Academic Journal of Architecture and Geotechnical Engineering, 2021, 3(1); doi: 10.25236/AJAGE.2021.030103.
Yuhao Liu, Xiao Feng
School of Civil Engineering, Chongqing Jiaotong University, Chongqing, China
Aiming at the characteristics of dam safety monitoring data sequence with few samples, short sequence and nonlinearity, a dam horizontal displacement prediction method based on attention mechanism, convolutional neural network (CNN) and long short-term memory (LSTM) is proposed. This method can reduce the loss of historical information and improve the prediction accuracy. First, the missing values are supplemented by linear interpolation to improve the integrity of the data. Then the abstract feature data extracted by CNN is mapped to the predicted value of LSTM, and then optimized through attention mechanism. Finally, the model is trained and verified with the monitoring data of a concrete gravity dam in Chongqing as a sample. Experimental results show that the root mean square error (RMSE), mean absolute percentage error (MAPE) and fit (R2) of the CNN-LSTM hybrid model based on attention mechanism are 0.3882, 0.7121% and 0.9543, respectively. The prediction accuracy of the new model is better than the CNN-LSTM model and the LSTM neural network model.
Horizontal displacement prediction of dam, CNN-LSTM, Attention mechanism, Linear interpolation method
Yuhao Liu, Xiao Feng. Prediction of dam horizontal displacement based on CNN-LSTM and attention mechanism. Academic Journal of Architecture and Geotechnical Engineering (2021) Vol. 3, Issue 1: 14-19. https://doi.org/10.25236/AJAGE.2021.030103.
[1] M.L. Du, J.Y. Gao and L.B. Zhang (2020). Time-series prediction and completion of dam monitoring data. Hydroelectric Power, vol.46, no.11, p.111-115.
[2] F.L. Li (2020). Analysis and prediction of dam safety monitoring data of Baishi reservoir. Heilongjiang Water Conservancy Technology, vol.48, no.8, p.52-56.
[3] Y.H. Wang and H.Z. Su (2020). Dam deformation prediction based on PCA-GWO-SVM. The People of The Yellow River, vol.42, no.11, p.111-115.
[4] M.J. Li, J.X. Wang and J.Y. Pan (2021). Dam deformation prediction based on improved GWO and SVM. Hydroelectric Power, vol.47, no.3, p.89-93.
[5] X.K. Zhou, Y.Y. Hu and W Liang (2021). Variational LSTM Enhanced Anomaly Detection for Industrial Big Data. IEEE Transactions on Industrial Informatics, vol.17, no.5, p.3469-3477.
[6] L. Ren, J.B, Dong and X.K. Wang (2021). A Data-Driven Auto-CNN-LSTM Prediction Model for Lithium-Ion Battery Remaining Useful Life. IEEE Transactions on Industrial Informatics, vol.17, no.5, p.3478-3487.
[7] B.C. Li, H.J. Yu and J.Y. Liu (2021). Short-term PV power generation prediction based on Kmeans and CEEMD-PE-LSTM. Hydroelectric Energy Science, vol.39, no.4, p.204-208.
[8] H.C. Shin, H.R. Roth and M.C. Gao (2016). Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning. IEEE Transactions on Medical Imaging, vol.35, no.5, p. 1285-1298.
[9] L. Zheng, Y. Yang and Q. Tian (2018). SIFT Meets CNN: A Decade Survey of Instance Retrieval. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.40, no.5, p.1224-1244.
[10] Y.B. Shen, X.L. Zhang and Y. Xia (2021). BI-LSTM neural network for residual service life prediction of bearings. Journal of Vibration Engineering, vol.34, no.2, p. 411-420.
[11] X. Liang and Z.H. Zhang (2021). Dynamic fluid level depth of oil well based on short-term energy and LSTM. Computers and Modernization, vol.32, no.4, p.15-19+26.
[12] Z. Zhao, W.H. Chen and X.M. Wu (2017). LSTM network: a deep learning approach for short-term traffic forecast. IET Intelligent Transport Systems, vol.11, no.2, p.68-75.
[13] X.Y. Guo, J.H. Lian and H.M. Li (2021). Prediction algorithm of ammonia concentration in chicken house based on two-stage attention mechanism and LSTM. Journal of China Agricultural University, vol.26, no.6, p.187-195.
[14] G.J. Liu and X.B. Wang (2020). Text classification of marketing news based on CNN+LSTM attention. Computer Technology and Development, vol.30, no.11, p.59-63.
[15] X.M. Liu, D.B. Zhao and R.Q. Xiong (2011). Image Interpolation Via Regularized Local Linear Regression. IEEE Transactions on Image Processing, vol.20, no.12, p.3455-3469.
[16] M.D. Zhen, B.L. Zhang and V.D. Radulescu (2021). Normalized solutions for nonlinear coupled fractional systems: low and high perturbations in the attractive case. Discrete and Continuous Dynamical Systems, vol.41, no.6, p.2653-2676.