[1]代祥,肖静,徐幼林,等.动态下电磁阀控对靶喷雾流量特性及控制方法[J].江苏农业学报,2019,(02):476-483.[doi:doi:10.3969/j.issn.1000-4440.2019.02.031]
　DAI Xiang,XIAO Jing,XU You-lin,et al.Flow characteristics and control method for solenoid valve controlled target spraying under dynamic conditions[J].,2019,(02):476-483.[doi:doi:10.3969/j.issn.1000-4440.2019.02.031]
点击复制

动态下电磁阀控对靶喷雾流量特性及控制方法()
分享到：

江苏农业学报[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2019年02期
页码:
476-483
栏目:
农业工程
出版日期:
2019-04-30

文章信息/Info

Title:
Flow characteristics and control method for solenoid valve controlled target spraying under dynamic conditions
作者:
代祥1; 肖静1; 徐幼林1; 宋海潮1; 2
（1.南京林业大学机械电子工程学院，江苏南京210037；2.南京工业职业技术学院机械工程学院，江苏南京210023）
Author(s):
DAI Xiang1; XIAO Jing1; XU You-lin1; SONG Hai-chao1; 2
(1.College of Mechanical and Electronic Engineering, Nanjing Forestry University, Nanjing 210037, China;2.College of Mechanical Engineering, Nanjing Institute of Industry Technology, Nanjing 210023, China)
关键词:
电磁阀控对靶喷雾; 动态条件; 流量特性; BP神经网络; 遗传算法
Keywords:
solenoid valve controlled target spraying; dynamic conditions; flow characteristics; BP neural network; genetic algorithm
分类号:
TP391.41；S220.3
DOI:
doi:10.3969/j.issn.1000-4440.2019.02.031
文献标志码:
A
摘要:
本研究对电磁阀控对靶喷雾系统动态条件（喷头开启数、开启时间、流量大小适时变化）下各参数[系统压力(P)、电磁阀频率(f)、占空比(D）]控制下的喷雾流量(Q)特性进行试验研究，并利用BP神经网络及遗传算法(GA)优化的BP神经网络对试验数据进行拟合和测试。试验结果表明：P每增大0.05 MPa，Q的最大调节范围增加约200 ml/min；较大的P会轻微减小流量控制线性区间(I)，而较高的f则显著减小线性区间(I)，f=20 Hz，P为0.10～0.35 MPa时对应的I约为0.3～0.6；Q与各控制参数间均存在非线性关系，利用BP神经网络进行喷头精准流量控制误差较小，平均误差仅0.20，经GA优化的BP神经网络具有更高的精度，误差低至0.15。综合考虑系统动态条件下电磁阀各参数可以实现流量的精准调节，依靠BP神经网络，尤其是GA优化的BP神经网络，可实现电磁阀控对靶喷雾流量的精准控制。
Abstract:
The real output flow rate (Q) controlled by system pressures (P), solenoid valve control frequencies (f) and duty cycles (D) in the solenoid valve controlled target spraying system was studied under dynamic working conditions. Furthermore, the test results were verified by using BP neural network and genetic algorithm (GA) optimized BP neural network. The results showed that the Q rose 200 ml/min when the P increased 0.05 MPa. Larger P would slightly reduce the linear interval (I) of flow control, while higher f would significantly reduce the I. When the P was 0.10-0.35 MPa and f was 20 Hz, the I ranged from 0.3 to 0.6. There was nonlinear relationship between Q and each control parameter. The use of BP neural network (with the error of 0.20), especially the GA optimized BP neural network (with the error of 0.15), was feasible in the solenoid valve controlled target spraying system. Considering the parameters of the solenoid valve under the dynamic condition of the system, the flow rate can be precisely adjusted. The BP neural network, especially the BP neural network optimized by GA, can realize the precise control of solenoid valve controlled target spraying.

参考文献/References:

[1]邱白晶,闫润,马靖,等. 变量喷雾技术研究进展分析[J]. 农业机械学报, 2015,46(3):59-72.
[2]薛新宇,兰玉彬.美国农业航空技术现状和发展趋势分析[J].农业机械学报,2013,44(5):194-201.
[3]郑加强,周宏平,徐幼林,等. 农药精确对靶施用及其系统设计[J]. 农业工程学报, 2005, 21(11):67-72.
[4]张美娜,吕晓兰,雷哓晖.可移植的对靶喷雾控制系统设计与试验[J].江苏农业学报,2017,33(5):1182-1187.
[5]ZHU H, OZKAN H E, BRAZEE R D, et al. A system to determine lag time and mixture uniformity for inline injection sprayers [J]. Applied Engineering in Agriculture, 1998, 14(2):103-110.
[6]LUCK J D, SHEARERS, LUCK B D, et al. Recalibration methodology to compensate for changing fluid properties in an individual nozzle direct injection system [J]. Transactions of the ASABE, 2016, 59(3):847-859.
[7]VONDRICKA J, LAMMERS P S. Evaluation of a carrier control valve for a direct nozzle injection system [J]. Biosystems Engineering, 2009, 103(1):43-48.
[8]邹凡,肖茂华,傅秀清,等. 新型南方水田喷杆喷雾机液压系统的设计与分析[J].江苏农业学报,2018，34(1):220-224．
[9]邓巍,何雄奎,丁为民. 基于压力变量喷雾的雾化特性及其比较[J]. 江苏大学学报(自然科学版), 2009, 30(6):545-548.
[10]ZHU H, OZKAN H E, FOX R D, et al. Mixture uniformity in supply lines and spray patterns of a laboratory injection sprayer [J]. Transactions of the ASAE，1998, 14(3):223-230.
[11]VONDRICKA J, LAMMERS P S. Evaluation of a carrier control valve for a direct nozzle injection system[J]. Biosystems Engineering, 2009, 103(1):43-48.
[12]HLOBEN P. Study on the response time of direct injection systems for variable rate application of herbicides [ D ]. Bonn: University of Bonn, 2007.
[13]CHEN Y, ZHU H, OZKAN H E. Development of a variable-rate sprayer with laser scanning sensor to synchronize spray outputs to tree structures[J]. Transactions of the ASABE, 2012, 55(3):773-781.
[14]LIU H, ZHU H, SHEN Y, et al. Development of digital flow control system for multi-channel variable-rate sprayers[J]. Transactions of the ASABE, 2014, 57(1):273-281.
[15]吴春笃,杜彦生,张伟,等. 脉宽调制型变量喷雾系统雾量沉积分布[J]. 农业机械学报, 2007, 38(12):70-73.
[16]邓巍,丁为民. 基于PWM技术的连续式变量喷雾装置设计与特性分析[J]. 农业机械学报, 2008, 39(6):77-80.
[17]翟长远,王秀,密雅荣,等. PWM变量喷雾喷头流量模型[J]. 农业机械学报, 2012, 43(4):40-44.
[18]魏新华,蒋杉,孙宏伟,等. PWM间歇喷雾式变量喷施控制器设计与测试[J]. 农业机械学报, 2012, 43(12):87-93.
[19]蒋焕煜,周鸣川,童俊华,等. 基于卡尔曼滤波的PWM变量喷雾控制研究[J]. 农业机械学报, 2014, 45(10):60-65.
[20]李龙龙,何雄奎,宋坚利,等. 基于高频电磁阀的脉宽调制变量喷头喷雾特性[J]. 农业工程学报, 2016, 32(1):97-103.
[21]SHEN Y, ZHU H. Embedded computer-controlled premixing inline injection system for air-assisted variable-rate sprayers [J]. Transactions of the ASABE, 2015, 58(1):39-46.
[22]张敏,范龙,代祥,等. 基于BP神经网络的变量喷雾供药系统研究[J]. 林业工程学报, 2017, 2(2):133-137.
[23]李晋阳,贾卫东,魏新华. 基于流量调节阀和神经网络的植保机械在线混药装置[J]. 农业机械学报, 2014, 45(11):98-103.
[24]蒲春,孙政顺,赵世敏. Matlab神经网络工具箱BP算法比较[J]. 计算机仿真, 2006, 23(5):142-144.
[25]田亮，罗宇，王阳. 基于遗传算法优化BP神经网络的TIG焊缝尺寸预测模型[J]. 上海交通大学学报（自然科学版）, 2013, 47(11): 1690-1696.

备注/Memo

备注/Memo:
收稿日期：2018-07-03 基金项目：江苏省基础研究计划青年基金项目(BK20170930);国家林业局“948”项目（2015-4-56）;江苏高校 “青蓝工程”项目；“333”人才培养工程项目 作者简介：代祥（1993-），男，安徽亳州人，博士研究生，主要从事农林机械化与自动化技术研究。(E-mail)18852089528@139.com 通讯作者：徐幼林，(E-mail)youlinxu@njfu.edu.cn
更新日期/Last Update: 2019-05-05