To improve the mechanical performance of large-size concrete-filled steel tubes without increasing the steel consumption, this study conducted a numerical analysis of the flexural behavior of concrete-filled square steel tubes with embedded steel angles and spiral stirrups (CFSST-SASS). A finite element (FE) model was established and validated against experimental results. Considering the composite confinement effects from the steel tube, angles, and stirrups, a compressive constitutive model for the core concrete of CFSST-SASS was developed. The flexural working mechanism and composite action were analyzed. Parametric studies were carried out to investigate the influences of steel ratio, volumetric stirrup ratio, angle configuration ratio, confinement diameter-to-width ratio, and material strengths on flexural capacity, stiffness, and ductility, with recommended ranges proposed. Results show that CFSST-SASS exhibits favorable composite action and flexural performance. The steel ratio, steel tube strength, and concrete strength are the primary influencing parameters. Increasing the angle configuration ratio can improve the bearing capacity and ductility. Recommended ranges are: steel ratio 5.96–11.61%, steel tube yield strength 355–690 MPa, concrete cubic strength 30–70 MPa, volumetric stirrup ratio 0.6–1.5%, angle configuration ratio not exceeding 2.5%, and confinement diameter-to-width ratio 0.5–0.9. Predictions from current codes are conservative. Based on the unified theory, a formula for the flexural capacity of CFSST-SASS was proposed, which shows good accuracy, with errors within 5%, verified by numerous numerical results.

Building façade damage segmentation remains challenging because cracks, peeling, hollow-like areas, stains, and erosion often exhibit weak contrast, irregular boundaries, discontinuous structures, and substantial scale variations under complex surface textures and illumination conditions. To address these challenges, this study proposes MMDF-Net, a multimodal instance segmentation network for paired RGB–IR façade damage images. The network adopts dual RGB and infrared branches and performs multi-scale cross-modal interaction across P2–P5 levels. A Frequency-Decoupled Cross-Modal Bridge is designed to separately model low-frequency material responses and high-frequency local damage details, thereby enabling gated bidirectional exchange between the two modalities. A Crack Topology-Aware Encoder further enhances the continuity of thin, curved, branched, and locally discontinuous cracks through directional strip convolution and bending-aware modeling. In addition, a Multi-Scale Damage Decoding Pyramid integrates high-resolution boundary details, mid-level structural cues, and high-level semantic context to support stable mask prediction across different damage scales. Experiments were conducted on a custom-built RGB–IR building façade damage dataset containing 1500 paired image samples across five damage categories. MMDF-Net achieved 82.1% mask precision, 78.6% mask recall, 72.3% mask mAP50, and 65.6% mask mAP50–95, with 7.8 M parameters and 23.5 GFLOPs, outperforming representative RGB and RGB–IR segmentation baselines. These results indicate that task-oriented multimodal feature organization can improve façade damage segmentation without relying on excessive model expansion.