Seepage prediction model of the earth-rock dam based on TCN considering rainfall lag effect

Abstract

Abstract Renewable energy has the highest conversion efficiency, is the most flexible in regulating peak power in the grid, and has the potential to significantly reduce emissions. Hydropower is one of the main ways to optimize power energy structure by building earth-rock dams that block water and generate electricity. Seepage is a physical quantity that characterizes the safety of earth-rock dams. Studying the intelligent prediction model of earth-rock dams is an effective means of understanding the evolution of seepage behavior, and it is also crucial for the safe operation and energy efficiency of earth-rock dams. To create a rainfall factor expression reflecting the hysteresis effect of rain, actual monitoring data of different piezoelectric tubes on the upstream and downstream sides of the soil core wall of an earth-rock dam is considered. Based on the key influencing factors of the seepage behavior of earth-rock dams, the novel temporal convolutional network (TCN) algorithm in deep learning is introduced into the seepage behavior prediction of earth-rock dams, constructing the intelligent prediction model of seepage of earth-rock dams based on TCN. The engineering example shows that the seepage prediction model of the earth-rock dam based on TCN has better prediction performance than the seepage prediction model of the earth-rock dam based on support vector regression (SVR), extreme learning machine, and long-short term memory. The determination coefficient is more significant than 0.9, and the relative error of prediction is less than 1‰. The model’s prediction accuracy is high, and the stability of the prediction performance is good. The model’s prediction performance also improves after considering the rainfall lag effect.