Calcium sulfoaluminate (CSA) cement has emerged as a low-carbon alternative to ordinary Portland cement (OPC), offering reduced CO₂ emissions and rapid strength development. However, the role of the ferrite phase in CSA systems remains underexplored. This study investigates the influence of ferrite-phase composition on CSA cement properties through targeted clinker design, hydration analysis, and macro–micro performance testing. Nine clinker formulations were synthesized by systematically increasing the ferrite content (10–30%) while adjusting belite (C₂S) proportions, using limestone, bauxite, and supplementary Fe₂O₃/SiO₂. Results reveal that the ferrite phase enhances the formation and stabilization of ye’elimite (C₄A₃Š) during clinkering and reduces low-activity transitional phase products. Increasing the iron-phase content appropriately improves early strength by promoting ettringite (AFt) formation and refines pore structures to enhance later strength development. The maximum strength improvement is achieved when the target ferrite-phase content is set to 15%, showing a 25.1% increase in 1 d strength and an 11.5% increase in 28 d strength. While ferrite phases and C₂S ensure long-term strength gains, excessive ferrite content reduces C₄A₃Š availability, limiting early AFt formation and compromising initial strength. These findings highlight the dual role of the ferrite phase in optimizing CSA cement performance and sustainability, providing a foundation for designing ferrite-rich, low-carbon binders.

Efficient acquisition of rock mass parameters is a critical step for conducting numerical simulations in tunneling and ensuring the safety of subsequent construction. This paper proposes an intelligent back-analysis method for key rock mass parameters (Young’s modulus, Poisson’s ratio, cohesion, and friction angle) based on excavation-induced deformation data, using a deformation database that incorporates multi-feature values from tunnel excavation. This study employs five machine learning algorithms with single-feature inputs and three deep neural networks (DNNs) with multi-feature inputs, with a particular focus on convolutional neural network (CNN) due to their superior performance in terms of both accuracy and efficiency. The results demonstrate that the CNN model incorporating excavation features achieves excellent performance in parameter back-analysis, with an R² of 0.99 and 97.8% of predictions having errors within 5%. Compared with machine learning models using single-feature inputs, the CNN-based approach improves predictive performance by an average of 13.9%. Furthermore, compared with other DNNs, the CNN consistently outperforms across various evaluation metrics. This study also investigates the CNN’s capability to predict rock mass parameters using deformation data from early-stage excavation. After ten excavation steps, 96.9% of test samples had prediction errors within 5%. Finally, the proposed method was validated using field-monitored deformation data from a real highway tunnel project, confirming the method’s effectiveness and practical applicability.

Slab–column structures are susceptible to sudden punching shear failure at connections due to the absence of traditional beam support, prompting the need for effective damage monitoring. This study employs an acoustic emission (AE) technique to investigate the failure process of reinforced concrete slab–column specimens, analyzing basic AE parameters (hits, amplitude, energy), improved b-value (Ib-value), and RA–AF correlation, while introducing a Gaussian Mixture Model (GMM) to establish a unified index integrating crack type identification and energy information. Experimental results show that AE parameters can effectively track different stages of crack development, with Ib-value reflecting the transition from micro-crack to macro-crack growth. The correlation between AE energy and structural strain energy enables quantitative damage assessment, while RA–AF analysis and GMM clustering reveal the shift from bending-dominated to shear-dominated failure modes. This study provides a comprehensive framework for real-time damage evaluation and failure mode prediction in slab–column structures, demonstrating that AE-based multi-parameter analysis and data-driven clustering methods can characterize damage evolution and improve the reliability of structural health monitoring.