Cold region covers over 50% all over the world. As an indispensable part of the project, concrete is greatly affected by temperature during the curing process. In this paper, through the orthogonal experiment design, we studied the mixing temperature, steel fiber, and water reducing agent dosage on concrete mixture slump; the influence of curing temperature, steel fiber, water reducing agent, and accelerating agent content on compressive strength of concrete; and the influence of the final microstructure by scanning electron microscopy (28-day concrete, analysis of the degree of hydration reaction). The results show that the slump of concrete increases with the amount of water reducing agent. Mixing temperature and steel fiber content have little effect on the workability of the mixture. Curing temperature has a significant effect on the growth of concrete compressive strength. The higher curing temperature is within 0∼20°C, the faster the growth of concrete strength is. The longer the age of concrete, the greater the compressive strength. The content of water reducing agent and accelerating agent only has a significant effect on the early strength of concrete, while the content of steel fiber has a great effect on the late strength of concrete. Curing temperature affects the degree of hydration reaction of concrete. The higher the curing temperature, the more the cementing substances produced by hydration reaction of concrete, the higher the degree of hydration reaction, and the higher the strength of concrete. The research results are helpful to improve the mine support operation in high-cold and high-temperature difference area.

This study aims to improve the prediction accuracy of rockburst intensity grades in gently dipping rock strata, and provide reliable technical support for risk prevention, long-term stable production and sustainable development in underground engineering construction. Therefore, a rockburst intensity grade prediction model combining multi-strategy improved particle swarm optimization (MIPSO) with random forest (RF) is proposed, and the stress coefficient (SCF), brittleness coefficient (B) and elastic energy index (W_et) are selected as input indicators. After the algorithm and model are validated using benchmark test functions and the five-fold cross-validation method, their performance is compared with that of the other four models based on evaluation metrics, and the Shapley interpretability analysis (SHAP) is conducted. The results show that the performance of the model is superior to that of other models, and the importance ranking of the prediction indicators is SCF, W_et, and B. Finally, the application software developed based on the model is used for rockburst intensity grade prediction; rockburst prediction indicators are obtained through experiments and numerical simulations, and the prediction results obtained after importing them into the software are consistent with the actual situation, which proves that the rockburst prediction framework constructed in this paper has practicality.