Please wait a minute...
工程设计学报
工程设计学报  2017, Vol. 24 Issue (5): 588-594    DOI: 10.3785/j.issn.1006-754X.2017.05.014
整机和系统设计     
基于CPSO-BP神经网络-PID的热熔胶机温控系统研究
王莉, 张士兵
南通大学 电子信息学院, 江苏 南通 226019
Research on temperature control system of hot melt glue machine based on CPSO-BP neural network-PID
WANG Li, ZHANG Shi-bing
School of Electronics and Information, Nantong University, Nantong 226019, China
 全文: PDF(911 KB)   HTML
摘要：

针对热熔胶机加热温度存在惯性大、滞后性强、非线性等缺点，且常规PID控制难以达到温控要求，提出了一种基于CPSO-BP神经网络的PID控制器参数自适应调整算法。该算法先用CPSO算法将BP神经网络的初始权值和阈值优化到全局极小点附近，然后用传统BP神经网络学习算法在线调整PID参数。采用MATLAB对设计的CPSO-BP神经网络-PID控制器进行了温控系统仿真分析，仿真结果显示该控制器可实现对热熔胶机温度的精确控制，具有良好的自适应性和鲁棒性；实验测得采用CPSO-BP神经网络-PID控制器的温控系统能够在3.5 min 内达到设定温度，温控精度为±2.5℃。CPSO-BP神经网络-PID控制器作为嵌入式系统的一个控制单元，已投入热熔胶机温控系统实际应用，使用效果表明：温控系统性能稳定，温控精度高，有效实现了热熔胶机加热温度的自动控制，具有良好的实际应用及推广价值。
关键词： 热熔胶机;  CPSO算法;  BP神经网络;  PID;  温控系统    
Abstract:

There are some problems, such as large inertia, strong hysteresis and nonlinearity, in the heating temperature of hot melt glue machine. And the conventional PID control is difficult to meet the temperature control requirements, a self-tuning optimization algorithm of PID controller based on CPSO-BP neural network is proposed. In the proposed algorithm, CPSO algorithm was used to optimize the initial weights and thresholds of BP neural network near the global minimum point, and then PID parameters were adjusted online by using the traditional BP neural network learning algorithm. The temperature control system was analyzed and simulated by MATLAB based on the designed CPSO-BP neural network-PID controller. Simulation results showed that it could control the temperature of the hot melt glue machine precisely, and had good adaptability and robustness. The temperature control system using CPSO-BP neural network-PID could reach the set temperature within 3.5 min, and the temperature control error was smaller than ±2.5℃. The CPSO-BP neural network-PID controller had been put into practical application of hot melt glue machine temperature control system as a control unit of embedded system. The application results show that the temperature control system has stable performance and precise temperature control, and it effectively realizes the automatic control of heating temperature of hot melt glue machine, which has good application and popularization value.
Key words: hot melt glue machine    chaos particle swarm optimization (CPSO) algorithm    back-propagation (BP) neural network    proportion integration differentiation (PID)    temperature control system
收稿日期: 2016-12-22 出版日期: 2017-10-28
CLC:  TP273  
基金资助:

国家自然科学基金资助项目（61371111，61371112）；南通大学研究生创新计划项目（YKC16009）
通讯作者: 张士兵(1962-),男,江苏海门人,教授,博士生导师,博士,从事超宽带无线通信、认知无线电网络等研究,E-mail:zhangshb@ntu.edu.cn,http://orcid.org/0000-0001-8836-376X     E-mail: zhangshb@ntu.edu.cn
作者简介: 王莉(1992-),女,江苏泰州人,硕士生,从事认知无线电网络研究,E-mail:457411204@qq.com,http://orcid.org/0000-0001-8499-9840
服务　　
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章　　
王莉
张士兵

引用本文:

王莉, 张士兵. 基于CPSO-BP神经网络-PID的热熔胶机温控系统研究[J]. 工程设计学报, 2017, 24(5): 588-594.

WANG Li, ZHANG Shi-bing. Research on temperature control system of hot melt glue machine based on CPSO-BP neural network-PID[J]. Chinese Journal of Engineering Design, 2017, 24(5): 588-594.

链接本文:

https://www.zjujournals.com/gcsjxb/CN/10.3785/j.issn.1006-754X.2017.05.014    或    https://www.zjujournals.com/gcsjxb/CN/Y2017/V24/I5/588

[1] 陆敏智,许平平.一种双轴伺服热熔机的研制[J].机电工程技术,2016,45(8):125-128. LU Min-zhi, XU Ping-ping. The research of a biaxial servo fuse machine[J]. Mechanical & Electrical Engineering Technology, 2016, 45(8):125-128.
[2] 孙灵芳,邵萌萌,刘旭颖.基于改进BP算法的过热汽温建模[J].自动化技术与应用,2010,29(4):1-3. SUN Ling-fang, SHAO Meng-meng, LIU Xu-ying. Superheated steam temperature modeling based on improving BP algorithm[J]. Techniques of Automation and Applications, 2010, 29(4):1-3.
[3] 王秋平,马春林,肖玲玲,等.基于蚁群算法-BP神经网络的主蒸汽温度控制系统仿真研究[J].热力发电,2013,42(11):64-68. WANG Qiu-ping, MA Chun-lin, XIAO Ling-ling, et al. Main steam temperature control based on ant colony optimization algorithm and BP neural network[J]. Thermal Power Generation, 2013, 42(11):64-68.
[4] LI J K, GUO B, SHEN Y, et al. A modeling approach for energy saving based on GA-BP neural network[J]. Journal of Electrical Engineering & Technology, 2016, 11(5):1289-1298.
[5] 刘国斌,龚国芳,朱北斗,等.基于BP神经网络的盾构推进速度自适应PID控制[J].工程设计学报,2010,17(6):454-458. LIU Guo-bin, GONG Guo-fang, ZHU Bei-dou, et al. Adaptive PID control for thrust speed of the shield based on BP neural networks[J]. Chinese Journal of Engineering Design, 2010, 17(6):454-458.
[6] WANG F, ZHU H, LI Y P, et al. Combined transmission laser spectrum of core-offset fiber and BP neural network for temperature sensing research[J]. Spectroscopy and Spectral Analysis, 2016, 36(11):3732-3736.
[7] 李东洁,李君祥,张越,等.基于PSO改进的BP神经网络数据手套手势识别[J].电机与控制学报,2014,18(8):87-93. LI Dong-jie, LI Jun-xiang, ZHANG Yue, et al. Gesture recognition of data glove based on PSO-improved BP neural network[J]. Electric Machines and Control, 2014, 18(8):87-93.
[8] 田东平.混沌粒子群优化算法研究[J].计算机工程与应用,2013,49(17):43-47. TIAN Dong-ping. Research of chaos particle swarm optimization algorithm[J]. Computer Engineering and Applications, 2013, 49(17):43-47.
[9] 胥小波,郑康锋,李丹,等.新的混沌粒子群优化算法[J].通信学报,2012,33(1):24-30. XU Xiao-bo, ZHENG Kang-feng, LI Dan, et al. New chaos-particle swarm optimization algorithm[J]. Journal on Communications, 2012, 33(1):24-30.
[10] PETROVIC M, VUKOVIC N, MITIC M, et al. Integration of process planning and scheduling using chaotic particle swarm optimization algorithm[J]. Expert Systems with Applications, 2016, 64(12):569-588.
[11] KIM J, JIN M L. Synchronization of chaotic systems using particle swarm optimization and time-delay estimation[J]. Nonlinear Dynamics, 2016, 86(3):2003-2015.
[12] ANG K H, CHONG G, LI Y. PID control system analysis, design, and technology[J]. IEEE Transactions on Control Systems Technology, 2005, 13(4):559-576.
[13] REN T, LIU S, YAN G C, et al. Temperature prediction of the molten salt collector tube using BP neural network[J]. IET Renewable Power Generation, 2016, 10(2):212-220.
[14] KENNEDY J, EBERHART C. Particle swarm optimization[C]//Proceedings of IEEE International Conference on Neural Networks, Washington, Nov.27-Dec.1, 1995.
[15] 辛儒,赵永杰,何俊.远邻粒子群算法及在Delta机器人优化设计中的应用[J].工程设计学报,2014,21(4):334-339. XIN Ru, ZHAO Yong-jie, HE Jun. Distant neighborhood PSO algorithm and its application on the optimization design of Delta robot[J]. Chinese Journal of Engineering Design, 2014, 21(4):334-339.
[16] SHI Y H, EBERHART R C. A modified particle swarm optimizer[C]//Proceedings of the IEEE International Conference on Evolutionary Computation. Piscataway, New Jersey:IEEE Press, 1998:69-73.
[17] 陈如清,俞金寿.混沌粒子群混合优化算法的研究与应用[J].系统仿真学报,2008,20(3):685-688. CHEN Ru-qing, YU Jin-shou. Study and application of chaos-particle swarm optimization-based hybrid optimization algorithm[J]. Journal of System Simulation, 2008, 20(3):685-688.
[18] 段艳明.基于PSO算法和BP神经网络的PID控制研究[J].计算机技术与发展,2014,24(8):238-241. DUAN Yan-ming. Research of PID control based on BP neural network and PSO algorithm[J]. Computer Technology and Development, 2014, 24(8):238-241.
[19] 廖振兴,钟伟民,钱锋.基于高斯白噪声扰动变异的粒子群优化算法[J].华东理工大学学报(自然科学版),2008,34(6):859-863. LIAO Zhen-xing, ZHONG Wei-min, QIAN Feng. Particle swarm optimization algorithm based on mutation of Gaussian white noise disturbance[J]. Journal of East China University of Science and Technology (Natural Science Edition), 2008, 34(6):859-863.
[1] 陈翼楠,蒲志新,郑珍妮. 一种具有力检测机制的新型血管介入手术机器人[J]. 工程设计学报, 2023, 30(1): 20-31.
[2] 周婧,高红飞,卢林,段国林. 变论域模糊PID控制微流挤出型3D打印机的挤压力研究[J]. 工程设计学报, 2022, 29(5): 572-578.
[3] 王超, 孙文旭, 马晓静, 陈纪旸, 栾义忠, 马思乐. 基于模糊控制的HVPE生长设备温度控制系统[J]. 工程设计学报, 2020, 27(6): 765-770.
[4] 郑华林, 杨舜波, 潘盛湖, 王超. 百叶片定长切料-自动排片控制系统研究[J]. 工程设计学报, 2019, 26(4): 461-468.
[5] 唐林, 许志沛, 贺田龙, 敖维川. 基于BP神经网络的转动架稳定性灵敏度分析[J]. 工程设计学报, 2018, 25(5): 576-582.
[6] 郑英杰, 牛兴华, 高卫国, 张大卫, 刘腾. 精密机床差异化温控系统设计方法与控制策略研究[J]. 工程设计学报, 2018, 25(4): 472-480.
[7] 钟健, 阎春平, 曹卫东, 陈诚. 基于BP神经网络和FPA的高速干切滚齿工艺参数低碳优化决策[J]. 工程设计学报, 2017, 24(4): 449-458.
[8] 陈馈, 牛彦杰, 李阁强, 徐莉萍, 郭冰菁. 基于单神经元PID的盾构推进系统同步控制研究[J]. 工程设计学报, 2017, 24(3): 330-336.
[9] 潘春荣, 许化. 基于STM32的X型四旋翼无人机设计[J]. 工程设计学报, 2017, 24(2): 196-202,210.
[10] 司国斌, 王春霞, 靳孝峰. FDM型3D打印机的高精度进料系统研究[J]. 工程设计学报, 2016, 23(5): 497-500,512.
[11] 王爱国, 陈健伟. 基于MATLAB的3-RPS并联机构控制系统仿真[J]. 工程设计学报, 2016, 23(2): 172-180.
[12] 杨前明，孔令奇，李 健，王世刚，郭建伟. 电液比例马达速度同步控制系统建模与仿真[J]. 工程设计学报, 2015, 22(5): 330-336.
[13] 杨前明，孔令奇，李 健，王世刚，郭建伟. 电液比例马达速度同步控制系统建模与仿真[J]. 工程设计学报, 2015, 22(4): 330-336.
[14] 谢 苗，刘治翔，毛 君. 综掘巷道超前支护装备多缸同步控制方法研究[J]. 工程设计学报, 2015, 22(2): 193-200.
[15] 董胜, 袁朝辉. 舵机电液伺服加载复合控制方法研究[J]. 工程设计学报, 2013, 20(6): 539-544.