A Deep Learning Prediction Model for Structural Deformation Based on Temporal Convolutional Networks

• Published in: Computational intelligence and neuroscience Vol. 2021; no. 1; p. 8829639
• Main Authors: Luo, Xianglong, Gan, Wenjuan, Wang, Lixin, Chen, Yonghong, Ma, Enlin
• Format: Journal Article
• Language: English
• Published: United States Hindawi 2021; John Wiley & Sons, Inc
• Subjects: Accuracy; Algorithms; Construction; Convolution; Deep learning; Deformation; Deformation effects; Fuzzy logic; Long term memory; Markov analysis; Mathematical models; Methods; Monitoring; Monitoring systems; Neural networks; Optimization; Parameters; Prediction models; Principal components analysis; Receptive field; Regression analysis; Statistical analysis; Structural engineering; System theory; Time series
• ISSN: 1687-5265; 1687-5273; 1687-5273
• DOI: 10.1155/2021/8829639

The structural engineering is subject to various subjective and objective factors, the deformation is usually inevitable, the deformation monitoring data usually are nonstationary and nonlinear, and the deformation prediction is a difficult problem in the field of structural monitoring. Aiming at the problems of the traditional structural deformation prediction methods, a structural deformation prediction model is proposed based on temporal convolutional networks (TCNs) in this study. The proposed model uses a one-dimensional dilated causal convolution to reduce the model parameters, expand the receptive field, and prevent future information leakage. By obtaining the long-term memory of time series, the internal time characteristics of structural deformation data can be effectively mined. The network hyperparameters of the TCN model are optimized by the orthogonal experiment, which determines the optimal combination of model parameters. The experimental results show that the predicted values of the proposed model are highly consistent with the actual monitored values. The average RMSE, MAPE, and MAE with the optimized model parameters reduce 44.15%, 82.03%, and 66.48%, respectively, and the average running time is reduced by 45.41% compared with the results without optimization parameters. The average RMSE, MAE, and MAPE reduce by 26.88%, 62.16%, and 40.83%, respectively, compared with WNN, DBN-SVR, GRU, and LSTM models.