[1]卢毅敏,张红.结合时间序列分解和神经网络的河流溶解氧预测[J].华侨大学学报(自然科学版),2020,41(5):659-666.[doi:10.11830/ISSN.1000-5013.202001027]
　LU Yimin,ZHANG Hong.Prediction of River Dissolved Oxygen Combined Times Series Decomposition and Neural Network[J].Journal of Huaqiao University(Natural Science),2020,41(5):659-666.[doi:10.11830/ISSN.1000-5013.202001027]
点击复制

结合时间序列分解和神经网络的河流溶解氧预测()
分享到：

《华侨大学学报（自然科学版）》[ISSN:1000-5013/CN:35-1079/N]

卷:
第41卷
期数:
2020年第5期
页码:
659-666
栏目:
出版日期:
2020-09-20

文章信息/Info

Title:
Prediction of River Dissolved Oxygen Combined Times Series Decomposition and Neural Network
文章编号:
1000-5013(2020)05-0659-08
作者:
卢毅敏1; 2; 3;  张红1; 2; 3
1. 福州大学 空间数据挖掘与信息共享教育部重点实验室, 福建 福州 350108;2. 福州大学 地理空间信息技术国家地方联合工程研究中心, 福建 福州 350108;3. 数字中国研究院(福建), 福建 福州 350003
Author(s):
LU Yimin1; 2; 3;  ZHANG Hong1; 2; 3
1. Key Lab of Spatial Data Mining and Information Sharing of Ministry of Education, Fuzhou University, Fuzhou 350108, China; 2. National Engineering Research Center of Geospatial Information Technology, Fuzhou University, Fuzhou 350108, China; 3. Academy
关键词:
河流溶解氧;  预测模型;  CEEMDAN;  样本熵;  布谷鸟搜索算法;  Elman神经网络
Keywords:
river dissolved oxygen;  forecasting models;  CEEMDAN;  sample entropy;  cuckoo search algorithm;  Elman neural network
分类号:
TP183;X832
DOI:
10.11830/ISSN.1000-5013.202001027
文献标志码:
A
摘要:
为克服小流域数据资料少,河流溶解氧的非平稳特性及动态变化造成的预测困难,提出结合具有自适应噪声的完整集成经验模态分解(CEEMDAN)和Elman动态神经网络的预测方法.使用CEEMDAN方法对原始溶解氧时序数据进行平稳化处理及降噪,提取溶解氧随时间变化的波动特征、周期特征,以及长期趋势,通过计算样本熵(SE)值,将相似的特征序列合并,以减小误差累积,对合并后的新序列分别采用布谷鸟搜索(CS)算法优化的Elman模型进行预测,将各预测值叠加,得到最终预测结果.实验结果表明:CEEMDAN-SE-CS-Elman方法平均绝对误差(EMA)为0.14;平均绝对百分误差(EMPA)为2.07%;均方根误差(ERMS)为0.24;可决系数(R2)达到0.951 6,精度较其他时间序列预测模型有所提高.
Abstract:
In order to overcome the difficulties of prediction caused by the unstable characteristics and dynamic changes of river dissolved oxygen in small watershed with few data, a prediction method was proposed based on complete ensemble empirical mode decomposition with adaptive noise(CEEMDAN)and Elman dynamic neural network. The CEEMDAN method was used to stabilize and reduce the noise of the original dissolved oxygen time series data. The fluctuation characteristics, periodic characteristics and long-term trend of dissolved oxygen with time change were extracted. By calculating the sample entropy(SE)value, several sequences with similar feature were combined to reduce the error accumulation. The Elman model optimized bythe cuckoo search(CS)algorithm was adopted to predict the new recombined sequences respectively, and thefinal prediction result was obtained by superposing the prediction results of each sequence. The experimental results showed that the mean absolute error(EMA)of CEEMDAN-SE-CS-Elman method was 0.14, the mean absolute percentage error(EMPA)was 2.07%, the root mean square error(ERMS)was 0.24, and the coefficient of determination(R2)reached 0.951 6. The prediction accuracy was improved compared with other time series forecasting models.

参考文献/References:

[1] NEMATI S,FAZELIFARD M H,TERZI ?,et al.Estimation of dissolved oxygen using data-driven techniques in the Tai Po River, Hong Kong[J].Environmental Earth Sciences,2015,74(5):4065-4073.DOI:10.1007/s12665-015-4450-3.
[2] 胡鹏,杨庆,杨泽凡,等.水体中溶解氧含量与其物理影响因素的实验研究[J].水利学报,2019,50(6):679-686.DOI:10.13243/j.cnki.slxb.20190108.
[3] 王思文,齐少群,于丹丹,等.基于WASP 模型的水环境质量预测与评价研究: 以松花江哈尔滨江段为例[J].自然灾害学报,2015,24(1):39-45.DOI:10.13577/j.jnd.2015.0106.
[4] 笪英云,汪晓东,赵永刚,等.基于关联向量机回归的DO预测模型[J].环境科学学报,2015,35(11):3730-3735.DOI:10.13671/j.hjkxxb.2015.0424.
[5] 张颖,高倩倩.基于灰色模型和模糊神经网络的综合水质预测模型研究[J].环境工程学报,2015,9(2):537-545.
[6] 宦娟,刘星桥.基于 K-means 聚类和ELM 神经网络的养殖水质溶解氧预测[J].农业工程学报,2016,32(17):174-181.DOI:10.11975/j.issn.1002-6819.2016.17.024.
[7] 陈英义,程倩倩,方晓敏,等.主成分分析和长短时记忆神经网络预测水产养殖水体溶解氧[J].农业工程学报,2018,34(17):183-191.DOI:10.11975/j.issn.1002-6819.2018.17.024.
[8] 石子泊,邹志红.基于小波变换的ARIMA模型在水质预测中的应用研究[J].环境工程学报,2014,8(10):4550-4554.
[9] XU Mei,YAN Fu,LIU Zhenzhong,et al.Forecasting of water quality using grey GM(1,1)-wavelet-GARCH hybrid method in Songhua River Basin[J].Transactions of the Chinese Society of Agricultural Engineering,2016,32(10):137-142.DOI:10.11975/j.issn.1002-6819.2016.10.019.
[10] WU Jing,LI Zhenbo,ZHU Ling,et al.Hybrid model of ARIMA model and GAWNN for dissolved oxygen content prediction[J].Transactions of the Chinese Society for Agricultural Machinery,2017(s1):204-210.
[11] 李军,李佳,张世义,等.采用EEMD算法与互信息法的机械故障诊断方法[J].华侨大学学报(自然科学版),2018,39(1):7-13.DOI:10.11830/ISSN.1000-5013.201706091.
[12] 余成洲,李勇,白云.基于集合经验模态分解和支持向量机的溶解氧预测 [J].环境监测管理与技术,2018,30(3):27-31.DOI:10.3969/j.issn.1006-2009.2018.03.007.
[13] BOUNY L E,KHALIL M,ADIB A.ECG signal filtering based on CEEMDAN with hybrid interval thresholding and higher order statistics to select relevant modes[J].Multimedia Tools and Applications,2018,78(10):13067-13089.DOI:10.1007/s11042-018-6143-x.
[14] 康艳,蔡焕杰,宋松柏.水文系统复杂性模型研究及应用[J].水力发电学报,2013,32(1):5-10.
[15] 施珮,袁永明,张红燕,等.GRNN和Elman神经网络在水体溶解氧预测中的应用[J].江苏农业科学,2017,45(23):217-221.DOI:10.15889/j.issn.1002-1302.2017.23.061.
[16] 严丽,王启志.GA-Elman网络的网络控制系统预测[J].华侨大学学报(自然科学版),2014,35(6):620-624.DOI:10.11830/ISSN.1000-5013.2014.06.0620.
[17] 李志新,赖志琴,龙云墨.基于GA-Elman神经网络模型的年径流预测[J].水利水电技术,2018,49(8):71-77.DOI:10.13928/j.cnki.wrahe.2018.08.009.
[18] WANG Zhilong,WANG Chen,WU Jie.Wind energy potential assessment and forecasting research based on the data pre-processing technique and swarm intelligent optimization algorithms[J].Sustainability,2016,8(11):1191.DOI:10.3390/su8111191.
[19] NAWI N M,KHAN A,REHMAN M Z,et al.Weight optimization in recurrent neural networks with hybrid metaheuristic cuckoo search techniques for data classification[J].Mathematical Problems in Engineering,2014,2015(4):1-12.DOI:10.1155/2015/868375.
[20] 秦喜文,刘媛媛,王新民,等.基于整体经验模态分解和支持向量回归的北京市PM2.5预测[J].吉林大学学报(地球科学版),2016,46(2):563-568.DOI:10.13278/j.cnki.jjuese.201602206.

相似文献/References:

[1]汪帆.自然通风建筑室内热状况预测模型[J].华侨大学学报(自然科学版),1991,12(2):182.[doi:10.11830/ISSN.1000-5013.1991.02.0182]
　Wang Fan.An Indoor Thermal Characteristics Prediction Model for the Use of Naturally Ventilated Building[J].Journal of Huaqiao University(Natural Science),1991,12(5):182.[doi:10.11830/ISSN.1000-5013.1991.02.0182]
[2]卫海燕.深圳市境外游客市场的动态预测模型分析[J].华侨大学学报(自然科学版),1999,20(3):326.[doi:10.11830/ISSN.1000-5013.1999.03.0326]
　Wei Haiyan.A Dynamic Prediction Model for Analysing the Market of Overseas Tourists in Shenzhen City[J].Journal of Huaqiao University(Natural Science),1999,20(5):326.[doi:10.11830/ISSN.1000-5013.1999.03.0326]
[3]李浩,施养杭.混凝土碳化深度预测模型的比对与分析[J].华侨大学学报(自然科学版),2007,28(2):192.[doi:10.3969/j.issn.1000-5013.2007.02.021]
　LI Hao,SHI Yang-hang.Discussion of Concrete Carbonation Depth Predictive Models[J].Journal of Huaqiao University(Natural Science),2007,28(5):192.[doi:10.3969/j.issn.1000-5013.2007.02.021]
[4]施养杭,李浩.混凝土结构碳化寿命可靠度分析[J].华侨大学学报(自然科学版),2008,29(4):600.[doi:10.11830/ISSN.1000-5013.2008.04.0600]
　SHI Yang-hang,LI Hao.Reliability Analysis on Life of Carbonized Concrete Structure[J].Journal of Huaqiao University(Natural Science),2008,29(5):600.[doi:10.11830/ISSN.1000-5013.2008.04.0600]
[5]叶青.厦门市工程估价的RBF神经网络预测模型[J].华侨大学学报(自然科学版),2012,33(4):446.[doi:10.11830/ISSN.1000-5013.2012.04.0446]
　YE Qing.Prediction Model of the Project Cost Estimation Based on RBF Neural Network[J].Journal of Huaqiao University(Natural Science),2012,33(5):446.[doi:10.11830/ISSN.1000-5013.2012.04.0446]
[6]刘婧,叶青.采用BP和RBF神经网络的厦门市工程造价预测模型[J].华侨大学学报(自然科学版),2013,34(5):576.[doi:10.11830/ISSN.1000-5013.2013.05.0576]
　LIU Jing,YE Qing.Project Cost Prediction Model Based on BP and RBP Neural Networks in Xiamen City[J].Journal of Huaqiao University(Natural Science),2013,34(5):576.[doi:10.11830/ISSN.1000-5013.2013.05.0576]
[7]莫小琴,李钟慎.混沌时间序列的LSSVM预测方法[J].华侨大学学报(自然科学版),2015,36(预先出版):0.
　MO Xiao-qin,LI Zhong-shen.Prediction Method of the Chaotic Time Series Using Least Squares Support Vector Machine[J].Journal of Huaqiao University(Natural Science),2015,36(5):0.
[8]莫小琴,李钟慎.混沌时间序列的LSSVM预测方法[J].华侨大学学报(自然科学版),2014,35(4):373.[doi:10.11830/ISSN.1000-5013.2014.04.0373]
　MO Xiao-qin,LI Zhong-shen.Prediction Method of the Chaotic Time Series Using Least Squares Support Vector Machine[J].Journal of Huaqiao University(Natural Science),2014,35(5):373.[doi:10.11830/ISSN.1000-5013.2014.04.0373]
[9]冉茂宇.非出水时段电热水器加热时间与能耗的预测模型[J].华侨大学学报(自然科学版),2016,37(2):247.[doi:10.11830/ISSN.1000-5013.2016.02.0247]
　RAN Maoyu.Prediction Model of the Heating Time and Energy Consumption of Electric Water Heater During the Un-Draining Period[J].Journal of Huaqiao University(Natural Science),2016,37(5):247.[doi:10.11830/ISSN.1000-5013.2016.02.0247]
[10]冉茂宇.不同出水方式下电热水器出水时间与出水量的预测模型[J].华侨大学学报(自然科学版),2016,37(4):451.[doi:10.11830/ISSN.1000-5013.201604012]
　RAN Maoyu.Prediction Model of Water Draining Time and Volume for Electric Water Heater in Different Water Draining Modes[J].Journal of Huaqiao University(Natural Science),2016,37(5):451.[doi:10.11830/ISSN.1000-5013.201604012]

备注/Memo

备注/Memo:
收稿日期: 2020-01-20
通信作者: 卢毅敏(1973-),男,副研究员,博士,主要从事资源环境模型与系统模拟的研究.E-mail:luym@lreis.ac.cn.
基金项目: 国家重点研发计划项目(2017YFB0503500)http://www.hdxb.hqu.edu.cn
更新日期/Last Update: 2020-09-20