基于RBF神经网络逆系统的注射速度控制

doi:-

东北大学学报(自然科学版) ›› 2013, Vol. 34 ›› Issue (2): 174-177.DOI: -

基于RBF神经网络逆系统的注射速度控制

常玉清¹，张红燕²，王姝¹

(1.东北大学信息科学与工程学院，辽宁沈阳110819；2.江苏徐州工程机械研究院，江苏徐州221004)

收稿日期:2012-07-06 修回日期:2012-07-06 出版日期:2013-02-15 发布日期:2013-04-04
通讯作者: 常玉清
作者简介:常玉清(1973-)，女，辽宁沈阳人，东北大学教授.
基金资助:
国家自然科学基金资助项目(61174130)；中央高校基本科研业务费专项资金资助项目(N100404022，N110304010).

Injection Speed Control Based on RBF Neural Network Inverse System

CHANG Yuqing¹， ZHANG Hongyan²， WANG Shu¹

1. School of Information Science ＆ Engineering， Northeastern University， Shenyang 110819， China; 2. Jiangsu Xuzhou Construction Machinery Research Institute， Xuzhou 221004， China.

Received:2012-07-06 Revised:2012-07-06 Online:2013-02-15 Published:2013-04-04
Contact: CHANG Yuqing
About author:-
Supported by:
-

摘要/Abstract

摘要： 为了实现注射速度的精确控制，针对其非线性时变的动态特性，提出了基于神经网络逆系统的控制方法.采用M.Rafizadeh模型描述注射速度系统特性，通过求解该系统的相对阶证明了系统的可逆性.由于注射速度系统逆模型的解析形式难以获得，因此构造了基于RBF神经网络的注射速度逆系统，并将该系统与常规PID控制相结合，对注射速度实现复合控制，解决了基于RBF神经网络逆系统的开环控制效果不理想的问题.仿真实验表明，该控制系统具有良好的跟踪性能及抗干扰性能.

关键词: 注塑过程, 注射速度, RBF神经网络逆系统, 复合控制系统

Abstract: Taking account of the nonlinear timevariant characteristics of injection speed， a control method based on a neural network inverse system was proposed to control injection speed precisely. The injection speed system was characterized by the M. Rafizadeh model， and its reversibility was confirmed through calculating the relative degree of the system. Considering the difficulty in obtaining the analytical form of reversible model for injection speed system， the RBF neural network (RBFNN) was used to build an inverse system of injection speed. The RBFNNbased inverse system， which has unsatisfied control effect due to openloop control， was combined with the conventional PID control， thus realizing the composite control of injection speed. The simulation results show that the control system proposed has good tracking and antidisturbance performance.

Key words: injection process, injection speed, RBF neural network inverse system, composite control system

中图分类号:

常玉清，张红燕，王姝. 基于RBF神经网络逆系统的注射速度控制[J]. 东北大学学报(自然科学版), 2013, 34(2): 174-177.

CHANG Yuqing， ZHANG Hongyan， WANG Shu. Injection Speed Control Based on RBF Neural Network Inverse System[J]. Journal of Northeastern University, 2013, 34(2): 174-177.

参考文献

[1] Xu H，Wu D M，Zhu Q X，et al.Research of precision injection control system based on the online measurement of polymer melt density［J］.Advanced Materials Research，2011，383/384/385/386/387/388/389/390:5136/5141.
[2] Pandelidis I O，Agrawal A R.Selftuning control of ram velocity in injection molding［C］//SPE Annual Technical Conference.Los Angeles，1987:235/237.
[3] Pandelidis I O，Agrawal A R.Optimal anticipatory control of ram velocity in injection molding［J］.Polymer Engineering and Science，1988，28(5):147/156.
[4] Tamma K K，Dowler B L，Railkar S B.Computer aided applications to injection molding:transfinite/finite element thermal/stress response formulations ［J］.Polymer Engineering and Science，1988，28(7):421/428.
[5] 崔采莲，孙明轩.注塑机注射速度的离散预期学习控制［J］.机械工程学报，2007，43(6):41/47.(Cui Cailian，Sun Mingxuan.Discrete anticipatory learning control of ram velocity in injection molding machines［J］.Chinese Journal of Mechanical Engineering，2007，43(6):41/47.)
[6] Huang S N，Tan K K，Lee T H.Neuralnetworkbased predictive learning control of ram velocity in injection molding ［J］.IEEE Transactions on Systems，Man，and Cybernetics，Part C:Applications and Reviews，2004，34(3):363/368.
[7] 柯敏，应济，周伟安，等.基于RBF神经网络的精密注塑机速度控制的研究［J］.轻工机械，2010，28(3):7/10.(Ke Min，Ying Ji，Zhou Weian，et al.Research on velocity control in precise injection molding based on RBF neural network［J］.Light Industry Machinery，2010，28(3):7/10.)
[8] 刘国海，孙玉坤，全力，等.基于神经网络逆系统的发酵过程多变量解耦控制［J］.仪器仪表学报，2006，27(3):71/74.(Liu Guohai，Sun Yukun，Quan Li，et al.Multivariable decoupling control based on neural network inverse system in a fermentation process［J］.Chinese Journal of Scientific Instrument，2006，27(3):71/74.)
[9] 任峰.神经网络逆系统的非线性控制及软测量研究［D］.大连:大连理工大学，2008.(Ren Feng.Study of nonlinear control based on ANN inverse system method and soft sensing［D］.Dalian:Dalian University of Technology，2008.)
[10] Chiu C P，Shih M C，Wei J H.Dynamic modeling of the mold filling process in an injection molding machine［J］.Polymer Engineering and Science，1991，31(19):1417/1425.

基于RBF神经网络逆系统的注射速度控制

Injection Speed Control Based on RBF Neural Network Inverse System

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 0

编辑推荐

Metrics

本文评价