[1]欧青立,张磊,邓鹏,等.粒子群优化BP神经网络PID控制注塑机液压系统[J].应用科技,2018,45(04):50-55.[doi:10.11991/yykj.201710007]
 OU Qingli,ZHANG Lei,DENG Peng,et al.Particle swarm optimization BP neural network PID control hydraulic system of injection molding machine[J].Applied science and technology,2018,45(04):50-55.[doi:10.11991/yykj.201710007]
点击复制

粒子群优化BP神经网络PID控制注塑机液压系统(/HTML)
分享到:

《应用科技》[ISSN:1009-671X/CN:23-1191/U]

卷:
第45卷
期数:
2018年04期
页码:
50-55
栏目:
计算机技术与应用
出版日期:
2018-08-05

文章信息/Info

Title:
Particle swarm optimization BP neural network PID control hydraulic system of injection molding machine
作者:
欧青立 张磊 邓鹏 雷鹏宇
湖南科技大学 信息与电气工程学院, 湖南 湘潭 411201
Author(s):
OU Qingli ZHANG Lei DENG Peng LEI Pengyu
School of Information and Electrical Engineering, Hu’nan University of Sciences and Technology, Xiangtan 411201, China
关键词:
注塑机控制液压系统粒子群优化算法神经网络PID控制参数整定伺服系统注塑工艺过程
Keywords:
injection molding machine controlhydraulic systemparticle swarm optimizationneural networksPID controlparameter tuningserver systeminjection molding process
分类号:
TP273
DOI:
10.11991/yykj.201710007
文献标志码:
A
摘要:
注塑机液压系统是一个时变、非线性和高耦合的复杂系统,传统PID控制参数不易整定,超调量大,对注塑机液压系统控制效果欠佳,现提出一种粒子群优化BP神经网络算法改良PID控制。BP神经网络算法存在收敛速度慢和容易陷入局部最小值的缺陷,利用粒子群算法的全局最优和收敛速度快的特性改良BP神经网络,然后利用粒子群优化BP神经网络对PID的3个参数进行在线调整。仿真结果表明,经过粒子群优化后的BP神经网络对PID3个参数的整定效果要比BP网络要好,同时粒子群优化BP神经网络PID控制效果明显优于传统PID控制,可以有效提高注塑机液压系统的精度和响应速度,优化注塑过程。
Abstract:
The hydraulic system of injection molding machine is a complex system with time-varying, non-linear and high coupling characteristics. It is not easy to tune traditional PID control parameters, the overshoot is large and the control effect on the hydraulic system of injection molding machine is not good, therefore, this paper proposes a particle swarm optimized BP neural network algorithm improved PID control. BP neural network algorithm has the defects of slow convergence rate and easily falling into local minimum. Use the characteristics of global optimization and fast convergence speed of particle swarm optimization algorithm to improve the BP neural network, then adjust those three parameters of PID by the particle swarm optimized BP neural network on line. Simulation results show that BP neural network after particle swarm optimization is better than BP network in tuning those three parameters of PID, and the effect of PID control of the particle swarm optimized BP neural network is obviously better than traditional PID control, which can effectively increase the accuracy and response speed of the hydraulic pressure system of injection molding machine, and optimize the injection molding process.

参考文献/References:

[1] 盘真保, 董菲, 赵吉文, 等. 基于遗传二自由度的永磁同步直线电机PID控制参数优化研究[J]. 电气工程学报, 2015, 10(8):50-55.
[2] 王卫兵, 张惠, 徐倩. 减温减压系统模糊PID温度控制器的设计[J]. 哈尔滨理工大学学报, 2016, 21(5):96-100.
[3] 杨达飞, 黄力. 混沌模糊神经网络算法在注塑机温度实时控制中的应用[J]. 塑料工业, 2016, 44(4):64-68.
[4] SINGH G, VERMA A. A Brief Review on injection moulding manufacturing process[J]. Materials today:proceedings, 2017, 4(2):1423-1433.
[5] 廖辉, 王青林, 黄崇林. 恒压变流量供油注塑机液压系统的研究[J]. 机床与液压, 2015, 43(4):113-115.
[6] 叶青. 注塑机电液伺服系统复合控制策略研究及其应用[J]. 电气传动, 2016, 46(2):55-59.
[7] MILOVANOVIC M B, ANTIC D S, MILOJKOVIC M T, et al. Adaptive PID control based on orthogonal endocrine neural networks[J]. Neural networks, 2016, 84:80-90.
[8] 阳同光, 桂卫华. 基于粒子群优化神经网络观测器感应电机定子电阻辨识[J]. 电机与控制学报, 2015, 19(2):89-95.
[9] KUO Jianlong, CHANG Mengti. Multiobjective design of turbo injection mode for axial flux motor in plastic injection molding machine by particle swarm optimization[J]. Mathematical problems in engineering, 2015:974624.
[10] 王茂林, 叶小红, 王洪光, 等. 液压系统中粒子群优化神经网络权值的控制算法[J]. 应用科技, 2014, 41(3):51-54.
[11] 杨娜, 荆园园. 基于改进PSO算法的函数极值寻优研究[J]. 计算机仿真, 2015, 32(9):263-266.
[12] HAVLICSEK H, ALLEYNE A. Nonlinear control of an electrohydraulic injection molding machine via iterative adaptive learning[J]. IEEE/ASME transactions on mechatronics, 1999, 4(3):312-323.

相似文献/References:

[1]方明杰,周光辉,程元森,等.基于运行状态信息的数控珩磨机液压系统可靠性预测方法[J].应用科技,2012,39(06):30.[doi:10.3969/j.issn.1009-671X.201209011]
 FANG Mingjie,ZHOU Guanghui,CHENG Yuansen,et al.Reliability prediction for hydraulic system of CNC honing machine based on the operational status information[J].Applied science and technology,2012,39(04):30.[doi:10.3969/j.issn.1009-671X.201209011]

备注/Memo

备注/Memo:
收稿日期:2017-10-27。
基金项目:国家自然科学基金项目(11272119);湖南省自然科学基金项目(14JJ2099).
作者简介:欧青立(1962-),男,教授.
通讯作者:欧青立,E-mail:qinghncn@163.com
更新日期/Last Update: 2018-09-05