摘要
堆石坝变形监测数据是一种时间序列数据,可以用时序预测模型挖掘其规律并进行预测。本文利用时序预测模型提出一种堆石坝变形预测方法,该方法首先采用时间序列分解(seasonal-trend decomposition procedure based on loess,STL)将堆石坝变形监测数据分解为趋势项、周期项和不规则波动三部分,再使用经验模态分解(empirical mode decomposition,EMD)对不规则波动平稳化处理,最后利用长短期记忆网络(long short-term memory,LSTM)预测分解后的序列,并利用贝叶斯优化方法进行超参数优化。为评估该方法的预测效果,以水布垭面板堆石坝为例,通过控制训练时长、预测时长、离群值数目等变量进行多组仿真实验,并与其他时序预测模型对比。结果表明该方法预测精度较高,适用性较广,对于堆石坝的性状评估具有一定的应用价值。
Deformation monitoring data of a rockfill dam are a time series that can be mined using a time series prediction model for analysis of its variation trend.This paper presents a new method for rockfill dam deformation prediction.First,we use a seasonal-trend decomposition procedure based on loess(STL)to decompose the deformation monitoring data of a rockfill dam into three parts:secular trend,seasonal variation,and irregular variation.Then,an empirical mode decomposition(EMD)method is used to stabilize the irregular variation.Finally,we adopt a long short-term memory(LSTM)technique to predict the decomposed sequences and a Bayesian optimization method to optimize the parameters.To evaluate the accuracy of this method,we numerically simulate the Shuibuya concrete faced rockfill dam for different training time,prediction time,and numbers of outliers;and compare it with other time series prediction models.The results show our new method is more accurate and applicable to evaluating rockfill dam performance.
作者
冷天培
马刚
向正林
梅江洲
关少恒
周伟
高宇
LENG Tianpei;MA Gang;XIANG Zhenglin;MEI Jiangzhou;GUAN Shaoheng;ZHOU Wei;GAO Yu(State Key Laboratory of Water Resources and Hydropower Engineering,Wuhan University,Wuhan 430072;Power Generation Company Limited of China Southern Power Grid,Guangzhou 510630;Datang Xuanwei Hydropower Development Co.,Ltd,Xuanwei,Yunnan 655400)
出处
《水力发电学报》
CSCD
北大核心
2021年第10期147-159,共13页
Journal of Hydroelectric Engineering
基金
国家自然科学基金(52179141,U1865204)
华能集团科技项目(HNKJ18-H26)。
关键词
堆石坝
变形预测
时间序列分解
经验模态分解
LSTM
贝叶斯优化
rockfill dam
deformation prediction
time series decomposition
empirical mode decomposition
LSTM
Bayesian optimization
