To proactively assess the losses caused by the deterioration of metro tunnels during the operational period, a new method, the cloud model‐based random forests (CRFs), is proposed to discuss the inconsistencies induced by mapping the monitoring data into the health rate of the metro tunnels. On top of the CRF, a self‐training framework is introduced to improve the predictive accuracy and the stability of the CRF by adding more unlabeled data. The main contribution of this paper is proposing a novel CRF model along with a semisupervised approach to overcome the inapplicability of the random forests algorithm in an inconsistent small database, and to reduce the substantial time and cost for expert annotation. The results indicate that (1) the proposed CRF achieves higher accuracy and stability than random forests in predictions; (2) the CRF outperforms the other state‐of‐the‐art methods even in a small database; (3) the self‐training improved CRF keeps highly precise when the ratio of labeled to unlabeled data is no less than 1:11.4. In this study, the suggested ratio of labeled and unlabeled data is no lower than 1:5.7 to reduce the risk of wrongly forecasting a seriously damaged tunnel section as a slightly damaged tunnel section.

One obstacle to the optimal time for pavement maintenance treatments based on the expected performance or cost-effectiveness is the lack of posttreatment performance models at different timings. This study first summarized the current effectiveness/cost-effectiveness evaluation methods. Then, the posttreatment performance model was established based on the pretreatment performance model and other factors such as traffic and environment. By incorporating the incremental posttreatment performance models into the effectiveness evaluation, an optimization method was developed to calculate the dynamic effectiveness/cost-effectiveness and to select the optimal performance threshold. Investigation of 243 sections from the long-term pavement performance (LTPP) database showed that when the pavement deteriorated very fast, an early age treatment was recommended, whereas when the pavement condition was good and the deterioration rate was not fast, a higher optimized international roughness index (IRI) threshold was recommended. In addition, the optimal IRI thresholds for fog seal and crack seal are lower than those of thin overlay, chip seal, and slurry seal, indicating that it is more effective or cost-effective to apply fog seal and crack seal treatments at a relatively early age.

A stochastic micromechanical framework for predicting the concrete probabilistic behavior is proposed considering the interfacial transition zone effects in this paper. The volume fraction of the interfacial transition zone is analytically calculated based on the aggregate grading. Multilevel homogenization schemes based on the direct interaction micromechanical solutions are presented to predict the concrete effective properties considering the aggregate and interfacial transition zone effects. By modeling the volume fractions and properties of the constituents as stochastic, we extend the deterministic framework to stochastic to incorporate the inherent randomness of effective properties among different concrete specimens. With the moments of the effective properties, the probability density function is approximated using the exponential polynomial for concrete material. Numerical examples including limited experimental validations, comparisons with existing micromechanical models, commonly used probability density functions, and the direct Monte Carlo simulations indicate that the proposed models provide an accurate and computationally efficient framework in characterizing the material’s effective properties. Finally, the effects of the randomness of interfacial transition zone and aggregate on the materials’ macroscopic probabilistic behaviors are investigated based on our proposed stochastic micromechanical framework.