期刊文献+

基于多智能体强化学习的焦炉集气管压力多级协调控制 被引量:3

Multi-Level Coordination Control Based on Multi-Agent Reinforcement Learning for the Pressure of Gas Collectors of Coke Ovens
下载PDF
导出
摘要 针对焦炉集气管压力这类多变量强扰动非线性耦合系统,提出了一种基于Multi-Agent system(MAS)的焦炉集气管压力智能多级协调控制系统方案.采用基于Agent单元系统梯级协调体系和基于任务分解的实时Agent的组织与演化机制,通过Agent模态变迁进行模式切换,以适应快速突变环境.在控制Agent中采用Actor-critic强化学习方法,运用TS回归模糊神经网络实现行动和评判模块,使用分布式学习算法对多个Agent协调优化.工程应用表明,提出的控制策略有效地解决了高压氨水大干扰对集气管压力的冲击控制问题. For the multi-variable nonlinear coupled system with strong disturbance such as the gas pressure of collectors of coke ovens, this paper proposes an intelligent multi-level coordinated control strategy based on multi-agent system. It adopts the multi-level coordination architecture with agent agency and the organization and evolution mechanism based on task decomposition. The system can be switched to different modes using the state change of agents in order to operate in rapidly time-varying environments. The reinforcement learning method is used in Agent learning, the TS type recurrent fuzzy neural network(TSRPNN) is employed to realize the actor-critic elements. The agents in system are optimized coordinately by using the distributed learning algorithm. The real-world application shows that the proposed control strategy has successfully solved the process coordination control problem of the gas pressure of collectors of coke ovens with the strong disturbance produced by high pressure ammonia.
出处 《电子学报》 EI CAS CSCD 北大核心 2006年第10期1847-1851,共5页 Acta Electronica Sinica
基金 国家杰出青年科学基金(No.60425310) 湖南教育厅资助项目(No.04C718) 中国包装总公司重点科研项目(No.2005-83)
关键词 焦炉集气管 梯级协调 多智能体 强化学习 TS回归模糊神经网络 gas collectors of coke ovens cascade coordination multi-Agent system reinforcement learning TS recurrent fuzzy neural network
  • 相关文献

参考文献9

  • 1Yang Cunhua,Wu Min,Shen Deyao,et al.Hybrid intelligent control of gas collectors of coke ovens[J].Control Engineering Practice 2001,9(7):725-733.
  • 2秦斌,吴敏,王欣,阳春华.基于MAS的分布式集成智能控制系统开发与应用[J].小型微型计算机系统,2006,27(7):1405-1408. 被引量:5
  • 3Barto A G,Sutton R S,Anderson C W.Neural-like adaptive elements that can solve difficult learning control problem[J].IEEE Trans on Systems,Man,and Cybem,1983.13(5):834 -846.
  • 4Konda V R,Tsitsiklis J N.Actor-critic algorithms[A].Advances in Neural Information Processing Systems[C].CambridgeMA:MIT Press,1999,12(11):1008-1014.
  • 5Berenji H R,Vengerov D.On convergence of fuzzy reinforcement learning[A].In proceedings of the 10th IEEE International Conference on Fuzzy Systems (FUZZ-IEEE'01)[C].Melbourne Australia,2001.618-621.
  • 6Juang Chia Feng.A TSK-type recurrent fuzzy network for dynamic systems processing by neural network and genetic algorithms[J].IEEE Trans on Fuzzy Systems,2002,10 (2):155 -170.
  • 7Hu Jun ling,Welhaan M P.Multi-gent reinforcement learning:Theoretical framework and an algorithm[A].proceedings of the 15th International Conference of Machme Leaming[C].Madison Wisconsin,1998.115-122.
  • 8Jacobs R A.Increased rates of convergence through learning rate adaptation[J].Neural Networks,1988,1 (4):295-307.
  • 9Kumpati S,Balakrishnan N J.Adaptive control using multiple models[J].IEEE Transactions on Automatic Control,1997,42(2):171-187.

二级参考文献10

  • 1Rao A S,Georgeff M P.BDI agents:from theory to practice[A].Proceedings of the First International Conference on Multi-Agent Systems[C],San Francisco,CA,1995:312-319.
  • 2Sycara K,Pannu A,Williamson M,Zeng D.Distributed intelligent agents[J].IEEE Expert 1996:11(6):36-46.
  • 3Baumann J,Hohl F,Rothermel K,Straβer M.Mole-concepts of a mobile agent system[J].World Wide Web,1998,1(3):123-137.
  • 4Patil R S,Fikes R E,Patel-Scheneider P F,et al.The DARPA knowledge sharing effort:Progress report[C].Proceedings of the Third Conference on Principles of Knowledge Representation and Reasoning,Cambridge,MA,1992:103-114.
  • 5Milojicic D,Breugst M,Busse I et al,The OMG mobile agent system interoperability facility[A].Proceedings of the 2nd International Workshop of Mobile Agents (MA '98)[C] (Lecture Notes in Computer Science,vol.1477),Rothermel K,Hohl F(eds.).Springer:Stuttgart,1998,50-67.
  • 6Foundation for Intelligent Physical Agents[EB/OL].Specifications.http://www.fipa.org,1999.
  • 7Java Agent Development Framework[EB/OL].http://jade.cselt.it/,1999.
  • 8Jennings N R,Wooldridge M.Agent oriented software engineering[A].Bradshaw J ed Handbook of Agent Technology[M] AAAI/MIT Press,2000.
  • 9Friedman-Hill.Java expert system shell[EB/OL].http://herzberg.ca.sandia.gov/jess,1998.
  • 10秦斌,罗智,刘翔宇,龚韬,王欣.焦炉集气管压力智能控制系统[J].冶金自动化,2002,26(2):50-53. 被引量:5

共引文献4

同被引文献39

  • 1胡志坤,桂卫华,彭小奇,姚俊峰,张卫华.铜转炉生产操作模式智能优化[J].控制理论与应用,2005,22(2):243-247. 被引量:16
  • 2嵇启春,刘光辉,孟月波.焦炉集气管压力系统智能控制与仿真[J].西安科技大学学报,2005,25(3):361-364. 被引量:2
  • 3周国雄,赖旭芝,曹卫华,吴敏.焦炉集气管压力智能解耦控制系统的应用[J].中南大学学报(自然科学版),2006,37(3):558-561. 被引量:28
  • 4易以锋,方康玲,李威.焦炉集气管压力控制的一种新方法[J].微计算机信息,2006,22(11S):45-47. 被引量:4
  • 5秦斌,吴敏,王欣,阳春华.基于MAS的分布式焦炉集气管压力解耦控制[J].控制理论与应用,2006,23(6):961-966. 被引量:2
  • 6V Vapnik. The Nature of Statistical Learning Theory[M]. New York:Springer Verlag, 1995.
  • 7R Goto, H Matsuo. State generalization method with support vector machines in reinforcement learning [ J ]. Systems and Computers in Japan,2006,37(9):77 - 86.
  • 8Xuesong Wang, Xilan Tian, Yuhu Cheng. Value approximation with least squares support vector machine in reinforcement learning system[ J ]. Joturnal of Computational and Theoretical Nanoscience, 2007,4( 7/8 ) : 1290 - 1294.
  • 9G Kai, H Barbara. A reinforcement learning algorithm to improve scheduling search heuristics with the SVM[ A]. Proceedings of the IEEE International Conference on Neural Networks [C]. Piscataway: IEEE, Inc,2004.1811 - 1816.
  • 10R Manimegalai,E S Soumya, V Muralidharan, et al.Placement and muting for 3D-FPGAs using reinforcement learning and support vector machines [ A ]. Proceedings of the International Conference on VLSI Design[ C]. Piscataway: IEEE Inc, 2005. 451 - 456.

引证文献3

二级引证文献13

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部