基于多层次滤波降噪的IGA-NARX混凝土坝变形预测模型
IGA-NARX Dam Deformation Prediction Model Based on Multi-level Filtering Noise Reduction
杨孟 1李永福 2梁云 3陈艺征 3顾冲时1
作者信息
- 1. 河海大学水利水电学院, 江苏 南京 210098
- 2. 国网重庆市电力公司电力科学研究院,重庆 401123
- 3. 国网智能电网研究院有限公司, 北京 102209
- 折叠
摘要
针对混凝土坝变形数据中存在非高斯分布噪声污染,难以描述混凝土坝变形数据自身的趋势性、季节性的问题,采用CEEMD与粒子滤波法相结合的方法对锦屏一级大坝径向位移进行分析.先将CEEMD分解后的高频和低频分量进行区分,仅对高频分量进行粒子滤波降噪,再进行分量重构;通过多层次滤波降噪处理的位移数据驱动 IGA-NARX神经网络构建预测模型,并使用RRMSE、MMSE 等指标进行评价.工程实例验证表明,所提模型相较于对比模型在评价指标上均有一定提升,具有较好的实用价值.
Abstract
In view of the non-Gaussian noise pollution in the deformation data of concrete dam,it is difficult to de-scribe the trend and seasonality of the deformation data of concrete dam.Combination of CEEMD and particle filter meth-od is proposed to analyze the dam radial displacement of Jingpin Level I Hydropower Station.Firstly,the high frequency component and the low frequency component after CEEMD decomposition are distinguished,and only the high frequency component is denoised by particle filter.And then the component is reconstructed.The IGA-NARX neural network is driven by the displacement data of multi-level filtering and noise reduction,and the prediction model is constructed.The indexes of RRMSE and MMSE is used to evaluate the effectiveness of the model.It is verified by engineering examples.Com-pared with the comparison model,the proposed model has certain improvement in several evaluation indexes and has good practical value.
关键词
CEEMD分解/混凝土坝变形监测/粒子滤波降噪/NARX神经网络/IGA算法Key words
CEEMD decomposition/concrete dam deformation monitoring/particle filtering for noise reduction/NARX neural network/improved genetic algorithm引用本文复制引用
基金项目
国家电网总部科技项目(5108-202218280A-2-417-XG)
出版年
2024
NETL
NSTL
维普
万方数据