相空间神经网络模型在大坝安全监控中的应用

Neural network of phase space and its application in dam safety monitoring

本文将混沌理论和神经网络理论相结合 ,并针对某一混凝土重力坝水平位移实测值建立相空间模糊神经网络预报模型 .首先对水平位移的实测序列 ,进行相空间重构 ,求算关联维 ,说明该序列存在混沌成分和奇异吸引子 ;应用自适应模糊神经网络 ,对水平位移实测序列构成的相点 ,建立相空间神经网络模型 .计算结果表明 ,相空间神经网络模型用于大坝监控中是可行的 ,其预报精度优于常规的统计回归模型 ,能揭示大坝的非线性性质 ,能更好地对大坝运行性态进行分析 .

Combining the chaos theory with neural network theory,a fuzzy network model of phase space for analyzing the observation data of dam monitoring is established.The analysis on the horizontal displacements of a gravity dam is given as an example for the application of the model.First,after reconstruction of phase space of measured time series,the correlation dimension is derived,which shows the chaos effect lies in the time series of the horizontal displacement.According to the phase point of measured time series,fuzzy neural network model of phase space is built.The result shows that the prediction according to this model is more precise than that of regression model.