舰船冷却水系统多智能体自治状态重构方法

摘要/Abstract

摘要： 针对现代舰船运行环境的不确定性和动力平台集成管理智能化的需求，以舰船冷却水系统为研究对象，研究了其在不确定性条件下基于多智能体（Agent）自治决策模型的状态重构方法.通过将该系统的状态重构问题看作松耦合的马尔可夫决策过程（MDP），建立了其基于MDP的多Agent自治决策模型.使用遗传算法对决策空间进行全面搜索得到最优策略，并通过数值计算验证了其性能.在获得的最优策略的指导下，实现了冷却水系统的自动状态重构.该方法能够提高冷却水系统的自主决策水平和任务效率.

关键词: 多智能体, 舰船冷却水系统, 自主决策, 状态重构, 马尔可夫决策过程, 遗传算法

Abstract: In consideration of the uncertainty of the modern ship environment and the requirements for the intelligence of integrated management of power platform, taking the shipboard chilled water system as the research object, the method of state reconfiguration based on the multi-agent autonomous decision making model with the existence of uncertainty was studied. The problem of state reconfiguration is formulated as a loosely coupled Markov decision process (MDP). Then the multi-agent autonomous decision making model based on MDP is established and the optimal policy is obtained by using genetic algorithm. Finally the performance of the optimal policy is examined in the numerical calculation and the autonomous state reconfiguration is realized by following the received policy. This method can increase the autonomous decision making level and enhance the mission effectiveness of shipboard chilled water system.

Key words: multi-agent, shipboard chilled water system, autonomous decision making, state reconfiguration, Markov decision process (MDP), genetic algorithm

中图分类号:

U 664.121

秦久峰, 曾凡明, 陈于涛. 舰船冷却水系统多智能体自治状态重构方法[J]. 上海交通大学学报（自然版）, 2013, 47(02): 284-289.

QIN Jiu-Feng, ZENG Fan-Ming, CHEN Yu-Tao. Method of Multi-agent Autonomous State Reconfiguration of Shipboard Chilled Water System[J]. Journal of Shanghai Jiaotong University, 2013, 47(02): 284-289.

参考文献

［1］Scheidt D. Intelligent control of auxiliary ship systems［C］// The 2nd World Maritime Technology Conference. London, UK: IMarEST, 2006: 10721079.

［2］Scheidt D. Intelligent agentbased control［J］. Johns Hopkins APL Technical Digest, 2002, 23(4):423.

［3］Lively K, Scheidt D. Mission based engineering plant［C］// Proceedings of ASNE Reconfiguration and Survivability Symposium. Orlando: IEEE Press, 2005: 311318.

［4］Tichy P, Slechta P. Industrial MAS for planning and control［J］. Lecture Notes in Computer Science, 2002, 2322(12):137154.

［5］Maturana F, Staron R. Agent virtual machine for automation controllers example application: Shipboard automation［J］. Robotics and ComputerIntegrated Manufacturing, 2008, 24(5):616624.

［6］朱琼, 陈雪芳, 张洁. 面向代理的车间动态调度方法［J］. 上海交通大学学报, 2008, 42(7): 10461050.

ZHU Qiong, CHEN Xuefang, ZHANG Jie. Multiagent based dynamic job shop scheduling method［J］. Journal of Shanghai Jiaotong University, 2008, 42(7): 10461050.

［7］赵敏, 姚敏, 刘兼唐. 基于遗传算法的小卫星多Agent任务调度优化设计［J］. 仪器仪表学报, 2008, 29(7): 14751479.

ZHAO Min, YAO Min, LIU Jiantang. Task scheduling optimization design for small satellite based on multiagent and genetic algorithm［J］. Chinese Journal of Scientific Instrument, 2008, 29(7): 14751479.

［8］刘波, 陈哨东, 贺建良. 基于概率群集的多战机协同空战决策算法［J］. 上海交通大学学报, 2011, 45(2): 257261.

LIU Bo, CHEN Shaodong, HE Jianliang. Air combat decisionmaking for multiflight coordinated attack based on probability collectives［J］. Journal of Shanghai Jiaotong University, 2011, 45(2): 257261.

［9］Spaan M T J, Groen F C A. Team coordination among robotic soccer players［J］. Journal of Control Science and Engineering, 2009, 23(8). 112119.

［10］黎恒烜, 孙海顺, 文劲宇, 等. 用于舰船电力系统重构的多代理系统设计［J］. 中国电机工程学报, 2011, 10(31): 8187.

LI Hengxuan, SUN Haishun, WEN Jinyu, et al. Design of a multiagent system for shipboard power system reconfiguration［J］. Proceedings of the CSEE, 2011, 10(31): 8187.

［11］尚永爽, 李文海, 刘长捷. 部分可观测信息条件下装备剩余寿命预测［J］. 航空学报, 2012, 33(5): 848894.

SHANG Yongshuang, LI Wenhai, LIU Changjie. Prediction of remaining useful life for equipment with partially observed information［J］. Acta Aeronautica et Astronautica Sinica, 2012, 33(5): 848894.

［12］周坡, 曹志刚. 基于马尔可夫过程的卫星移动信道模型及长期预测方法［J］. 电子与信息学报, 2011, 33(12): 29482953.

ZHOU Po, CAO Zhigang. Markov process based satellite mobile channel model and long term prediction method［J］. Journal of Electronics & Information Technology, 2011, 33(12): 29482953.

［13］刘克. 实用马尔可夫决策过程［M］. 北京：清华大学出版社, 2004:710.

［14］LI Yongchang. A multiagent autonomous decision making process for resource allocation［J］. Journal of American Society of Naval Engineers, 2007, 38(6):10961107.

[1]	刘亚辉, 申兴旺, 顾星海, 彭涛, 鲍劲松, 张丹. 面向柔性作业车间动态调度的双系统强化学习方法[J]. 上海交通大学学报, 2022, 56(9): 1262-1275.
[2]	闫青, 鲁建厦, 江伟光, 邵益平, 汤洪涛, 李英德. 考虑双端口布局的紧致化仓储系统堆垛机路径优化[J]. 上海交通大学学报, 2022, 56(7): 858-867.
[3]	周天颜, 冯小恩, 范云锋, 董诗音, 李玉庆, 金慧中. 避免防空火力过剩的地面兵力防御部署优化模型[J]. 空天防御, 2022, 5(4): 19-23.
[4]	王箫剑, 洪君, 陈晶华, 李鸿光. 基于参数化建模和响应面优化的箱体减重研究[J]. 空天防御, 2022, 5(4): 60-66.
[5]	王卓鑫, 赵海涛, 谢月涵, 任翰韬, 袁明清, 张博明, 陈吉安. 反向传播神经网络联合遗传算法对复合材料模量的预测[J]. 上海交通大学学报, 2022, 56(10): 1341-1348.
[6]	陶海红, 闫莹菲. 一种基于GA-CNN的网络化雷达节点遴选算法[J]. 空天防御, 2022, 5(1): 1-5.
[7]	周宇泰, 徐岳, 李宇, 蒋国韬. 基于遗传算法的干扰态势下三维雷达网优化布站方法[J]. 空天防御, 2022, 5(1): 52-59.
[8]	李翠明, 王宁, 张晨. 基于改进遗传算法的光伏板清洁分级任务规划[J]. 上海交通大学学报, 2021, 55(9): 1169-1174.
[9]	顾一凡, 赵文龙, 唐善军, 杨擎宇, 郑鑫. 分布式主/被动成像探测系统目标空间协同定位方法研究[J]. 空天防御, 2021, 4(4): 119-126.
[10]	卓鹏程, 严瑾, 郑美妹, 夏唐斌, 奚立峰. 面向滚动轴承全生命周期故障诊断的GA-OIHF Elman神经网络算法[J]. 上海交通大学学报, 2021, 55(10): 1255-1262.
[11]	王金凤, 陈璐, 杨雯慧. 考虑设备可用性约束的单机调度问题[J]. 上海交通大学学报, 2021, 55(1): 103-110.
[12]	牛志华, 苑璨, 孔得宇. 计算周期序列k-错线性复杂度的混合遗传算法[J]. 上海交通大学学报, 2020, 54(6): 599-606.
[13]	康俊涛, 张亚州, 秦世强. 基于一种混合智能算法的有限元模型修正多解问题[J]. 上海交通大学学报, 2020, 54(6): 652-660.
[14]	姚来鹏, 侯保林, 刘曦. 采用摩擦补偿的弹药传输机械臂自适应终端滑模控制[J]. 上海交通大学学报, 2020, 54(2): 144-151.
[15]	戴少怀, 王磊, 李旻, 余科, 罗晨. 基于遗传算法的SVM自适应干扰样式选择[J]. 空天防御, 2020, 3(2): 59-64.