A physics knowledge-based surrogate model framework for predicting multiple time-dependent responses of surrounding rock induced by tunnel excavation

Nov 2026

Hybrid PINN–GPR Method for Probabilistic Prediction of Concrete Creep Behavior

A novel hybrid method integrating physics-informed neural network (PINN) and Gaussian process regression (GPR) that enforces the B4 creep model as a physics-informed constraint by embedding its governing equations into the loss function, effectively incorporating physical knowledge into data-driven training.

Zhiren Tao, Jian-Xin Peng, Shijie Liao et al. · Journal of materials in civi... · 0 citations

Sep 2026

Transformer-Based Surrogate Model for Prediction of Hydraulic Fracture Geometry

We developed a computationally efficient and accurate surrogate model to assess key descriptors of fracture geometry during reservoir stimulation associated with unconventional subsurface energy scenarios. The work is motivated by the observation that accurate quantification of fracture length, width, and height is k...

Lu-Yao Wang, Qin-Zhuo Liao, Jin-Liang Xie et al. · SPE Journal · 0 citations

Nov 2026

A Physics-Data Hybrid Model for Predicting Earth Pressure Evolution in Buried Horizontal Cylindrical Tanks

Buried horizontal cylindrical tanks are susceptible to stress instabilities, such as shell buckling and weld fatigue, under nonuniform ground settlement. Classical Terzaghi-based earth pressure theories simplify key parameters into static constants, rendering them inadequate for capturing the dynamic soil-tank inte...

Quanen Li, Yu Zhang, Sheng-Jie Di et al. · Journal of computing in civi... · 0 citations

Conference Aug 2026

Historical-Boundary-Condition-Based POD-MLP Surrogate Modeling for Transient Thermal-Hydraulic Prediction in Rod-Bundle Channels

Fast and accurate prediction of transient thermalhydraulic parameters is essential for reliability assessment and safety-margin evaluation in safety-critical nuclear reactor components. However, high-fidelity computational-fluiddynamics simulations are computationally prohibitive for the many-query scenarios required b...

Yu-Zhao Ye, Xiao-Meng Dong, An-Qi Xu et al. · 2026 8th International Confe... · 0 citations

Open access Sep 2026

Time‐Dependent Settlement Model for Driven Piles Using Hybrid Finite Element‐Artificial Neural Network and Regression Approaches

The prediction of time‐dependent pile settlement remains challenging due to the nonlinear behavior of saturated clay soils, consolidation, and pile setup effects. The complexity of this phenomenon is not fully captured by classical elasticity theories. This study develops a hybrid model for time‐dependent pile settleme...

Gbênihon Céleste-Amour Kenoukon, Joseph Ng'ang'a Thuo, Kiplagat Chelelgo et al. · Engineering Reports · 0 citations

Open access Sep 2026

Simulation of crest crack in high earth-core rockfill dam using XFEM 2-D modeling

Crest cracking represents a pervasive structural hazard during the construction and operational phases of high earth-core rockfill dams (ECRDs); consequently, the development of history-matched numerical tools is rendered an engineering necessity to prevent catastrophic risks. To address the limitations inherent in tra...

Serges Mendomo Meye, Paul F. Nguema · Journal of engineering and a... · 0 citations