Conventional neural networks tend to fall into local extremum on large datasets, while the research on the strength of rubber concrete using intelligent algorithms to optimize artificial neural networks is limited. Therefore, to improve the prediction accuracy of rubber concrete strength, an artificial neural network model with hybrid algorithm optimization was developed in this study. The main strategy is to mix the simulated annealing (SA) algorithm with the particle swarm optimization (PSO) algorithm, using the SA algorithm to compensate for the weak global search capability of the PSO algorithm at a later stage while changing the inertia factor of the PSO algorithm to an adaptive state. For this purpose, data were first collected from the published literature to create a database. Next, ANN and PSO-ANN models are also built for comparison while four evaluation metrics, MSE, RMSE, MAE, and $R^2$, were used to assess the model performance. Finally, compared with empirical formulations and other neural network models, the result shows that the proposed optimized artificial neural network model successfully improves the accuracy of predicting the strength of rubber concrete. This provides a new option for predicting the strength of rubber concrete.

The addition of rubber to concrete improves resistance to chloride ion attacks. Therefore, rapidly determining the chloride permeability coefficient (D_CI) of rubber concrete (RC) can contribute to promotion in coastal areas. Most current methods for determining D_CI of RC are traditional, which cannot account for multi-factorial effects and suffer from low prediction accuracy. Machine learning (ML) techniques have good non-linear learning capabilities and can consider the effects of multiple factors compared with traditional methods. However, ML models easily fall into the local optimum due to their parameters’ influence. Therefore, a mixed whale optimization algorithm (MWOA) was developed in this paper to optimize ML models. The main strategies are to introduce Tent mapping to expand the search range of the algorithm, to use an adaptive t-distribution dimension-by-dimensional variation strategy to perturb the optimal fitness individual to thereby improve the algorithm’s ability to jump out of the local optimum, and to introduce adaptive weights and adaptive probability threshold values to enhance the adaptive capacity of the algorithm. For this purpose, data were collected from the published literature. Three machine learning models, Extreme Learning Machine (ELM), Random Forest (RF), and Elman Neural Network (ELMAN), were built to predict the D_CI of RC, and the three models were optimized using MWOA. The calculations show that the MWOA is effective with the optimized ELM, RF, and ELMAN models improving the prediction accuracy by 54.4%, 62.9%, and 36.4% compared with the initial model. The MWOA-ELM model was found to be the optimal model after a comparative analysis. The accuracy of the multiple linear regression model (MRL) and the traditional mathematical model is calculated to be 87.15% and 85.03%, which is lower than that of the MWOA-ELM model. This indicates that the ML model that is optimized using the improved whale optimization algorithm has better predictive ability than traditional models, providing a new option for predicting the D_CI of RC.

Rubber concrete (RC) exhibits high durability due to the rubber admixture. It is widely used in a large number of fatigue-resistant structures. Mesoscale studies are used to study the composition of polymers, but there is no method for fatigue simulation of RC. Therefore, this paper presents a finite element modeling approach to study the fatigue problem of RC on the mesoscale, which includes the random generation of the main components of the RC mesoscale structure. We also model the interfacial transition zone (ITZ) of aggregate mortar and the ITZ of rubber mortar. This paper combines the theory of concrete damage to plastic with the method of zero-thickness cohesive elements in the ITZ, and it is a new numerical approach. The results show that the model can simulate reasonably well the random damage pattern after RC beam load damage. The damage occurred in the middle of the beam span and tended to follow the ITZ. The model can predict the fatigue life of RC under various loads.

Understanding the impact of creep on the long-term mechanical features of concrete is crucial, and constructing an accurate prediction model is the key to exploring the development of concrete creep under long-term loads. Therefore, in this study, three machine learning (ML) models, a Support Vector Machine (SVM), Random Forest (RF), and Extreme Gradient Boosting Machine (XGBoost), are constructed, and the Hybrid Snake Optimization Algorithm (HSOA) is proposed, which can reduce the risk of the ML model falling into the local optimum while improving its prediction performance. Simultaneously, the contributions of the input features are ranked, and the optimal model’s prediction outcomes are explained through SHapley Additive exPlanations (SHAP). The research results show that the optimized SVM, RF, and XGBoost models increase their accuracies on the test set by 9.927%, 9.58%, and 14.1%, respectively, and the XGBoost has the highest precision in forecasting the concrete creep. The verification results of four scenarios confirm that the optimized model can precisely capture the compliance changes in long-term creep, meeting the requirements for forecasting the nature of concrete creep.

Rubber concrete has been applied to a certain extent in fatigue-resistant structures due to its good durability. Based on a cohesive model of rubber composed of a five-phase material containing mortar, aggregate, rubber, aggregate-mortar interfacial transition zone (ITZ), and rubber-mortar ITZ, this paper studies the influence of the cohesive parameters in the rubber-mortar ITZ on the fatigue problem of rubber concrete on the mesoscopic scale. As the weak part of cement-based composite materials, the ITZ has a great influence on the mechanical properties and durability of concrete, but the performance of the ITZ is difficult to test in macro experiments, resulting in difficulties in determining its simulation parameters. Based on the cohesive model with a rubber content of 5%, this study uses Monofactor analysis and the Plackett-Burman test to quickly and effectively determine the primary and secondary influences of the cohesive model parameters in the rubber-mortar ITZ; further, the response surface method is used to optimize the cohesive parameters in the rubber-mortar ITZ, and the numerical simulation results after optimizing the cohesive parameters are compared and analyzed with the simulation results before optimization. The results show that, under the setting of the optimized parameters, the simulation results of each item of the optimal cohesive model parameters in the rubber-mortar ITZ are in line with the reality and closer to the experimental data, and they are also applicable to rubber concrete models with different rubber dosing.