排灌机械工程学报
   首页  学报介绍  编 委 会  作者园地  征订启事  编校法规  编读往来  录用公告  广告合作   行业新闻  留  言  English 
排灌机械工程学报  2019, Vol. 37 Issue (3): 263-269    DOI: 10.3969/j.issn.1674-8530.17.0225
泵理论与技术 最新目录 | 下期目录 | 过刊浏览 | 高级检索 Previous Articles  |  Next Articles  
BP和RBF神经网络预测射流式喷头射程对比
胡广,朱兴业*,袁寿其,张林国,李扬帆
江苏大学国家水泵及系统工程技术研究中心, 江苏 镇江 212013
Comparison of ranges of fluidic sprinkler predicted with BP and RBF neural network models
HU Guang, ZHU Xingye*, YUAN Shouqi, ZHANG Linguo, LI Yangfan
National Research Center of Pumps, Jiangsu University, Zhenjiang, Jiangsu 212013, China
 全文: PDF (2459 KB)   HTML (1 KB)   输出: BibTeX | EndNote (RIS)      背景资料
摘要 为了探究适合全射流喷头多因素下射程的预测模型,通过改变喷头工作压力、安装高度、喷嘴直径、喷头仰角共4个参数,对射程进行测量.基于BP神经网络和广义径向基(RBF)神经网络的基本原理和算法,建立了全射流喷头射程预测的BP和RBF神经网络模型,并分析BP和RBF神经网络的预测性能.结果表明射程与工作压力、喷嘴直径呈非线性关系;当喷头在1.2 m安装高度、27°仰角、4~10 mm喷嘴直径时,压力增大到0.4 MPa,射程趋于极限,并且安装高度与射程呈正相关关系.BP与RBF神经网络均能较好地表达全射流喷头射程与主控因素之间的非线性关系.在训练时间方面,RBF网络比BP网络慢8.05 s;预测过程中,BP网络在每次运行程序时的预测结果不一定相同,而RBF网络则不会出现此问题,且RBF网络预测值与实测值之间的平均绝对误差比BP网络的小3.55%.从网络预测总体效果观察,RBF神经网络预测喷头射程具有更好的推广能力.
服务
把本文推荐给朋友
加入我的书架
加入引用管理器
E-mail Alert
RSS
作者相关文章
胡广
朱兴业*
袁寿其
张林国
李扬帆
关键词全射流喷头   射程   预测   BP神经网络   RBF神经网络     
Abstract: To explore a suitable multi-parameter model for predicting ranges of completely fluidic sprinkler, the ranges of a fluidic sprinkler were measured by varying four parameters such as installation height, diameter, nozzle tilt angle and working pressure. Based on the basic principles and algorithms of BP neural network and generalized radial basis(RBF)neural network, BP and RBF neural network models for range prediction of the fluidic sprinkler were established and their performance in the prediction was analyzed. The results show that the range is related nonlinearly to the working pressure and nozzle diameter. For the nozzle installed at 1.2 m height, 27° tilt angle and with a diameter ranged in 4-10 mm, when the working pressure is increased to 0.4 MPa, the range tends to reach a limit, but also the installation height is correlated positively with the range. Both BP and RBF neural net-works can better express the nonlinear relationship between the range and the main control parameters of the fluidic sprinkler. In terms of training time, the RBF network is 8.05 s longer than the BP network. In the prediction process, the BP network program can produce the same result unnecessarily in each run, however, this problem doesn′t exist in the RBF network. Further, the average prediction error of the RBF network against the measurements is 3.55% smaller than that of the BP network. Based on the overall effectiveness of both networks in prediction, the nozzle range predicted by RBF neural network model has an even better applicability.
Key wordscomplete fluidic sprinkler   range   prediction   BP neural network   RBF neural network   
收稿日期: 2017-10-16;
基金资助:“十三五”国家重点研发计划项目(2016YFC0400202);江苏高校优势学科建设工程项目(PAPD)
引用本文:   
胡广,朱兴业*,袁寿其等. BP和RBF神经网络预测射流式喷头射程对比[J]. 排灌机械工程学报, 2019, 37(3): 263-269.
HU Guang,ZHU Xing-Ye-*,YUAN Shou-Qi et al. Comparison of ranges of fluidic sprinkler predicted with BP and RBF neural network models[J]. Journal of Drainage and Irrigation Machinery Engin, 2019, 37(3): 263-269.
 
[1] 李世英. 喷灌喷头理论与设计[M]. 北京:兵器工业出版社. 1995.
[2] 陆梦雅,陆科骥,胡广,等. SD-03型地埋式喷头水力性能试验研究[J]. 排灌机械工程学报, 2018,36(11): 1120-1124. 浏览
LU Mengya, LU Keji, HU Guang, et al. Experiment on hydraulic performance of type SD-03 pop-up sprinkler[J]. Journal of drainage and irrigation machinery engineering, 2018,36(11):1120-1124.(in Chinese)
[3] EDLING R J. Kinetic energy,evaporation and wind drift of droplet from low pressure irrigation nozzles[J].Transac-tion of the ASAE,1985,28(5):1543-1550.
[4] 干浙民,杨生华. 旋转式喷头射程的试验研究及计算公式[J]. 农业机械学报,1998,29(4):145-149.
GAN Zhemin, YANG Shenghua. The formula and experimental research on the range of the whirl sprinkler[J]. Transactions of the CSAM, 1998,29(4):145-149.(in Chinese)
[5] De LIMA J L M P,TORFS P J J F,SINGH V P. A mathematical model for evaluating the effect of wind on downward-spraying rainfall simulators[J]. Catena,2002, 46(4):221-241.
[6] 脱云飞,杨路华,柴春岭,等. 喷头射程理论公式与试验研究[J]. 农业工程学报, 2006,22(1):23-26.
TUO Yunfei, YANG Luhua, CHAI Chunling, et al. Experimental study and theoretical formula of the sprinkler range[J]. Transactions of the CSAE, 2006,22(1):23-26.(in Chinese)
[7] 吕名礼, 张中华, 刘俊萍. 微喷头水力性能及喷灌组合均匀性试验研究[J]. 排灌机械工程学报,2017,35(7):641-644. 浏览
LYU Mingli, ZHANG Zhonghua, LIU Junping. Experimental study on hydraulic performance and combined uniformity of micro sprinklers[J]. Journal of drainage and irrigation machinery engineering, 2017,35(7):641-644.(in Chinese)
[8] 刘敏华. BP网络模型在大型泵站用电量预测中的应用[J]. 水电能源科学,2004,22(1):86-88.
LIU Minhua. Application of BP model to power consumption forecast in big pump station[J]. Water resources and power, 2004,22(1):86-88.(in Chinese)
[9] 王晓玲. 基于DEBBO-LM算法的BP网络非线性系统辨识[D]. 成都:西南交通大学,2012.
[10] 陈光华. 人工神经网络在证券价格预测中的应用[J]. 计算机仿真, 2007,24(10):244-248.
CHEN Guanghua. Application of artificial neural net-works in price forecast of securities market[J]. Compu-ter simulation, 2007,24(10):244-248.(in Chinese)
[11] 张宏,马岩,李勇,等. 基于BP神经网络的核桃破裂功预测模型[J]. 农业工程学报,2014,30(18):78-84.
ZHANG Hong, MA Yan, LI Yong, et al. Rupture energy prediction model for walnut shell breaking based on genetic BP neural network[J]. Transactions of the CSAE, 2014,30(18):78-84.(in Chinese)
[12] 涂琴,李红,王新坤,等. 不同指标轻小型喷灌机组配置优化[J]. 农业工程学报,2013,29(22):83-89.
TU Qin, LI Hong, WANG Xinkun, et al. Optimization of small-scale sprinkler irrigation systems for different indicators[J]. Transactions of the CSAE, 2013,29(22):83-89.(in Chinese)
[13] 王波雷,马孝义,郝晶晶. 基于L-M优化算法的喷头射程神经网络预测模型[J]. 农业机械学报,2008,39(5):36-40,35.
WANG Bolei, MA Xiaoyi, HAO Jingjing. Prediction of sprinkler nozzle range based on L-M optimized algorithm[J]. Transactions of the CSAM, 2008,39(5):36-40,35.(in Chinese)
[14] 楼文高,刘遂庆.区域水资源可持续利用评价的神经网络方法[J].农业系统科学与综合研究,2004,20(2):113-119.
LOU Wengao, LIU Suiqing. On assessment of sustainable development level of regional water resource using artificial neural networks[J]. System sciences and comprehensive studies in agriculture, 2004,20(2):113-119.(in Chinese)
[15] MOODY J,DARKEN C J. Fast learning in networks of locally-tuned processing units[J]. Neural computation, 2014, 1(2):281-294.
[16] COUREY A J, HOLTZMAN D A, JACKSON S P, et al. Syner-gistic activation by the glutamine-rich domains of human transcription factor Sp1[J]. Cell, 1989, 59(5):827-836.
[17] 刘兴发. 全射流喷头水滴分布特性试验研究[D]. 镇江:江苏大学,2016.
[18] 刘俊萍,袁寿其,李红,等. 全射流喷头射程与喷洒均匀性影响因素分析与试验[J]. 农业机械学报,2008,39(11):51-54.
LIU Junping, YUAN Shouqi, LI Hong, et al. Analysis and experiment on influencing factors of range and spraying uniformity for complete fluidic sprinkler[J]. Transactions of the CSAM, 2008,39(11):51-54.(in Chinese)
[19] 任自中. 柴油机相继增压系统的理论与试验研究[J]. 内燃机工程,2001(1):32-37.
[20] REN Zizhong. Theoretical and experimental study on the sequential turbocharging system of diesel engines[J]. Chinese internal combustion engine engineering, 2001(1):32-37.(in Chinese)
[1] 李扬帆, 刘俊萍*, 李滔, 许继恩. 多因素下全射流喷头射程计算模型及试验[J]. 排灌机械工程学报, 2018, 36(8): 685-689.
[2] 江显群, 陈武奋*. BP神经网络与GA-BP农作物需水量预测模型对比[J]. 排灌机械工程学报, 2018, 36(8): 762-766.
[3] 黄思, 康文明*, 邱光琦, 王学谦. 基于CFD的全金属单螺杆泵非稳态流场计算及性能预测[J]. 排灌机械工程学报, 2018, 36(12): 1211-1215.
[4] 张娜,, 张红玲, 张栋良, 屈忠义*. 基于高光谱的区域土壤颗粒组成及有机质预测模型尺度转换[J]. 排灌机械工程学报, 2018, 36(11): 1175-1179.
[5] 徐胜荣, 王新坤*, 肖思强, 樊二东, 张晨曦, 薛子龙, 王轩. 双喷嘴射流喷头数值模拟和射程试验研究[J]. 排灌机械工程学报, 2018, 36(10): 981-984.
[6] 刘俊萍1, 刘伟忠2, 鲍亚1, 张前1, 刘兴发1. 全射流喷头水滴分布试验及模型[J]. 排灌机械工程学报, 2017, 35(8): 731-.
[7] 韩志慧, 刘小刚, 郝琨, 余宁, 刘艳伟, 杨启良. 基于SPI指数的内蒙古地区干旱演变特征及趋势预测[J]. 排灌机械工程学报, 2017, 35(5): 430-439.
[8] 王蒙蒙, 戴凌全, 戴会超,, 毛劲乔, 梁璐. 基于支持向量回归的洞庭湖水位快速预测[J]. 排灌机械工程学报, 2017, 35(11): 954-961.
[9] 王洋, 赵立峰, 刘志超, 宁超, 朱振涛, 谢山峰. 多级离心泵水力性能数值预测涡量分析法[J]. 排灌机械工程学报, 2016, 34(7): 561-566.
[10] 薛延刚. 基于EMD和Multi-fractal spectrum的BP水机故障诊断[J]. 排灌机械工程学报, 2016, 34(5): 455-460.
[11] 杨兴标, 李红, 陈超. 湍流模型对离心泵扬程预测准确性的影响[J]. 排灌机械工程学报, 2015, 33(8): 656-660.
[12] 王春林, 曾成, 杨晓勇, 彭海菠, 刘栋. 双吸泵正反转内部流场数值模拟及性能预测[J]. 排灌机械工程学报, 2015, 33(7): 577-582.
[13] 朱兴业,, 蒋建园, 刘俊萍, 刘兴发, 胡斌. 外取水射流喷头与全射流喷头的比较[J]. 排灌机械工程学报, 2015, 33(2): 172-178.
[14] 叶道星, 李红, 庄海飞, 汤攀, 邹晨海. 中浓纸浆泵湍流发生器设计与试验研究[J]. 排灌机械工程学报, 2015, 33(11): 921-925.
[15] 王圃,, 王以知,, 张晋, 王颖,. 基于用水量驱动因子的水量预测模型[J]. 排灌机械工程学报, 2014, 32(12): 1051-1056.

江苏大学梦溪校区(镇江市梦溪园巷30号)图书馆5楼 0511-84440893 传真0511--84440033
Copyright 江苏大学杂志社 2010-2015 All Rights Reserved