高峰;冯民权;滕素芬;

• 1:西安理工大学陕西省西北旱区生态水利工程重点实验室

摘要(Abstract)：

为快速准确地预测河流水质,结合汾河监测数据,使用粒子群算法(PSO)优化BP神经网络模型(PSO-BP)进行水质预测。通过灰色关联度分析确定输入变量,利用PSO算法修正BP网络的初始权值、阈值,优化神经网络结构及算法全局收敛性。采用该模型对汾河主要污染物指标COD、BOD5、氨氮、挥发酚等进行预测和验证。结果表明,与传统的BP神经网络模型相比,PSO-BP模型使最大相对误差从15.43%减小到1.46%,其平均误差由4.00%减小到1.01%,预测均方根误差从5.956×10-3减小到1.605×10-4。因此,基于PSO-BP神经网络模型的预测更加精确,可用于水质预测。

关键词(KeyWords)： 环境工程学;粒子群算法;水质;灰色关联度;预测

Abstract:

Keywords:

基金项目(Foundation): 高等学校博士学科点专项科研基金博导类课题(20126118110015);; 陕西省科技统筹创新工程重点实验室项目(2013SZS02-Z01)

作者(Authors): 高峰;冯民权;滕素芬;

参考文献(References)：

• [1]OH H M,AHN C Y,LEE J W,et al.Community patterning and identification of predominant factors in algalbloom in Daechung Reservoir(Korea)using artificial neural networks[J].Ecological Modelling,2007,203(2):109-118.
• [2]ZHANG Zhi(张志).Study on artificial neural network model for water quality prediction[J].Acta Scientiarum Naturalium Universitatis Neimongol(内蒙古大学学报:自然科学版),2006,37(6):703-707.
• [3]YUAN Honglin(袁宏林),GONG Ling(龚令).Forecasting the water quality index in Zaohe River based on BP neural network model[J].Journal of Safety and Environment(安全与环境学报),2013,13(2):106-110.
• [4]GUO Liang(郭亮),WANG Peng(王鹏),ZHAO Ying(赵英).Water quality forecast through application of BP neural network at Sifangtai[J].Journal of Harbin Institute of Technology(哈尔滨工业大学学报),2009,41(6):62-66.
• [5]LIU Dongjun(刘东君),ZOU Zhihong(邹志红).Application of weighed combination model on forecasting water quality[J].Acta Scientiae Circumstantiae(环境科学学报),2012,32(12):3128-3132.
• [6]WU Chengxuan(吴承璇),ZHANG Yingying(张颖颖),LEI Zhuo(雷卓).Water quality parameter prediction using neural network based on time series[J].Water Resources and Power(水电能源科学),2013,31(2):47-49.
• [7]ZHAO Shixin(赵世新),ZHANG Chen(张晨),LI Jingyi(李静怡),et al.Predicted water-quality evaluation of Lihe sector in Luanhe diversion to Tianjin water project based on BP neural network[J].Journal of Safety and Environment(安全与环境学报),2010,10(2):93-96.
• [8]BAI Jizhong,YANG Jianming,FENG Minquan.Study on the water environmental capacity and the sewage control of the Sushui River[J].Advanced Materials Research,2012,433/434/435/436/437/438/439/440:995-1001.
• [9]GAO Shang(高尚),YANG Jingyu(杨静宇).Research on chaos particle swarm optimization algorithm[J].Pattern Recognition and Aitificial Intelligence(模式识别与人工智能),2006,19(2):266-270.
• [10]WANG Wenjuan(王文娟),CAO Junxing(曹俊兴),ZHANG Yuanbiao(张元标),et al.Reservoir parameter reduction of neural network based on particle swarm optimization[J].Journal of Southwest Petroleum University(西南石油大学学报),2007,29(6):31-34.
• [11]LI Zuoyong(李祚泳),WANG Jiayang(汪嘉杨),GUO Chun(郭淳).A new method of BP network optimized based on particle swarm optimization and simulation test[J].Acta Electronica Sinica(电子学报),2008,36(11):2224-2228.
• [12]XU Longqin(徐龙琴),LIU Shuangyin(刘双印).Study of short term water quality prediction model based on PSO-WSVR[J].Journal of Zhengzhou University:Engineering Science(郑州大学学报:工学版),2013,34(3):112-116.
• [13]YU Yingjie(虞英杰),JIANG Weigang(蒋卫刚),XU Mingfang(徐明芳).Prediction of chlorophyll a by BP neural network based on PSO algorithm[J].Research of Environmental Sciences(环境科学研究),2011,24(5):526-532.
• [14]WANG Ping(王平),WANG Caiyun(王彩芸),WANG Wenjian(王文健),et al.Application of BP ANN optimized by hybrid algorithm based on PSO in wear volume prediction of rail steel[J].Journal of Machine Design(机械设计),2013,30(8):15-20.
• [15]FENG Minquan(冯民权),XING Xiaopeng(邢肖鹏),XUE Pengsong(薛鹏松).Water quality prediction using BP network and Markov model:based on grey incidence analysis[J].Journal of Natural Disasters(自然灾害学报),2011,10(5):169-175.