Please wait a minute...
浙江大学学报(工学版)  2019, Vol. 53 Issue (7): 1323-1330    DOI: 10.3785/j.issn.1008-973X.2019.07.011
自动化技术、计算机技术     
基于IABC-RBF神经网络的地下水埋深预测模型
邵光成1(),章坤1,王志宇1,王小军2,3,卢佳1
1. 河海大学 农业工程学院,江苏 南京 210098
2. 南京水利科学研究院 水文水资源与水利工程科学国家重点实验室,江苏 南京 210029
3. 水利部应对气候变化研究中心,江苏 南京 210029
Groundwater depth prediction model based on IABC-RBF neural network
Guang-cheng SHAO1(),Kun ZHANG1,Zhi-yu WANG1,Xiao-jun WANG2,3,Jia LU1
1. College of Agricultural Engineering, Hohai University, Nanjing 210098, China
2. State Key Laboratory of Hydrology-Water Resources and Hydraulic Engineering, Nanjing Hydraulic Research Institute, Nanjing 210029, China
3. Research Center for Climate Change, Ministry of Water Resources, Nanjing 210029, China
 全文: PDF(894 KB)   HTML
摘要:

为了验证基于改进人工蜂群算法的径向基函数(RBF)神经网络模型在地下水埋深预测中的可行性和优越性,在基本人工蜂群算法中引入高斯变异算子,优化初始蜜源位置,设计建立基于改进人工蜂群算法的RBF神经网络模型(IABC-RBF). 通过输入泾惠渠灌区的年降雨量、年渠首引水量、年田间灌溉用水量、年地下水开采量和前一年的地下水埋深共5个相关影响因子的数据,对地下水埋深进行预测,与实测的地下水埋深数据进行比较,误差很小. 与RBF神经网络模型和基于基本人工蜂群算法训练的RBF神经网络模型(ABC-RBF)的预测结果进行比较,结果表明,基于改进人工蜂群算法的RBF神经网络模型收敛速度更快,预测结果误差最小,精度最高.

关键词: 人工蜂群算法径向基函数神经网络高斯变异泾惠渠灌区地下水埋深预测    
Abstract:

The Gaussian mutation operator was introduced into the basic artificial bee colony algorithm, and the initial nectar location was optimized in order to verify the feasibility and superiority of radial basis function (RBF) neural network model based on improved artificial bee colony algorithm in groundwater depth prediction. A RBF neural network model was designed based on improved artificial bee colony algorithm (IABC-RBF). The groundwater depth was predicted by inputting the annual rainfall, the amount of annual water intake in the first ditch, the amount of annual field irrigating, the annual groundwater exploitation and the groundwater depth in the previous year of Jinghui irrigation district. The error is very small compared with the measured groundwater depth data. The model was compared with the RBF neural network model and the RBF neural network model based on the basic artificial bee colony algorithm (ABC-RBF). Results show that the RBF neural network model based on the improved artificial bee colony algorithm has faster convergence speed, the least error of the prediction result and the highest accuracy.

Key words: artificial bee colony algorithm    radial basis function neural network    Gaussian mutation    Jinghui irrigation district    groundwater depth    prediction
收稿日期: 2018-05-17 出版日期: 2019-06-25
CLC:  P 332  
作者简介: 邵光成(1975—),男,教授,从事农业水资源高效利用研究. orcid.org/0000-0001-6353-362X. E-mail: sgcln@126.com
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
作者相关文章  
邵光成
章坤
王志宇
王小军
卢佳

引用本文:

邵光成,章坤,王志宇,王小军,卢佳. 基于IABC-RBF神经网络的地下水埋深预测模型[J]. 浙江大学学报(工学版), 2019, 53(7): 1323-1330.

Guang-cheng SHAO,Kun ZHANG,Zhi-yu WANG,Xiao-jun WANG,Jia LU. Groundwater depth prediction model based on IABC-RBF neural network. Journal of ZheJiang University (Engineering Science), 2019, 53(7): 1323-1330.

链接本文:

http://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2019.07.011        http://www.zjujournals.com/eng/CN/Y2019/V53/I7/1323

图 1  各影响因素与地下水埋深动态关系图
图 2  径向基函数(RBF)神经网络模型结构示意图
图 3  改进人工蜂群算法优化过程图
图 4  RBF神经网络模型结构示意图
序号 参数
Goal Spread MN
1 0.000 862 1.826 070 8
2 0.000 498 2.933 067 10
3 0.000 798 1.688 562 12
4 0.000 789 1.825 936 12
5 0.000 254 1.326 492 11
6 0.000 467 2.526 777 14
7 0.000 207 1.522 293 9
8 0.000 309 1.318 309 8
9 0.000 763 1.383 367 7
10 0.000 168 2.421 241 8
表 1  RBF神经网络模型参数训练结果
图 5  IABC-RBF神经网络模型预测值与实测值对比图
年份 实测值/m 模型 预测值/m MRE/%
最优 最差 平均
2006 15.59 RBF ? ? 14.97 3.95
2006 15.59 ABC-RBF 15.76 16.07 15.85 1.66
2006 15.59 IABC-RBF 15.74 15.92 15.83 1.51
2007 15.57 RBF ? ? 14.56 6.46
2007 15.57 ABC-RBF 15.73 16.27 16.02 2.91
2007 15.57 IABC-RBF 15.79 16.18 15.97 2.58
2008 15.78 RBF ? ? 15.15 4.01
2008 15.78 ABC-RBF 15.69 15.32 15.55 1.44
2008 15.78 IABC-RBF 15.71 15.42 15.59 1.20
2009 16.21 RBF ? ? 17.19 6.08
2009 16.21 ABC-RBF 16.06 14.97 15.66 3.38
2009 16.21 IABC-RBF 16.06 15.59 15.75 3.04
2010 16.25 RBF ? ? 14.78 9.05
2010 16.25 ABC-RBF 16.25 16.04 16.20 0.68
2010 16.25 IABC-RBF 16.25 16.11 16.25 0.03
表 2  3种模型预测结果的对比
图 6  3种模型预测结果的平均相对误差对比
模型 MRE/% σ/m
RBF模型 5.91 0.992 2
ABC-RBF模型 2.01 0.356 5
IABC-RBF模型 1.67 0.305 9
表 3  预测结果的平均相对误差和方差对比
图 7  每次迭代后的最佳值
1 刘东, 付强 三江平原井灌水稻地区地下水动态变化规律的小波神经网络分析[J]. 灌溉排水学报, 2008, 27 (3): 86- 89
LIU Dong, FU Qiang Dynamic variation regularities analysis of groundwater in well irrigation paddy in sanjiang plain based on waveletneural network[J]. Journal of Irrigation and Drainage, 2008, 27 (3): 86- 89
2 CHINH L V, HIRAMATSU K, HARADA M Estimation of water levels in a main drainage canal in a flat low-lying agricultural area using artificial neural network models[J]. Agricultural Water Management, 2009, 96 (9): 1332- 1338
doi: 10.1016/j.agwat.2009.04.005
3 张斌, 刘俊民 基于BP神经网络的地下水动态预测[J]. 水土保持研究, 2012, 19 (5): 235- 237
ZHANG Bin, LIU Jun-min Prediction of groundwater dynamics based on the BP neural network[J]. Research of Soil and Water Conservation, 2012, 19 (5): 235- 237
4 曹文洁, 肖长来, 梁秀娟, 等 RBF神经网络在地下水动态预测中的应用[J]. 水利水电技术, 2018, 49 (2): 43- 48
CAO Wen-jie, XIAO Chang-lai, LIANG Xiu-juan, et al Application of RBF neural network for groundwater dynatic prediction[J]. Water Resources and Hydropower Engineering, 2018, 49 (2): 43- 48
doi: 10.3969/j.issn.1672-9900.2018.02.014
5 曹邦兴 基于蚁群径向基函数网络的地下水预测模型[J]. 计算机工程与应用, 2010, 46 (2): 224- 226
CAO Bang-xing Prediction model of underground water level that combined ant colony algorithms with RBF network[J]. Computer Engineering and Applications, 2010, 46 (2): 224- 226
doi: 10.3778/j.issn.1002-8331.2010.02.066
6 李慧, 周维博, 刘博洋, 等 基于粒子群优化算法的RBF神经网络在泾惠渠灌区地下水位埋深预测中的应用[J]. 水电能源科学, 2014, 32 (8): 127- 130
LI Hui, ZHOU Wei-bo, LIU Bo-yang, et al Groundwater depth prediction model in Jinghui irrigation district of RBF neural network based on particle swarm optimization[J]. Water Resources and Power, 2014, 32 (8): 127- 130
7 徐强, 束龙仓, 杨桂莲, 等 基于遗传算法优化的小波神经网络在地下水位预测中的应用[J]. 水文, 2010, 30 (1): 27- 30
XU Qiang, SHU Long-cang, YANG Gui-lian, et al Application of optimized wavelet neuralnetwork based on genetic algorithm in groundwater level prediction[J]. Journal of China Hydrology, 2010, 30 (1): 27- 30
8 KARABOGA D. An idea based on honey beeswarm for numerical optimization [R]. Kayseri: Erciyes University, 2005.
9 KARABOGA D, BASTURK B On the performance of artificial bee colony (ABC) algorithm[J]. Applied Soft Computing, 2008, (8): 687- 697
10 李文莉, 李郁侠, 任平安 基于云变异人工蜂群算法的梯级水库群优化调度[J]. 水力发电学报, 2014, 33 (1): 37- 42
LI Wen-li, LI Yu-xia, REN Ping-an Optimaloperatin of cascade reservoirs based on cloud variation-artificial bee colony algorithm[J]. Journal of Hydroelectric Engineering, 2014, 33 (1): 37- 42
11 钱坤, 苏国韶 人工蜂群算法在渠道断面优化设计中的应用[J]. 水利水电科技进展, 2011, 31 (3): 57- 60
QIAN Kun, SU Guo-shao Application of artificial bee colony algorithm to optimizationof channel section[J]. Advances in Science and Technology of Water Resources, 2011, 31 (3): 57- 60
12 黄文明, 徐双双, 邓珍荣, 等 改进人工蜂群算法优化RBF神经网络的短时交通流预测[J]. 计算机工程与科学, 2016, 38 (4): 713- 719
HUANG Wen-ming, XU Shuang-shuang, DENG Zhen-rong, et al Short-term traffic flow prediction of optimized RBF neural networks based on the modified ABC algorithm[J]. Computer Engineering and Science, 2016, 38 (4): 713- 719
doi: 10.3969/j.issn.1007-130X.2016.04.015
13 苏彩红, 向娜, 陈广义, 等 基于人工蜂群算法与BP神经网络的水质评价模型[J]. 环境工程学报, 2012, 6 (2): 699- 704
SU Cai-hong, XIANG Na, CHEN Guang-yi, et al Water quality evaluation model based on artificial bee colony algorithm and BP neural network[J]. Chinese Journal of Environmental Engineering, 2012, 6 (2): 699- 704
14 许贤杰, 周玲, 蒋丹, 等 基于人工蜂群算法计及线路故障的配电网网络重构[J]. 电测与仪表, 2014, 51 (3): 33- 36
XU Xian-jie, ZHOU Ling, JIANG Dan, et al Distribution network reconfiguration based on artificial bee colony algorithm and line fault[J]. Electrical Measurement and Instrumentation, 2014, 51 (3): 33- 36
doi: 10.3969/j.issn.1001-1390.2014.03.008
15 刘三阳, 张平, 朱明敏 基于局部搜索的人工蜂群算法[J]. 控制与决策, 2014, 29 (1): 123- 128
LIU San-yang, ZHANG Ping, ZHU Ming-min Artificial bee colony algorithm based on local search[J]. Control and Decision, 2014, 29 (1): 123- 128
16 罗钧, 李研 具有混沌搜索策略的蜂群优化算法[J]. 控制与决策, 2010, 25 (12): 1913- 1916
LUO Jun, LI Yan Artificial bee colony algoithm with chaotic-search strategy[J]. Control and Decision, 2010, 25 (12): 1913- 1916
17 暴励, 曾建潮 自适应搜索空间的混沌蜂群算法[J]. 计算机应用研究, 2010, 27 (4): 1330- 1334
BAO LI, ZENG Jian-chao Self-adapting search space chaos-artificial bee colony algorithm[J]. Application Research of Computers, 2010, 27 (4): 1330- 1334
18 姜鹏, 刘俊民, 黄一帆, 等 泾惠渠地下水对气候变化和人类活动的响应[J]. 人民黄河, 2014, 36 (5): 45- 47
JIANG Peng, LIU Jun-min, HUANG Yi-fan, et al Groundwater response to climate change and human activities in Jinghuiqu[J]. Yellow River, 2014, 36 (5): 45- 47
19 向娜. 基于神经网络和人工蜂群算法的水质评价和预测研究[D]. 广州: 华南理工大学, 2012.
XIANG Na. Water quality evaluation and prediction based on neural network and artificial bee colony algorithm [D]. Guangzhou: South China University of Technology, 2012.
20 王晓慧, 刘雪英, 白梅花 引入高斯变异和最速下降算子的人口迁移算法[J]. 计算机工程与应用, 2009, 45 (20): 57- 60
WANG Xiao-hui, LIU Xue-ying, BAI Mei-hua Population migration algorithm with Gaussian mutation and the steepest descent operator[J]. Computer Engineering and Applications, 2009, 45 (20): 57- 60
doi: 10.3778/j.issn.1002-8331.2009.20.017
21 刘运, 程家兴, 林京 基于高斯变异的人工萤火虫算法在云计算资源调度中的研究[J]. 计算机应用研究, 2015, 32 (3): 834- 837
LIU Yun, CHENG Jia-xing, LIN Jing Study of artificial glowworm algorithm based on Gauss mutation in resource scheduling of cloud computing[J]. Application Research of Computers, 2015, 32 (3): 834- 837
doi: 10.3969/j.issn.1001-3695.2015.03.044
22 张京京. 渠井结合灌区地下水位动态对变化环境的响应及调控研究[D]. 杨凌: 西北农林科技大学, 2016.
ZHANG Jing-jing. Groundwater dynamic response and regulation under variational environment in canal-well combined irrigation district [D]. Yangling: Northwest A&F University, 2016.
[1] 许佳辉,王敬昌,陈岭,吴勇. 基于图神经网络的地表水水质预测模型[J]. 浙江大学学报(工学版), 2021, 55(4): 601-607.
[2] 于勇,薛静远,戴晟,鲍强伟,赵罡. 机加零件质量预测与工艺参数优化方法[J]. 浙江大学学报(工学版), 2021, 55(3): 441-447.
[3] 毛奕喆,龚国芳,周星海,王飞. 基于马尔可夫过程和深度神经网络的TBM围岩识别[J]. 浙江大学学报(工学版), 2021, 55(3): 448-454.
[4] 黄发明,曹中山,姚池,姜清辉,陈佳武. 基于决策树和有效降雨强度的滑坡危险性预警[J]. 浙江大学学报(工学版), 2021, 55(3): 472-482.
[5] 苗发盛,吴益平,李麟玮,廖康,薛阳. 基于Boosting-决策树C5.0的岩体结构面粗糙度预测[J]. 浙江大学学报(工学版), 2021, 55(3): 483-490.
[6] 刘芳,汪震,刘睿迪,王锴. 基于组合损失函数的BP神经网络风力发电短期预测方法[J]. 浙江大学学报(工学版), 2021, 55(3): 594-600.
[7] 段有康,陈小刚,桂剑,马斌,李顺芬,宋志棠. 基于相位划分的下肢连续运动预测[J]. 浙江大学学报(工学版), 2021, 55(1): 89-95.
[8] 陈纬奇,王敬昌,陈岭,杨勇勤,吴勇. 基于深度神经网络的多因素感知终端换机预测模型[J]. 浙江大学学报(工学版), 2021, 55(1): 109-115.
[9] 李文书,邹涛涛,王洪雁,黄海. 基于双尺度长短期记忆网络的交通事故量预测模型[J]. 浙江大学学报(工学版), 2020, 54(8): 1613-1619.
[10] 江冬冬,李道飞,俞小莉. 基于驾驶员需求转矩预测的模型预测控制能量管理[J]. 浙江大学学报(工学版), 2020, 54(7): 1325-1334.
[11] 王晨霖,杨洁,居文军,顾复,陈芨熙,纪杨建. 基于智能家电的短期电力负荷预测与削峰填谷优化[J]. 浙江大学学报(工学版), 2020, 54(7): 1418-1424.
[12] 闫旭,范晓亮,郑传潘,臧彧,王程,程明,陈龙彪. 基于图卷积神经网络的城市交通态势预测算法[J]. 浙江大学学报(工学版), 2020, 54(6): 1147-1155.
[13] 刘创,梁军. 基于注意力机制的车辆运动轨迹预测[J]. 浙江大学学报(工学版), 2020, 54(6): 1156-1163.
[14] 陶正瑞,党嘉强,徐锦泱,安庆龙,陈明,王力,任斐. 曲面基体绝缘涂镀层涡流测厚高精度标定方法[J]. 浙江大学学报(工学版), 2020, 54(6): 1218-1227.
[15] 杨萍,王丹,康子健,李童,付利华,余悦任. 基于模式识别和集成CNN-LSTM的阵发性房颤预测模型[J]. 浙江大学学报(工学版), 2020, 54(5): 1039-1048.