[1]于立君,陈佳,刘繁明,等.改进粒子群算法的PID神经网络解耦控制[J].智能系统学报编辑部,2015,10(5):699-704.[doi:10.11992/tis.201406028]
 YU Lijun,CHEN Jia,LIU Fanming,et al.An improved particle swarm optimization forPID neural network decoupling control[J].CAAI Transactions on Intelligent Systems,2015,10(5):699-704.[doi:10.11992/tis.201406028]
点击复制

改进粒子群算法的PID神经网络解耦控制(/HTML)
分享到:

《智能系统学报》编辑部[ISSN:1673-4785/CN:23-1538/TP]

卷:
第10卷
期数:
2015年5期
页码:
699-704
栏目:
学术论文—智能系统
出版日期:
2015-10-25

文章信息/Info

Title:
An improved particle swarm optimization forPID neural network decoupling control
作者:
于立君 陈佳 刘繁明 王辉
哈尔滨工程大学 自动化学院, 黑龙江 哈尔滨 150001
Author(s):
YU Lijun CHEN Jia LIU Fanming WANG Hui
College of Automation, Harbin Engineering University, Harbin 150001, China
关键词:
粒子群算法综合减摇系统PID神经网络解耦控制仿真分析
Keywords:
particle swarm algorithmsintegrate stabilization systemPID neural networkdecoupling controlsimulation analysis
分类号:
TH186
DOI:
10.11992/tis.201406028
文献标志码:
A
摘要:
综合减摇控制系统存在非线性、多变量、强耦合等因素,会导致减摇系统达不到最佳控制状态。利用粒子群算法具有对整个空间进行高效搜索以及PID神经网络的自适应特点,提出一种改进粒子群算法,以解决粒子群算法中存在算法精度不高、粒子易陷入局部极小值等问题,并提高PID神经网络训练速度和训练精度,便于参数寻优。仿真结果表明,改进的粒子群算法具有一定优越性,将其运用到综合减摇控制系统解耦控制器设计中,能够有效地减小船舶横摇,达到较好的控制效果。
Abstract:
The integrated ship stabilization system has nonlinear, multi-variable and strong coupling characteristics, which may hinder the system from reaching the best control state. An improved particle swarm algorithm is proposed based on the characteristics of particle swarm optimization (PSO) algorithm, which can search the parameter space efficiently, along with its associated PID artificial neuron network that has self-regulation and adaptability. The improved particle swarm algorithm can overcome disadvantages in former particle swarm algorithms such as low precision, the particles tend to fall into extremely small values, and so on. In addition, the improved algorithm can increase the training speed and precision of the PID nerve network, which facilitates parameter optimization. The simulation results show that the improved PSO has certain advantages, it can reduce ship rolling, and can achieve excellent control effects when it is applied to the design of the decoupling control of an integrated stabilization control system.

参考文献/References:

[1] 孟祥振. 综合减摇系统参数配置及控制器优化研究[D]. 哈尔滨:哈尔滨工程大学, 2012:27-28. MENG Xiangzhen. The study of parameters configuration and controller optimization of integrated stabilization system[D]. Harbin:Harbin Engineering University, 2012:27-28.
[2] 周西峰, 林莹莹, 郭前岗. 基于粒子群算法的PID神经网络解耦控制[J]. 计算机技术与发展, 2013, 23(9):158-161.ZHOU Xifeng, LIN Yingying, GUO Qiangang. PID neural network decoupling control based on particle swarm optimization[J]. Computer Technology and Development, 2013, 23(9):158-161.
[3] MOHANDES M A. Modeling global solar radiation using particle swarm optimization (PSO)[J]. Solar Energy, 2012, 86(1):3137-3145.
[4] 应进. 基于粒子群算法的航空发动机多变量控制研究[D].南昌:南昌航空大学, 2011:23-24.YING Jin. Multivariable control for aeroengines based on particle swarm optimization algorithm[D]. Nanchang:Nanchang Hangkong University, 2011:23-24.
[5] AL-GEELANI N A, PIAH M A M, ADZIS Z, et al. Hybrid regrouping PSO based wavelet neuralnetworks for characterization of acoustic signalsdue to surface discharges on H.V.glass insulators[J]. Applied Soft Computing, 2013, 13(12):4622-4632.
[6] 胡建秀,曾建潮. 微粒群算法中惯性权重的调整策略[J]. 计算机工程, 2007, 33(11):193-195.HU Jianxiu,ZENG Jianchao.Selection on inertia weight of particle swarm optimization[J]. Computer Engineering, 2007, 33(11):193-195.
[7] 陈水利, 蔡国榕. PSO算法加速因子的非线性策略研究[J]. 长江大学学报(自然版):理工卷, 2007, 4(4):1-4.CHEN Shuili, CAI Guorong. Nonlinear strategy of PSO algorithm acceleration factor[J]. Journal of Yangtze University (Nat Sci Edit):Sci & Eng V, 2007, 4(4):1-4.
[8] ALIREZA A. PSO with adaptive mutation and inertia weight and its application in parameter estimation of dynamic systems[J]. Acta Automatica Sinica, 2011, 37(5):541-549.
[9] 于立君, 孟祥振, 金宏章, 等. 综合减摇系统参数配置研究[J]. 中国造船, 2012, 53(4):13-21.YU Lijun, MENG Xiangzhen, JIN Hongzhang, et al. Study of configuration parameters of integrated stabilization system[J]. Shipbuilding of China, 2012, 53(4):13-21.
[10] 于立君, 孙经广, 刘繁明, 等. 广义预测算法在综合减摇系统控制器设计中的应用[J]. 船舶工程, 2013, 35(6):76-79, 83.YU Lijun, SUN Jingguang, LIU Fanming, et al. Application of generalized prediction algorithm in designing integrated stabilization system controller[J]. Ship Engineering, 2013, 35(6):76-79, 83.
[11] CHIOU J S, TSAI S H, LIU Mingtang. A PSO-based adaptive fuzzy PID-controllers[J]. Simulation Modelling Practice and Theory, 2012, 26:49-59.
[12] 沈锡.基于粒子群优化算法的船舶航向PID控制[D]. 大连:大连海事大学, 2011:6-7.SHEN Xi. PID control for ship steering based on particle swarm optimization[D]. Dalian:Dalian Maritime University, 2011:6-7.
[13] BOUALLÈGUE S, HAGGÈGE J, AYADI M, et al. PID-type fuzzy logic controller tuning based on particle swarm optimization[J]. Engineering Applications of Artificial Intelligence, 2012, 25(3):484-493.
[14] RATNAWEERA A, HAIGAMUGE S K, WATSON H C. Self-organizing hierarchical particle swarm optimizer with time-varying acceleration coefficients[J]. IEEE Transactions on Evolutionary Compution, 2004, 8(3):240-255.
[15] 乔俊飞, 逄泽芳, 韩红桂. 基于改进粒子群算法的污水处理过程神经网络优化控制[J]. 智能系统学报, 2012, 7(5):429-436.QIAO Junfei, PANG Zefang, HAN Honggui. Neural network optimal control for wastewater treatment process based on APSO[J]. CAAI Transactions on Intelligent Systems, 2012,7(5):429-436.

相似文献/References:

[1]刘 胜,宋 佳,李高云.PSO并行优化LSSVR非线性黑箱模型辨识[J].智能系统学报编辑部,2010,5(01):51.
 LIU Sheng,SONG Jia,LI Gao-yun.Modeling a complex nonlinear system with particle swarm optimizationand paralleloptimized least squares support vector regression[J].CAAI Transactions on Intelligent Systems,2010,5(5):51.
[2]唐小勇,于 飞,潘洪悦.改进粒子群算法的潜器导航规划[J].智能系统学报编辑部,2010,5(05):443.[doi:10.3969/j.issn.1673-4785.2010.05.011]
 TANG Xiao-yong,YU Fei,PAN Hong-yue.Submersible path-planning based on an improved PSO[J].CAAI Transactions on Intelligent Systems,2010,5(5):443.[doi:10.3969/j.issn.1673-4785.2010.05.011]
[3]沈继红,王侃.求解旅行商问题的混合粒子群优化算法[J].智能系统学报编辑部,2012,7(02):174.
 SHEN Jihong,WANG Kan.The light ray particle swarm optimization for solving the traveling salesman problem[J].CAAI Transactions on Intelligent Systems,2012,7(5):174.
[4]钱晓山,阳春华.基于GEP的最小二乘支持向量机模型参数选择[J].智能系统学报编辑部,2012,7(03):225.
 QIAN Xiaoshan,YANG Chunhua.A parameter selection method of a least squares support vector machine based on gene expression programming[J].CAAI Transactions on Intelligent Systems,2012,7(5):225.
[5]乔俊飞,逄泽芳,韩红桂.基于改进粒子群算法的污水处理过程神经网络优化控制[J].智能系统学报编辑部,2012,7(05):429.
 QIAO Junfei,PANG Zefang,HAN Honggui.Neural network optimal control for wastewater treatment processbased on APSO[J].CAAI Transactions on Intelligent Systems,2012,7(5):429.
[6]拓守恒,雍龙泉.一种用于PID控制的教与学优化算法[J].智能系统学报编辑部,2014,9(06):740.[doi:10.3969/j.issn.1673-4785.201304072]
 TUO Shouheng,YONG Longquan.A modified teaching-learning-based optimization algorithm for parameter tuning of a PID controller[J].CAAI Transactions on Intelligent Systems,2014,9(5):740.[doi:10.3969/j.issn.1673-4785.201304072]
[7]王辉,车超,于立君,等.鳍-水舱综合减摇混沌系统控制方法研究[J].智能系统学报编辑部,2017,12(03):318.[doi:10.11992/tis.201607012]
 WANG Hui,CHE Chao,YU Lijun,et al.Control method for a fin/tank integrated stabilization chaotic system[J].CAAI Transactions on Intelligent Systems,2017,12(5):318.[doi:10.11992/tis.201607012]
[8]翟俊海,刘博,张素芳.基于粗糙集相对分类信息熵和粒子群优化的特征选择方法[J].智能系统学报编辑部,2017,12(03):397.[doi:10.11992/tis.201705004]
 ZHAI Junhai,LIU Bo,ZHANG Sufang.A feature selection approach based on rough set relative classification information entropy and particle swarm optimization[J].CAAI Transactions on Intelligent Systems,2017,12(5):397.[doi:10.11992/tis.201705004]
[9]徐鹏,谢广明,文家燕,等.事件驱动的强化学习多智能体编队控制[J].智能系统学报编辑部,2019,14(1):93.[doi:10.11992/tis.201807010]
 XU Peng,XIE Guangming,WEN Jiayan,et al.Event-triggered reinforcement learning formation control for multi-agent[J].CAAI Transactions on Intelligent Systems,2019,14(5):93.[doi:10.11992/tis.201807010]
[10]刘楠,刘福才,孟爱文.基于改进PSO和FCM的模糊辨识[J].智能系统学报编辑部,2019,14(2):378.[doi:10.11992/tis.201707025]
 LIU Nan,LIU Fucai,MENG Aiwen.Fuzzy identification based on improved PSO and FCM[J].CAAI Transactions on Intelligent Systems,2019,14(5):378.[doi:10.11992/tis.201707025]

备注/Memo

备注/Memo:
收稿日期:2014-06-17;改回日期:。
基金项目:中央高校自由探索计划资助项目(HEUCF041406).
作者简介:于立君,男,1975年生,副教授,博士,主要研究方向为船舶运动控制、先进控制理论及应用。主持并完成博士后基金1项、横向项目1项、中央高校自由探索计划5项,获得黑龙江省科技进步二等奖1项;陈佳,女,1989年生,硕士研究生,主要研究方向为船舶智能控制理论方法与应用;刘繁明,男,1963年生,教授,博士生导师,主要研究方向为水下潜器定位技术、弱信号测量与处理技术、被动导航与定位技术、工业装置测控技术。承担“十二五”预先研究项目2项,国家自然科学基金重点项目1项,设备研制项目多项。
通讯作者:于立君.E-mail:yulijun@hrbeu.edu.cn.
更新日期/Last Update: 2015-11-16