Seepage real-time forecast model based on genetic neural network

In terms of main influencing factors of seepage, a seepage real-time forecast model is established based on genetic algorithm and neural network. The model can be trained sequentially with new observed data in further application; and the accuracy of the model can be improved in less training time with the accumulation of samples. Thus, it can satisfy the demand of real-time forecast. The predicted results agree well with the measured ones in the forecast of transverse uplift pressure of Fengman Dam so as to indicate that the proposed method has high prediction accuracy and is valid and practical for seepage real-time forecast.