Temperature Prediction of Seasonal Frozen Subgrades Based on CEEMDAN-LSTM Hybrid Model.

Improving the temperature prediction accuracy for subgrades in seasonally frozen regions will greatly help improve the understanding of subgrades' thermal states. Due to the nonlinearity and non-stationarity of the temperature time series of subgrades, it is difficult for a single general neural network to accurately capture these two characteristics. Many hybrid models have been proposed to more accurately forecast the temperature time series. Among these hybrid models, the CEEMDAN-LSTM model is promising, thanks to the advantages of the long short-term memory (LSTM) artificial neural network, which is good at handling complex time series data, and its combination with the broad applicability of the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) in the field of signal decomposition. In this study, by performing empirical mode decomposition (EMD), ensemble empirical mode decomposition (EEMD), and CEEMDAN on temperature time series, respectively, a hybrid dataset is formed with the corresponding time series of volumetric water content and frost heave, and finally, the CEEMDAN-LSTM model is created for prediction purposes. The results of the performance comparisons between multiple models show that the CEEMDAN-LSTM model has the best prediction performance compared to other decomposed LSTM models because the composition of the hybrid dataset improves predictive ability, and thus, it can better handle the nonlinearity and non-stationarity of the temperature time series data.

A Freezing-Thawing Damage Characterization Method for Highway Subgrade in Seasonally Frozen Regions Based on Thermal-Hydraulic-Mechanical Coupling Model.

Seasonally frozen soil where uneven freeze-thaw damage is a major cause of highway deterioration has attracted increased attention in China with the rapid development of infrastructure projects. Based on Darcy's law of unsaturated soil seepage and heat conduction, the thermal-hydraulic-mechanical (THM) coupling model is established considering a variety of effects (i.e., ice-water phase transition, convective heat transfer, and ice blocking effect), and then the numerical solution of thermal-hydraulic fields of subgrade can be obtained. Then, a new concept, namely degree of freeze-thaw damage, is proposed by using the standard deviation of the ice content of subgrade during the annual freeze-thaw cycle. To analyze the freeze-thaw characteristics of highway subgrade, the model is applied in the monitored section of the Golmud to Nagqu portion of China National Highway G109. The results show that: (1) The hydrothermal field of subgrade has an obvious sunny-shady slopes effect, and its transverse distribution is not symmetrical; (2) the freeze-thaw damage area of subgrade obviously decreased under the insulation board measure; (3) under the combined anti-frost measures, the maximum frost heave amount of subgrade is significantly reduced. This study will provide references for the design of highway subgrades in seasonally frozen soil areas.