Dam deformation is a result of the combined action of multiple loads at the same time. Itis a key technology for prediction and diagnosis of deformation by exploring the potential laws anddevelopment trends of displacement monitoring data. However, the existing normal analysis methodssuch as GNSS+ prism, and automatic monitoring system have large non-linear error. In order torealize the smooth fitting process of non-linear and non-stationary dam deformation data, the BPneural network model for dam deformation prediction is constructed based on the correlationfunction of dam deformation and displacement. Mainly based on the characteristics of waterpressure, temperature, and time-depended factors, the BP prediction model can obtain verticaldisplacement prediction data which can truly show the deformation law and trend of dam body throughself-adaptive learning and training of measured data. The model proposed would provide detailedand accurate data and technical support for safety prediction and analysis of dam deformation.