Page 38 - 2022年第53卷第4期

［ 25］ 雷华阳，张雅杰，冯双喜，等 . 循环荷载作用下软黏土累积塑性应变与微观参数灰色关联分析［J］. 天津大
学学报（自然科学与工程技术版），2021，54（3）：245-254 .
［ 26］ 秦继辉，吴云星，谷艳昌 . 基于逐步回归和小波神经网络的土石坝渗压预测模型研究［J］. 安全与环境学
报，2018，18（5）：1670-1674 .
［ 27］ HOCHREITER S，SCHMIDHUBER J . Long short-term memory［J］ . Neural Computation，1997，9（8）：
1735-1780 .
［ 28］ MIRJALILI S . The ant lion optimizer［J］. Advances in Engineering Software，2015，83：80-98 .
［ 29］ BAHDANAU D，CHO K，BENGIO Y . Neural machine translation by jointly learning to align and translate［J］.
DOI：10.48550/arXiv1409 . 0473 .
［ 30］ CHEN X，ZHAO H D，YANG D X，et al . SA-SinGAN：self-attention for single-image generation adversarial
networks［J］. Machine Vision and Applications，2021，32（4）：104 .
［ 31］ 李明超，田丹，沈扬，等 . 融入 Attention 机制改进 Word2vec 技术的水利水电工程专业词智能提取与分析方
法［J］. 水利学报，2020，51（7）：816-826 .
［ 32］ QIU J Y，WANG B，ZHOU C J . Forecasting stock prices with long-short term memory neural network based on
attention mechanism［J］. PloS One，2020，15（1）：e0227222 .
［ 33］ 庞琼，王士军，谷艳昌，等 . 基于滞后效应函数的土石坝渗流水位模型应用［J］. 水土保持学报，2016，30
（2）：225-229 .
［ 34］ 虞鸿，包腾飞，薜凌峰 . 降雨滞后效应的数值模拟［J］. 水力发电学报，2010，29（4）：200-206 .
［ 35］ WEI B W，GU M H，LI H K，et al . Modeling method for predicting seepage of RCC dams considering time-vary⁃
ing and lag effect［J］. Structural Control and Health Monitoring，2018，25（2）：e2081 .

Coupled ALO-LSTM and feature attention mechanism prediction model
for seepage pressure of earth-rock dam

1 1 2 1 2 1
WANG Xiaoling ，LI Ke ，ZHANG Zongliang ，YU Hongling ，KONG Lingxue ，CHEN Wenlong
（1. State Key Laboratory of Hydraulic Engineering Simulation and Safety，Tianjin University，Tianjin 300072，China；
2. Kunming Engineering Corporation Limited，Kunming 650051，China）

Abstract： The existing prediction model of seepage pressure of earth-rock dam lacks quantitative analysis
of the influence degree of each influencing factor in seepage effect quantity，which makes it difficult to ex⁃
plore the internal influencing mechanism of seepage effect quantity change . In view of the above prob⁃
lems， this paper proposes a prediction model of seepage pressure of earth-rock dam by coupling
ALO-LSTM and feature attention mechanism from the perspectives of time dimension and characteristic di⁃
mension. The model firstly adopts principal component analysis to reduce dimension of each influencing fac⁃
tor. Then， a long short-term memory network based on ant lion optimization algorithm is proposed to opti⁃
mize the number of neurons in long short-term memory network by using random walk in ant lion optimiza⁃
tion and roulette to capture the deep information of osmotic pressure data in time dimension. Furthermore，
the feature attention mechanism is introduced in the feature dimension to calculate the contribution rate of
each influencing factor to the osmotic effect volume， so as to find out the internal reasons for the change
of the seepage effect volume adaptively. The case analysis shows that the proposed model has high accura⁃
cy，and its MAPE，RMSE and MAE on test samples are 0.28%，0.022m and 0.17m，respectively. In addi⁃
tion， the contribution rate of water level component to osmotic effect is 47.9% ， followed by precipitation
temperature and aging component，which are 33.5%，9.8% and 8.8%，respectively.
Keywords：seepage pressure prediction；long short-term memory；feature attention mechanism；ant lion op⁃
timization；principal component analysis

（责任编辑：李福田）

— 412 —