English
引用本文:李析男,王 宁,梅亚东,等.NAR神经网络的应用与检验 ——以城市居民生活需水定额为例[J].灌溉排水学报,2017,36(11):122-128.
LI Xi’nan,WANG Ning,MEI Yadong,et al.NAR神经网络的应用与检验 ——以城市居民生活需水定额为例[J].灌溉排水学报,2017,36(11):122-128.
【打印本页】   【下载PDF全文】   查看/发表评论  【EndNote】   【RefMan】   【BibTex】
←前一篇|后一篇→ 过刊浏览    高级检索
本文已被:浏览 5391次   下载 8420 本文二维码信息
码上扫一扫!
分享到: 微信 更多
NAR神经网络的应用与检验 ——以城市居民生活需水定额为例
李析男, 王 宁, 梅亚东, 赵先进
贵州省水利水电勘测设计研究院, 贵阳 550002;贵州省喀斯特地区水资源开发利用工程技术研究中心, 贵阳 550002; 武汉大学 水资源与水电工程科学国家重点实验室, 武汉430072
摘要:
NAR神经网络具有反馈和记忆功能,其在时间序列的建模仿真方面具有显著优点。以城市居民生活需水定额为例,采用NAR神经网络建立了贵州省城市居民生活需水定额的时间序列模型,通过试验法、留一法交叉检验讨论了模型相关输入参数的计算与选取,通过相关系数、Nash效率系数、LBQ检验、ROC曲线方法检验了模型的性能和预测结果的精度,进而对贵州省城市居民生活需水定额变化趋势进行了预测。结果表明,①NAR模型性能良好并具有较高的预测精度,NAR神经网络的相关系数r、Nash效率系数分别达到0.97、0.87,LBQ检验得出预测结果误差不存在自相关性,采用预测结果绘制ROC曲线,其AUC值达到0.938(处于水平1,有较高准确性);②需水定额合理性评价中,预测2020年、2030年需水定额分别为137.72 L/(人·d)、132.94 L/(人·d),满足《室外给水设计规范》(GB50013—2006)的要求,具有较好的适用性。
关键词:  NAR神经网络模型; 留一法交叉验证; Ljung-Box Q检验; ROC曲线; 定额预测
DOI:10.13522/j.cnki.ggps.2017.11.020
分类号:
基金项目:
Application and Validation of Nonlinear Auto-regressive Neural Network Model: Taking Water Supply to Residential Area as an Example
LI Xi’nan, WANG Ning, MEI Yadong, ZHAO Xianjin
Guizhou Water Conservancy and Hydroelectric Power Investigation, Design and Research Institute, Guiyang 550002, China; Reserch Center on Water Resources Exploitation in the Karst of Guizhou, Guiyang 550002, China; State Key Laboratory of Water Resources and Hydropower Engineering Science, Wuhan 430072, China
Abstract:
Nonlinear auto regressive (NAR) neural network with feedback and memory has many advantages in analysis of time series. Taking water supply to urban residential areas as an example, we proposed a NAR neural network model in this paper to analyze the domestic demand of Guizhou Province for water. The performance of the model was validated and the temporal variation in water requirement was then calculated. The predicted results are summarized as follows. ①The NAR neural network model was efficient and accurate, and the correlation coefficient and Nash coefficient of efficiency predicted by the model were 0.97 and 0.87 respectively. The results from the LBQ test showed that there was no autocorrelation among the predicted results. The AUC in the ROC curves of the predicted results was 0.938 (i.e., in the first level, and a higher accuracy). ② In the calculated rational water requirement, the predicted average water requirement per person in 2020 and 2030 was 137.72 liter per day and 132.94 liter per day respectively, meeting the requirements set in the design code of GB50013-2006. In summary, the NAR network is suitable for predicting the time series of water requirement and provides a reference for analyzing future demand for water.
Key words:  NAR Neural Network; leave one out cross validation; Ljung-Box Q test; ROC curve; quota forecast