This study investigates the effects of basalt–polypropylene fibers on the compressive strength and splitting tensile strength of concrete and calculates the fractal dimension of the pore structure of concrete by using a fractal model based on the optical method. Test results reveal that hybrid fibers can improve the compressive strength and splitting tensile strength of concrete, and the synergistic effect of the hybrid fibers is strongest when the contents of basalt fiber (BF) and polypropylene fiber (PF) are 0.05% each, and that the maximum increments in compressive strength and splitting tensile strength are 5.06% and 9.56%, respectively. The effect of hybrid fibers on splitting tensile strength is greater than on compressive strength. However, hybrid fibers have adverse effects on mechanical properties when the fiber content is too high. The pore structure of basalt–polypropylene fiber-reinforced concrete (BPFRC) exhibits obvious fractal characteristics, and the fractal dimension is calculated to be in the range of 2.297–2.482. The fractal dimension has a strong correlation with the air content and spacing factor: the air content decreases significantly whereas the spacing factor increases with increasing fractal dimension. In addition, the fractal dimension also has a strong positive correlation with compressive strength and splitting tensile strength. Therefore, the fractal dimension of the pore structure can be used to evaluate the microscopic pore structure of concrete and can also reflect the influence of the complexity of the pore structure on the macroscopic mechanical properties of concrete.

Coal gangue, a by-product produced during the process of coal mining and washing, has a serious impact on the environment. Using coal gangue as a concrete aggregate has been proven helpful in potentially improving its value and reducing its environmental impact to a certain extent. However, the high water absorption and low strength of coal gangue aggregate cause a poor frost resistance of coal gangue aggregate concrete (CGAC), and thus limits its application in cold areas. This study attempted to modify the CGAC with steel fibers (including hooked-end, undulated, and copper-plated steel fiber) and slag powder, and investigated its frost resistance. Moreover, the impact that steel fiber and slag powder had on air-void characteristics of CGAC was also analyzed. The results show that when steel fibers were incorporated into CGAC, the compressive strength and splitting tensile strength of CGAC reduced significantly after freezing/thawing and that they experienced the smallest reduction when the content of the steel fiber was 1 vol.% and the undulated steel fibers worked best. However, the effect of slag powder on frost resistance of CGAC at an early age was not obvious, which may be related to the slower pozzolanic reaction of slag powder. Incorporating steel fiber or slag powder into CGAC can optimize its mesostructure and make the air-voids of concrete smaller, which is beneficial to its frost resistance. The results provide a good way to improve the performance of CGAC, expand its application in cold regions, and reduce the pollution caused by coal gangue.

A large number of in-service reinforced concrete structures are now entering the mid-to-late stages of their service life. Efficient detection of damage characteristics and accurate prediction of material performance degradation have become essential for ensuring the safety of these structures. Traditional damage detection methods, which primarily rely on manual inspections and sensor monitoring, are inefficient and lack accuracy. Similarly, performance prediction models for reinforced concrete materials, which are often based on limited experimental data and polynomial fitting, oversimplify the influencing factors. In contrast, partial differential equation models that account for degradation mechanisms are computationally intensive and difficult to solve. Recent advancements in deep learning and machine learning, as part of artificial intelligence, have introduced innovative approaches for both damage detection and material performance prediction in reinforced concrete structures. This paper provides a comprehensive overview of machine learning and deep learning theories and models, and reviews the current research on their application to the durability of reinforced concrete structures, focusing on two main areas: intelligent damage detection and predictive modeling of material durability. Finally, the article discusses future trends and offers insights into the intelligent innovation of concrete structure durability.