摘要
为提高浸润线的预测精度,减少尾矿库安全预警的误报和漏报,采用小波多尺度分析方法对浸润线监测数据序列进行预处理,并利用Matlab程序实现.以MAE,MSE,MAPE,MSPE作为预测精度的评价指标,对两个工程实例进行研究.结果表明:多尺度小波分析预测模型的MAE,MSE,MAPE,MSPE值较其他模型低.因此,通过多尺度小波分析处理,能够较大地提高预测模型的预测精度.
In order to improve the prediction precision and the false positives and fail to declare of the tailing dam safety warning,the data is preprocessed by wavelet multi-resolution analysis method,and used Matlab program to achieve the calculation. This paper gives two engineering examples and takes the MAE,MSE,MAPE and MSPE as the evaluation index of the prediction accuracy. The results showed that: the MAE,MSE,MAPE and MSPE of the wavelet multi-resolution analysis model were lower than the other's. So it can significantly improve the prediction accuracy of forecasting model by wavelet multi-resolution analysis.
作者
邱坤南
沈斐敏
QIU Kunnan SHEN Feimin(College of Civil Engineering, Fuzhou University, Fuzhou, Fujian 350116, China)
出处
《福州大学学报(自然科学版)》
CAS
北大核心
2016年第5期746-752,共7页
Journal of Fuzhou University(Natural Science Edition)
基金
国家安全监管总局科技基金资助项目(ZY2013-6)
福建省自然科学基金资助项目(2011J01297)
关键词
浸润线
小波多尺度分析
非平稳时间序列
尾矿库
预测
infiltration route
wavelet multi-resolution-analysis
non-stationary time series
tailing dam
prediction