Application of Statistic Model and Backpropagation Neural Network to Analyzing and Forecasting Hydropower Dam Displacement

Horizontal displacement of Hoa Binh dam in operation phase is analyzed and then forecasted by using three methods: the multi-regression model (MTR), Seasonal Integrated Auto-regressive Moving Average (SARIMA) Back-propagation Neural Network (BPNN) model. The monitoring data Dam 137 periods, including horizontal displacement, time, reservoir water level air temperature, are used for experiments. results indicate that all these methods can describe real trend deformation achieve required accuracy short-term forecast up to 9 months. In addition, BPNN have highest stability accuracy.