[1]李界家,李晓峰,片锦香.基于改进PSO和模糊RBF神经网络的退火炉温控制[J].南京理工大学学报(自然科学版),2014,38(03):337.
 Li Jiejia,Li Xiaofeng,Pian Jinxiang.Temperature control of annealing furnaces based on improved PSO and fuzzy RBF neural network[J].Journal of Nanjing University of Science and Technology,2014,38(03):337.
点击复制

基于改进PSO和模糊RBF神经网络的退火炉温控制
分享到:

《南京理工大学学报》(自然科学版)[ISSN:1005-9830/CN:32-1397/N]

卷:
38卷
期数:
2014年03期
页码:
337
栏目:
出版日期:
2014-06-30

文章信息/Info

Title:
Temperature control of annealing furnaces based on improved PSO and fuzzy RBF neural network
作者:
李界家李晓峰片锦香
沈阳建筑大学 信息与控制工程学院,辽宁 沈阳 110168
Author(s):
Li JiejiaLi XiaofengPian Jinxiang
Information and Control Engineering Faculty,Shenyang Jianzhu University,Shenyang 110168,China
关键词:
改进粒子群优化算法模糊径向基函数神经网络退火炉温度控制径向基函数权值阀值超调量响应时间稳态误差
Keywords:
improved particle swarm optimization algorithmfuzzy radial basis function neural networkannealing furnacestemperature controlradial basis functionweightsthresholdsovershootresponse timesteady state errors
分类号:
TP183
摘要:
为提高对具有大滞后,强耦合的退火炉温度控制系统的控制精度,采用模糊径向基函数(RBF)神经网络控制炉温,并采用改进粒子群优化(PSO)算法进行优化。利用模糊推理过程与RBF神经网络所具有的函数等价性,统一系统函数。在利用改进PSO算法对模糊RBF神经网络进行训练时,先利用改进PSO算法得到模糊RBF神经网络的初始权值和阀值,然后对其进行二次优化得到最终的权值和阀值。仿真结果表明:该文方法降低了超调量,缩短了响应时间,稳态误差很小,能够拟合参考模型的输出,控制效果明显优于常规PID控制。
Abstract:
In order to improve the control accuracy of temperature control systems of annealing furnaces with large time delay and strong coupling,the temperature of annealing furnaces is controlled by a fuzzy radial basis function(RBF)neural network and optimized by an improved particle swarm optimization(PSO)algorithm.The system functions are unified using the function equivalency of the fuzzy inference process and RBF neural network.The initial weights and thresholds of the fuzzy RBF neural network are obtained by the PSO algorithm,and the final weights and thresholds are obtained by quadratic optimization when the fuzzy RBF neural network is trained by the improved PSO algorithm.The simulation results show that the method proposed here decreases the overshoot,shortens the response time,and the steady state error is small,which can fit the outputs of the reference model and is better than common PID control in control effects.

参考文献/References:

[1]王立新.模糊系统与模糊控制教程[M].北京:清华大学出版社,2003:8-10.
[2]谢铮桂,钟少丹,韦玉科.改进的粒子群算法及收敛性分析[J].计算机工程与应用,2011,47(1):46-49.
Xie Zhenghui,Zhong Shaodan,Wei Yuke.Modified particle swarm optimization algorithm and its convergence analysis[J].Computer Engineering and Applictions,2011,47(1):46-49.
[3]任子晖,王坚.一种动态改变惯性权重的自适应粒子群算法[J].计算机科学,2009,36(2):227-229,256.
Ren Zihui,Wang Jian.New adaptive particle swarm optimization algorithm with dynamically changing inertia weight[J].Computer Science,2009,36(2):227-229,256.
[4]Yang Shangdong,Li Xiang.A new ANN optimized by improved PSO algorithm combined with chaos and its application in shortterm load forecasting[A].2006 International Conference on Computational Intelligence and Security[C].Guangzhou,China:IEEE,2006:945-948.
[5]Garcia M L,Hoffman J M,Rowley J L.Test for success:Next generation aircraft identification system RF simulation[A].Integrated Communications,Navigation and Surveillance Conference,2007[C].Herndon,VA,USA:IEEE,2007:1-10.
[6]Sun Chaoli,Zeng Jianchao,Pan J S.An improved vector particle swarm optimization for constrained optimization problems[J].Information Sciences,2011,181(6):1153-1163.
[7]陈宁,林秋芳.计算球面对称动力系统Lyapunov指数[J].小型微型计算机系统,2012,33(4):878-881.
Chen Ning,Lin Qiufang.Computation of Lyapunov exponents of dynamic systems with spherical surface symmetry[J].Journal of Chinese Computer Systems,2012,33(4):878-881.
[8]马斌,王迪,韩忠华,等.基于多Agent的无线网络火灾探测系统设计[J].沈阳建筑大学学报(自然科学版),2011,27(3):592-597.
Ma Bin,Wang Di,Han Zhonghua,et al.Wireless network fire detection system based on mutiagent[J].Journal of Shenyang Jianzhu University(Natural Science),2011,27(3):592-597.
[9]宋晓宇,郑妍,常春光.基于变精度粗糙集的应急调度模型[J].信息与控制,2011,40(6):858-864.
Song Xiaoyu,Zheng Yan,Chang Chunguang.A variable precision rough set based model for emergency scheduling[J].Information and Control,2011,40(6):858-864.

备注/Memo

备注/Memo:
收稿日期:2013-07-04修回日期:2013-12-16
基金项目:国家自然科学基金(60874103)
作者简介:李界家(1957-)男,博士,教授,主要研究方向:智能控制、故障诊断、建筑智能化等,E-mail:ljj_0123@sjzu.edu.cn。
引文格式:李界家,李晓峰,片锦香.基于改进PSO和模糊RBF神经网络的退火炉温控制[J].南京理工大学学报,2014,38(3):337-341.
投稿网址:http://zrxuebao.njust.edu.cn
更新日期/Last Update: 2014-06-30