithm[J] . Genetic Programming & Evolvable Machines, 2015, 16(4):399-453.
[14] Howell M N, Gordon T J, Best M C. The application of continuous action reinforcement learning automata to adaptive PID tuning[C] //Proc of IEEE Seminar Learning Systems for Control. Piscataway, NJ:IEEE Press, 2000:2/1-2/4.
[15] Kashki M, Abdel-Magid Y L, Abido M A. A reinforcement learning automata optimization approach for optimum tuning of PID controller in AVR system[C] //Proc of International Conference on Intelligent Computing:Advanced Intelligent Computing Theories and Applications-with Aspects of Artificial Intelligence. Berlin:Springer-Verlag, 2008:684-692.
[16] Hasanien H M. Design optimization of PID controller in automatic voltage regulator system using taguchi combined genetic algorithm method[J] . IEEE Systems Journal, 2013, 7(4):825-831.
[17] 宋明智, 杨乐. 基于改进自适应PSO算法的WSN覆盖优化方法[J] . 计算机应用研究, 2013, 30(11):3472-3475. (Song Mingzhi, Yang Le. Improving coverage of wireless sensor network using enhanced adaptive PSO algorithm[J] . Application Research of Computers, 2013, 30(11):3472-3475. )
[18] 章家岩, 郎佳红, 王金忠. 转炉炉口微差压滑模变结构控制技术[J] . 控制工程, 2009, 16(4):419-422. (Zhang Jiayan, Lang Jiahong, Wang Jinzhong. Sliding mode controller of micro-differential pressure of converter mouth[J] . Control Engineering of China, 2009, 16(4):419-422. )
收稿日期 2017/9/25
修回日期 2017/11/20
页码 677-680
中图分类号 TP301.6
文献标志码 A