This study aims to resolve the “secondary activation” challenge when erecting structures over goaf zones by employing a novel grouting and filling material. It delves into the performance degradation of the innovative ECS soil grouting filling material (ESGF material) within the goaf’s ionic erosion context. Erosion tests were performed on ESGF material specimens with varying mix designs to mimic the sulfate and chloride erosion scenarios commonly encountered in practical engineering. The macro-mechanical properties and microstructural changes of ESGF materials under ionic erosion environment were systematically investigated by various testing methods, such as unconfined compressive strength (UCS), SEM, XRD, TG, FTIR, and Raman. The findings indicate that both sulfate and chloride erosion lead to a reduction in the strength of the ESGF material. As erosion progresses, the specimens experience a mass increase followed by a decrease, with their strength exhibiting a consistent downward trend. In sulfate erosion conditions, the buildup of expansion product like ettringite (AFt) and thaumasite (TSA) inflicts substantial internal structural damage. Conversely, Friedel’s salt, the primary product of chloride erosion, exhibits relatively weaker expansiveness, and chloride concentration exerts a less pronounced effect on material degradation. Moreover, the cementitious material content and the proportion of quick-setting component play a significant role in determining the ESGF material’s resistance to erosion. By adjusting the quick-setting components ratio in response to changes in the water content of soft soil, the anti-ion erosion performance of solidified soil can be effectively enhanced. Notably, curing with a 5% sulfate maintenance could significantly improve the erosion resistance of ESGF material. This suggests that ESGF materials can be used without concern for curing issues in high-salinity environments during grouting. The research addresses the root cause of goaf subsidence while facilitating the recycling of solid waste, offering an environmentally friendly solution.

Image-based detection of concrete water tank damage in mining areas holds promise for practical applications. However, current deep learning-based detection algorithms often face challenges in balancing accuracy with computational complexity for real-world deployment. This paper presents an improved YOLOv5 detection method for concrete water tank damage. Firstly, the conventional convolution module in the CSPDarknet backbone is optimized with GSConv (Grouped Shuffle Convolution) to enhance feature extraction while reducing the number of parameters. Secondly, a weight transformation attention mechanism is integrated into the C3 structure to strengthen the feature representation of crack regions. Finally, the Minimum Point Distance IoU (MPDIoU) is employed for precise localization of irregular damage. On a dataset of over 11,000 images, the proposed method achieves a mean average precision (mAP@0.5) of 84.3% (precision: 88.7%; recall: 85.9%). It outperforms the original YOLOv5s, with a 6.5% higher mAP and an 11.1% faster inference speed, while maintaining a compact model size of 7.5M parameters and running at 86 FPS. Ablation studies confirm the individual contributions of each proposed module to these improvements. The algorithm thus provides an efficient and accurate solution that is suitable for deployment on resource-constrained devices.