Dam safety monitoring model based on ARIMA-ANN
Huaizhi Su · Engineering Journal of Wuhan University · 2010
Affected by various complicated factors,dam deformation monitoring data is a nonstationary time series.Based on the traditional time-series we can not solve the nonstationary data.Autoregressive integrated moving average(ARIMA)model is used to fit and forecast data.The BP neural network is used to predict error.The dam deformation data fitting analysis and forecasting research show that the ARIMAANN model is not only quickly enough to improve the efficiency of the algorithm,but also has a good effect in fitting with monitoring data,so as to improve forecast accuracy a lot.