Concrete surface crack detection is a critical research area for ensuring the safety of infrastructure, such as bridges, tunnels and nuclear power plants, and facilitating timely structural damage repair. Addressing issues in existing methods, such as high cost, lengthy processing times, low efficiency, poor effectiveness and difficulty in application on mobile terminals, this paper proposes an improved lightweight concrete surface crack detection algorithm, YOLOv8-Crack Detection (YOLOv8-CD), based on an improved YOLOv8. The algorithm integrates the strengths of visual attention networks (VANs) and Large Convolutional Attention (LCA) modules, introducing a Large Separable Kernel Attention (LSKA) module for extracting concrete surface crack and local feature information, adapted for features such as fracture susceptibility, large spans and slender shapes, thereby effectively emphasizing crack shapes. The Ghost module in the YOLOv8 backbone efficiently extracts essential information from original features at a minimal cost, enhancing feature extraction capability. Moreover, replacing the original convolution structure with GSConv in the neck network and employing the VoV-GSCSP module adapted for the YOLOv8 framework reduces floating-point operations during feature channel fusion, thereby lowering computational complexity whilst maintaining model accuracy. Experimental results on the RDD2022 and Wall Crack datasets demonstrate the improved algorithm increases in mAP50 by 15.2% and 12.3%, respectively, and in mAP50-95 by 22.7% and 17.2%, respectively, whilst achieving a reduced model computational load of only 7.9 × 10⁹, a decrease of 3.6%. The algorithm achieves a detection speed of 88 FPS, enabling real-time and accurate detection of concrete surface crack targets. Comparison with other mainstream object detection algorithms validates the effectiveness and superiority of the proposed approach.

To improve the properties of ground granulated blast furnace slag (GGBS) and utilize ground granulated blast furnace slag efficiently, this study investigates the effect of fineness on the hydration activity index (HAI) of ground granulated blast furnace slag. The hydration activity index of GGBS with six specific surface areas (SSAs) was characterized by the ratio of compressive strength of the prismatic mortar test block. The particle size distribution of GGBS with different grinding times was tested by laser particle size analyzer. The paste of different specific surface area GGBSs in different curing ages was investigated at the micro level by X-ray diffraction, scanning electron microscope, energy dispersive spectrometer, thermogravimetric scanning calorimeter, and differential scanning calorimeter. The effect of particle distribution of GGBS on the hydration activity index of different curing ages was studied by gray correlation analysis. The results indicated that the compressive strength and hydration activity index increases with the increase of a specific surface area of GGBS at different curing ages. The hydration activity index at different curing ages is almost a linear role for specific surface areas. With the increase in the specific surface area of GGBS, the content of Ca(OH)₂ in paste decreases gradually. When GGBS was added into a mortar test block, the hydrate calcium silicate gel in paste changed from a high Ca/Si ratio to a low Ca/Si ratio. The 0–10 micron particles of GGBS particle distribution were highly correlated with the hydration activity index at different curing ages.

Bridge crack detection is a key factor in ensuring the safety and extending the lifespan of bridges. Traditional detection methods often suffer from low efficiency and insufficient accuracy. The development of computer vision has gradually made bridge crack detection methods based on deep learning to become a research hotspot. In this study, a lightweight bridge crack detection algorithm, YOLO11-Bridge Detection (YOLO11-BD), is proposed based on the optimization of the YOLO11 model. This algorithm uses an efficient multiscale conv all (EMSCA) module to enhance channel and spatial attention, thereby strengthening its ability to extract crack features. Additionally, the algorithm improves detection accuracy without increasing the model size. Furthermore, a lightweight detection head (LDH) is introduced to process feature information from different channels using efficient grouped convolutions. It reduces the model’s parameters and computations whilst preserving accuracy, thereby achieving a lightweight model. Experimental results show that compared with the original YOLO11, the YOLO11-BD algorithm improves mAP50 and mAP50-95 on the bridge crack dataset by 3.1% and 4.8%, respectively, whilst significantly reducing GFLOPs by 19.05%. Its frame per second remains higher than 500, demonstrating excellent real-time detection capability and high computational efficiency. The algorithm proposed in this study provides an efficient and flexible solution for the monitoring of bridge cracks using remote sensing devices such as drones, and it has significant practical application value. Its lightweight design ensures strong cross-platform adaptability and provides reliable technical support for intelligent bridge management and maintenance.

Compressive strength of concrete is an important parameter in the design of concrete structures and the prediction of their durability. Therefore, it is of great significance to predict the compressive strength of concrete. In this study, a fully connected neural network model is developed using the PyTorch framework to predict the compressive strength of concrete and compared with six other machine learning models. These models are multiple linear regression, K‐nearest neighbor regression, support vector machine, decision tree, random forest, light gradient boosting machine, and artificial neural network. The model is trained using 4,253 data with seven input parameters, including cement (C), fly ash (F), mineral powder (K), fine aggregate (FA), coarse aggregate (CA), water reducer admixture (WRA), and water (W). Three thousand six hundred twenty‐one data in the datasets are used to train the prediction model after data cleaning, and 632 data are used to validate the model. The results show that the fully connected neural network model based on PyTorch frame can predict the compressive strength of concrete with higher accuracy. Therefore, it is a reliable and useful method to optimize the artificial network model. So, it has important application value in practice. The strength of concrete can be predicted in advance, making the project more efficient and reducing costs. Besides, by adjusting the mix ratio, combining the strength prediction results in different environments and industries to ensure the quality of construction.