The transversely isotropic (TISO) constitutive and frost heave models for the freezing of fine-grained soils are more accurate than the isotropic model and simpler than the orthotropic models. First, in combination with the mesoscopic composition of freezing soils, a mechanical model for the interaction between the equivalent ice lens and the soil in frozen soils is established based on the series and parallel models in the theory of composite mechanics. Second, the TISO constitutive model together with the analytic expression of five elastic constants is provided for analysis of the freezing soils. Third, a preliminary elastoplastic model for TISO freezing soil is established based on the Hill plastic model. Fourth, the heat–moisture–deformation coupling TISO model and the hydrodynamic frost heave model are derived according to a thermodynamics equation, a soil water motion equation, and generalized Hooke’s law. Synchronization and uniformity of the TISO constitutive model and the TISO frost heave model are realized for analyzing the interaction between permafrost soils and buildings. Finally, an indoor standard frost heave test and the frost heave of a prototype canal are simulated based on the above models. The numerical results indicated that the models presented in this paper accurately described the frost heave and revealed the interaction between permafrost and buildings.
23 April 2020 in Archives of Computational Methods in Engineering
The accurate prediction of wastewater quality parameters is pivotal for evaluating the treatment stability of processes and for ensuring regulatory compliance in wastewater treatment plants. A singular machine learning model often faces challenges in fully capturing and extracting the complex nonlinear relationships inherent in multivariate time series data. To overcome this limitation, this study proposes a dual hybrid modeling framework that effectively integrates LSTM and XGBoost models, leveraging their complementary strengths. The first hybrid model refines the residues to utilize the information, whereas the second hybrid model enhances the input features by extracting temporal dependencies. A comparative analysis against three standalone models reveals that the proposed hybrid framework consistently outperforms them in both predictive accuracy and generalization ability across four key effluent indicators—chemical oxygen demand, ammonia nitrogen, total nitrogen, and total phosphorus. These results demonstrate that the proposed hybrid machine learning framework has great potential to be used to evaluate process stability in wastewater treatment plants, paving a way for smarter, more resilient, and more sustainable wastewater management, which will improve ecological integrity and regulatory compliance.
12 December 2019 in Environmental Science and Pollution Research