基于神经网络和粒子群算法产流量模型构建

doi:10.3969/j.issn.1674-8530.15.0006

Abstract
Figure/Table
References
Related Citation (5)

Download: PDF (1743 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract Two runoff production models are built by using artificial neural network and particle swarm algorithm, respectively, to study the relationships between runoff production and related factors based on existing multiple scale field data. The results showed that the relationships between runoff production and slope length, width, gradient and antecedent soil water are parabolic, but those between runoff production and vegetation cover and rainfall can be described with power and linear functions, respectively. The optimum topological structure and the network parameters of the BP model for predicating runoff production are determined by means of weighted summation of relative difference, and the relative error between the model estimate and observed data is within ?20%, showing a good prediction accuracy. According to the quantitative relationship between runoff production and each factor, the empirical model of runoff production is established, and the particle swarm algorithm is used to determine model parameters. Its relative error of the empirical model is ?30%, slightly poorer than the BP model.

Key words： rainfall amount slope length vegetation slope gradient summation of relative difference

Received: 29 December 2014

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	HUANG Jun-

	KANG Qing-

	JIN Ping-Wei-

	LI Lan-Bin-

	LI Hong-Jun-
	JIANG Xue-Bing-

Cite this article:

HUANG Jun-^,,KANG Qing-^{等. Study on runoff production model by artificial neural network and particle swarm algorithm[J]. Journal of Drainage and Irrigation Machinery Engin, 2015, 33(9): 779-786.}

URL:

http://zzs.ujs.edu.cn/pgjx/EN/10.3969/j.issn.1674-8530.15.0006 OR http://zzs.ujs.edu.cn/pgjx/EN/Y2015/V33/I9/779

[1]刘金涛, 宋慧卿, 张行南,等. 新安江模型理论研究的进展与探讨[J]. 水文, 2014, 34(1): 1-6.
　　Liu Jintao, Song Huiqing, Zhang Xingnan, et al. A discussion on advances in theories of Xinanjiang model[J]. Journal of China Hydrology, 2014, 34(1): 1-6.(in Chinese)
[2]Zhang X C, Nearing M A, Risse L M, et al. Evaluation of weep runoff and soil loss predictions using natural runoff plot data[J]. Transcations of the ASAE, 1996, 39(3): 855-863.
[3]罗鹏,宋星原. 基于栅格的分布式SCS产流模型研究[J]. 水土保持通报, 2010, 30(4):138-142.
　　Luo Peng, Song Xingyuan. Raster-based distributed SCS runoff model[J]. Bulletin of Soil and Water Conservation, 2010, 30(4): 138-142.(in Chinese)
[4]梁忠民, 施晔, 李彬权, 等. 基于统计理论的产流模型[J]. 水科学进展, 2009, 20(6):789-793.
　　Liang Zhongmin, Shi Ye, Li Binquan,et al. Runoff-yield model based on statistical theory[J]. Advances In Water Science, 2009, 20(6):789-793.(in Chinese)
[5]王占礼, 黄新会, 张振国,等. 黄土裸坡降雨产流过程试验研究[J]. 水土保持通报, 2005, 25(4): 1-4.
　　Wang Zhanli, Huang Xinhui, Zhang Zhenguo, et al. Experimental study of runoff processes on bare loess hillslope[J].Bulletin of Soil and Water Conservation, 2005, 25(4): 1-4.(in Chinese)
[6]耿晓东, 郑粉莉, 张会茹. 红壤坡面降雨入渗及产流产沙特征试验研究[J]. 水土保持学报, 2009, 23(4): 39-43.
　　Geng Xiaodong, Zheng Fenli, Zhang Huiru. Effect of rainfall intensities and slope gradient on characteristics of rainfall infiltration, runoff and sediment on red soil[J]. Journal of Soil and Water Conservation, 2009, 23(4): 39-43.(in Chinese)
[7]王辉, 王全九, 邵明安. 前期土壤含水量对坡面产流产沙特性影响的模拟试验[J]. 农业工程学报, 2008, 24(5): 65-68.
　　Wang Hui, Wang Quanjiu, Shao Ming′an. Simulation experiment of effect of antecedent soil moisture content on characteristics of runoff and sediment from two soil sloping lands[J]. Transactions of the CSAE, 2008, 24(5): 65-68.(in Chinese)
[8]黄俊, 赵西宁, 吴普特. 基于通径分析和灰色关联理论的坡面产流产沙影响因子分析[J]. 四川大学学报:工程科学版, 2012, 44(5): 64-70.
　　Huang Jun, Zhao Xining, Wu Pute. Factors analysis of runoff and sediment based on path analysis and grey relational analysis[J]. Journal of Sichuan University:Engineering Science Edition, 2012, 44(5): 64-70.(in Chinese)
[9]程琴娟, 蔡强国, 郑明国. 黄土土壤结皮对产流临界雨强的影响分析[J]. 地理科学, 2007, 27(5): 678-682.
　　Cheng Qinjuan, Cai Qiangguo, Zheng Mingguo. Effects of soil crust on critical rainfall intensity of runoff production[J].Scientia Geographica Sinica, 2007, 27(5): 678-682.(in Chinese)
[10]Zhao X N, Chen X L, Huang J, et al. Effects of vegetation cover of natural grassland on runoff and sediment yield on loess hilly region of China[J]. Journal of the Science of Food and Agriculture, 2013, 94(3): 497-503.
[11]Huang J, Zhao X N, Wu P T. Surface runoff volumes from vegetated slopes during simulated rainfall events[J]. Journal of Soil and Water Conservation, 2013, 68(4): 283-295.
[12]高军侠, 党宏斌, 刘作新, 等. 黄土高原南部裸露坡耕地产流产沙试验研究[J]. 生态学杂志, 2004, 23(3): 138-140.
　　Gao Junxia, Dang Hongbin, Liu Zhuoxin, et al. Research of soil and water losss law in uncovered sloping field of Loess Plateau[J]. Chinese Journal of Ecology, 2004, 23(3): 138-140.(in Chinese)
[13]吴发启, 赵晓光, 刘秉正. 缓坡耕地降雨、入渗对产流的影响分析[J]. 水土保持研究,2000, 7(1): 12-17,37.
　　Wu Faqi,Zhao Xiaoguang,Liu Bingzheng. Analysis of the effect of rainfall and infiltration on runoff in gently sloping farmland[J]. Research of Soil and Water Conservation,2000, 7(1): 12-17,37.(in Chinese)
[14]Puigdefábregas J, Barrio G, Boer M M, et al. Differential responses of hillslope and channel elements to rainfall events in a semi-arid area[J]. Geomorphology, 1998, 23(2/3/4): 337-351.
[15]刘青泉, 陈力, 李家春. 坡度对坡面土壤侵蚀的影响分析 [J]. 应用数学和力学, 2001, 22(5): 449-457.
　　Liu Qingquan, Chen Li, Li Jiachun. Influences of slope gradient on soil erosion[J]. Applied Mathematics and Mechanics, 2001,22(5): 449-457.(in Chinese)
[16]Zhao X N, Huang J, Gao X D, et al. Runoff features of pasture and crop slopes at different rainfall intensities, antecedent moisture contents and gradients on the Chinese Loess Plateau: A solution of rainfall simulation experiments[J]. Catena, 2014, 119(1): 90-96.
[17]Ju Q, Yu Z, Hao Z, et al. Division-based rainfall-runoff simulations with BP neural networks and Xinanjiang model[J]. Neurocomputing, 2009, 72(13): 2873-2883.
[18]Abdi H, Valentin D, Edelman B, et al. A widrow-hoff learning rule for a generalization of the linear auto-associator[J]. Journal of Mathematical Psychology, 1996, 40(2): 175-182.
[19]El-Din A G, Smith D W. A neural network model to predict the wastewater inflow incorporating rainfall events[J]. Water Research, 2002, 36(5): 1115-1126.
[20]Yesilnacar M I, Sahinkaya E, Naz M, et al. Neural network prediction of nitrate in groundwater of Harran Plain, Turkey[J]. Environmental Geology, 2007, 56(1): 19-25.
[21]李遵伟, 陈明. 基于相对差距和法的改装船舶优选 [J]. 船舶工程, 2013, 35(S1): 130-133.
　　Li Zhunwei, Chen Ming. Optimization of selecting ships to convert based on the summation of relative difference[J]. Ship Engineering, 2013, 35(S1): 130-133.(in Chinese)
[22]Kennedy J, Eberhart R. Particle swarm optimization[C]//Proceedings of IEEE International Conference on Neural Networks, 1995.
[23]Schmitt M, Wanka R. Particle swarm optimization almost surely finds local optima[J]. Theoretical Computer Science, 2015, 561: 57-72.
[24]Shi Y H, Eberhart R. Empirical study of particle swarm optimization[C]//Proceedings of the 1999 Congress on Evolutionary Computation. Washington DC, 1999.