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

Abstract

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.

PFVAE: A Planar Flow-Based Variational Auto-Encoder Prediction Model for Time Series Data

“…Xue-Bo Jin et al [46] proposed a deep hybrid model with a serial two-layer decomposition structure to predict the future power load. Agga, Ali, et al [47] proposed two models, CNN-LSTM and ConvLSTM, to predict the power generation of photovoltaic power plants in four different time ranges from 1 day to 7 days; Luo, Xianglong, et al [48] proposed a structural deformation prediction model based on the time convolutional network (TCN), which uses one-dimensional expansion causal convolution to reduce model parameters and obtain long-term memory of time series. Although deep learning methods have strong learning capabilities, the prediction performance is not high enough since a large amount of data causes the learning efficiency of neural networks to be low.…”

“…(1) VAE with LSTM is designed as a time series data predictor to learn the long-and short-term dependencies of time series data. Compared with the prediction networks [34][35][36][37][38][39][40]48,53], the proposed VAE model can effectively learn the relation and extract representative information of time series and improve the computational efficiency of the model. Moreover, it has sufficient robustness to noise and prevents overfitting.…”

“…In the experiment, we compared the prediction performance with the other seven models, LSTM [34], GRU [35], BiLSTM [36], BiGRU [37], TCN [48], CNN-LSTM [38],…”

A Variational Bayesian Deep Network with Data Self-Screening Layer for Massive Time-Series Data Forecasting

“…In this section, we want to compare the performance of the VBGRU model with models such as LSTM [12], GRU [13], CNN-LSTM [14], ConvLSTM [15], and TCN [49] in predicting the hourly PM2.5 concentration in the next 24 h. To better compare the prediction performance of each model, we consider the use of cross-validation methods for performance validation. The commonly used cross-validation methods in machine learning are Monte Carlo simulation [50] and K-fold cross-validation [51].…”

FenceNet: Fine-grained Footwork Recognition in Fencing

“…In the case that the input channel size could differ from the output channel size of the second convolutional layer, a 1×1 convolution is added to account for this discrepancy. Our structure is based on those used in [2,25] but with increasing hidden size and decreasing kernel size as the number of layers increase. The increasing dilation factors are also adjusted to accommodate for the limited input length while maintaining full history coverage.…”