Yingang Wang

Machine learning (ML) models are increasingly applied in rock mechanics. However, purely data-driven approaches trained on limited experimental data can often exhibit physically unrealistic results, such as violating established physical laws, which undermines their reliability. To address this, we introduce a Physics-Informed Machine Learning (PIML) approach utilizing XGBoost to predict the stress wave transmission coefficient (T) across realistic rock joints. Our model was developed using a dataset from 279 Split Hopkinson Pressure Bar (SHPB) tests conducted on granite samples replicating 80 unique natural joint morphologies. We integrated known physical constraints directly into the modeling process: (1) boundedness of T within [0, 1] enforced through logit and sigmoid transformations, and (2) hard monotonicity constraints ensuring T consistently increases with joint matching coefficient (JMC) and decreases with aperture (e). To ensure the model generalizes to unseen joint morphologies, we employed a rigorous Nested Leave-One-Group-Out (LOGO) cross validation strategy. The con-strained XGBoost model achieved R2 of 0.761 and demonstrated a statistically significant 20.55% reduction in Mean Absolute Error (MAE) compared to a Ridge Regression baseline. Post-hoc analyses using Partial Dependence and Individual Conditional Expectation plots confirmed that the model’s predictions are not only accurate but also physically realistic and interpretable. This PIML approach successfully guarantees physically consistent predictions and reaffirms the dominant influence of contact area parameters on stress wave transmission.

Small-diameter tunnels play a crucial role in urban infrastructure, managing functions such as sewage, rainwater, and electrical systems. However, the safety assessment of small-diameter tunnel shield construction faces difficulties due to unclear physical relationships and the limitations of traditional physical information models in predicting complex risks. To address this issue, the integration of physical information with data-driven analysis methods offers a promising approach. Combining these advantages, a hybrid model was proposed to establish a robust construction safety risk evaluation framework for small-diameter tunnels under geological conditions. The presently proposed method mainly consists of a clustering of risk factors, physical information stratification, and risk early warning. Specifically, the K-means clustering method optimized by the Harris Hawks algorithm was used for risk identification, the Analytic Hierarchy Process was used for risk analysis, and the physical information output from the risk analysis was used for risk warning. A case study was produced, utilizing the proposed hybrid model for the Wuhan East Lake Deep Tunnel project. The results show the risk transfer path through inadequate personnel safety awareness and protection, mechanical system failures and installation deviations, substandard material quality and improper stacking, outdated or immature construction technology, and environmental risks.

The deep drainage tunnel project is an important measure to alleviate urban waterlogging. The construction of a deep drainage tunnel is a complicated process, involving many influencing factors, and there are correlations among these influencing factors, so the risk assessment is difficult. In this study, the ISM method, CRITIC method and cloud model are combined to build a risk assessment model for the small-diameter shield construction of a deep drainage tunnel. Firstly, the risk index system of small-diameter shield construction in a deep drainage tunnel is put forward. Secondly, the ISM method is used to divide the risk indicators and extract the key risk factors. Then, these key risk factors are weighted with the CRITIC method, and the cloud model is used to evaluate the construction risk of a small-diameter shield of a deep drainage tunnel. Finally, the feasibility and accuracy of the proposed method are verified by a practical case. It was found that the risk assessment method proposed in this study can not only effectively assess the level of security risk, but also identify the key risk factors and rank the importance of these factors. The results of this study can reduce the interference items and workload of risk assessment to a certain extent, and help provide managers with an accurate decision-making basis.

Fine calculation of bridge temperature fields is significant for accurately evaluating thermal actions in bridge structures. Determining thermal loads on bridge surfaces caused by solar radiation is the most challenging part of the numerical thermal analysis because the sunlit and shaded areas on bridge surfaces change continuously with the sun’s rotation. Existing methods have low accuracy in determining thermal loads and cannot be applied to complex bridges. This study presents a new method for calculating temperature fields based on the advantages of building information modeling (BIM) technology in solar radiation analysis (SRA) and information sharing. This method starts with obtaining an accurate hourly insolation distribution on bridge surfaces through SRA implemented in a BIM system. Then, a Python script seamlessly maps the insolation information to finite element surfaces as thermal loads. This paper details the new method’s implementation steps and technical details, and a practical application on a concrete box girder demonstrates its applicability and effectiveness. Compared with previous methods, the proposed method has significant advantages, such as a more accurate calculation for solar radiation, a lower technical threshold, a higher degree of automation, less computational time, and easier finite element modeling.