江淮水利科技2026，Vol.21Issue(4)：9-12,4.DOI:10.20011/j.cnki.JHWR.202604002
基于改进分批估计算法的水闸安全监测数据处理方法
A safety monitoring data processing method for sluices based on an improved batch estimation algorithm
摘要
Abstract
To address the challenges in sluice safety monitoring,where multi-sensor data from the same type of monitoring item are susceptible to environmental disturbances,equipment failures,and variations in instrument accuracy,resulting in insufficient data accuracy,poor stability,frequent outliers,and difficulties in achieving reliable data fusion,this paper proposes a sluice safety monitoring data processing method based on an improved batch estimation algorithm.Firstly,gross errors are eliminated through data preprocessing.Then,batch estimation is carried out by grouping according to the characteristics of monitoring areas.Finally,adaptive weights are calculated in real time based on the variance of each group to realize the optimal fusion of multi-sensor data.Field monitoring data collected from a sluice in a plain area were used to validate the proposed method,and its performance was compared with those of the conventional averaging method and the traditional batch estimation algorithm.The results showed that the time-varying variance of the proposed method was significantly reduced compared with traditional methods.In the scenario with outliers,the global variance decreased from 3.719 to 0.129,and the root mean square error declined from 0.762 to 0.481,with simultaneous improvement in accuracy and stability.Extreme outliers caused by equipment faults were effectively suppressed.The research indicates that this method can effectively improve the accuracy and stability of data processing,and provide reliable data support for the safety state evaluation of sluices.关键词
水闸安全监测/数据处理/分批估计/异常值/加权Key words
sluice safety monitoring/data processing/batch estimation/outliers/weighting分类
建筑与水利引用本文复制引用
孙小冉,宋才仁旦,彭建和..基于改进分批估计算法的水闸安全监测数据处理方法[J].江淮水利科技,2026,21(4):9-12,4.基金项目
安徽省自然科学基金资助项目(2208085US17) （2208085US17）
