Efficient and reliable structural health monitoring is essential for ensuring the safety and extending the service life of steel structures. Owing to the advantages of non-contact nature， high efficiency， and a high degree of automation， computer vision （CV） has gradually become an important technology for the inspection and maintenance of steel structures. Focusing on surface cracks and corrosion damage of steel structures， this review systematically summarizes the recent research progress in CV-based damage detection and outlines the major approaches， including image classification， object detection， and image segmentation. Particular attention is paid to key optimization strategies for small object detection， robustness under complex backgrounds， few-shot learning， and on-site deployment. Existing studies indicate that CV has significantly improved the automation， intelligence， and precision of damage detection for steel structures. However， further advances are still required in dataset standardization， model robustness to interference， generalization capability across scenarios， and lightweight real-time inference.

The concrete-filled steel tubular （CFST） column-double laminated slab composite shear wall is a novel composite structural form for prefabricated buildings. A refined three-dimensional finite element model was established using ABAQUS and validated against quasi-static test data. Combined with test and numerical results， the mechanical mechanism under quasi-static loading was revealed， and the shear slip at the precast-cast-in-situ concrete interface was identified as the intrinsic cause of composite action degradation and performance deterioration. On this basis， a trilinear backbone curve model applicable to composite shear walls with a shear span ratio greater than 1.5 was proposed， along with formulas for equivalent stiffness and cross-sectional bearing capacity. Hysteretic rules were established based on a modified Clough model to develop a complete restoring force model. Validation results showed that the theoretical predictions agreed well with the test （numerical） results. Furthermore， an interface strengthening scheme using angle steel shear keys was proposed， which increased the ultimate drift ratio by 34% and the ductility coefficient by 26%， significantly improving the plastic deformation capacity.

This study investigated the fatigue life of steel crane beams through fatigue testing and combined finite element analysis to reveal the stress distribution changes at the support of variable-section beams before and after prestress strengthening. In addition， the equivalent structural stress method was employed to predict the fatigue life corresponding to the initiation of 20 mm cracks at the support. The results indicated that prestress strengthening significantly reduced the stress level at critical welds， while the location of maximum stress and the failure mode remained unchanged. With increasing prestress control values， both the overall failure life of the beam and the crack initiation life at the support were significantly extended. Under a prestress control value of 12.5 t， the strengthening effectiveness factors for overall beam failure and visible support cracks reached 4.08 and 4.23， respectively， demonstrating the effectiveness of high-level prestressing.

To meet the demand for optimizing long-term maintenance decisions in intelligent bridge operation and maintenance， considering the characteristics of time-varying bridge deterioration under a finite horizon， financial discounting of maintenance costs， and difficulty in long-term reward propagation， a life-cycle maintenance decision model incorporating non-homogeneous deterioration and discounting effects was developed. The bridge deterioration process was characterized by non-homogeneous Markov state transitions. Based on discrete health states and maintenance actions， maintenance costs and risk costs were integrated into a unified cost function， while cash-flow discounting was introduced into the decision-making process. To address the limitations of conventional reinforcement learning methods in handling finite-horizon stage-wise decision tasks， non-homogeneous state transitions， and unstable training， a reinforcement learning framework combining state augmentation and backward curriculum learning was proposed. Expanded state representation enhanced the policy’s capability to capture finite-horizon characteristics， while backward curriculum learning gradually extended the training interval to improve learning stability and convergence efficiency. Numerical results demonstrated that the proposed method effectively adapted to finite-horizon maintenance decision problems under non-homogeneous bridge deterioration and achieved favorable performance in both policy quality and training stability， thereby providing methodological support for maintenance planning in life-cycle bridge operation and maintenance management.

Taking the renovation project of C10 Laboratory at Tsinghua University’s Nankou Base for State Key Laboratories as the engineering background， this study focused on the core contradiction between industrial heritage conservation and the functional needs of national key laboratories in the adaptive reuse of old industrial buildings， and proposed a full-cycle renovation framework of "Conservation–Reconstruction–Symbiosis". With multi-source heterogeneous data fusion， this study completed a comprehensive diagnosis of the workshop， established a three-level industrial heritage conservation system， and developed integrated renovation technologies for heritage feature preservation and building performance improvement. The project achieved the coordinated goals of industrial context inheritance， scientific research function implementation and low-carbon development， and provided replicable engineering reference for the sci-tech innovation-oriented regeneration of similar old industrial areas.

To address the low efficiency， high risk， and limited quantitative capability of manual inspection for fatigue cracks in steel box girders， a study was conducted on the force analysis and motion control of a magnetic wall-climbing robot for crack inspection. According to the crack inspection requirements for deck plates and diaphragms， a wall-climbing robot equipped with an eddy current testing device was designed， and key parameters including overall dimensions， payload capacity， and operating speed were determined. Static and dynamic models of the robot were established to analyze the minimum magnetic adhesion force and driving torque required on steel plate surfaces. Based on the Webots platform， simulations were carried out to investigate the robot’s motion under different payload and weld obstacle conditions. The results showed that the robot could move continuously between the diaphragm and deck plate. As the payload increased， the start-up time on the diaphragm became longer and speed fluctuation became more pronounced， while the motion on the deck plate remained relatively stable. When crossing a weld， short-term speed fluctuations occurred， and the pitch angle increased significantly with the rising payload. Overall， the robot still maintained good obstacle-crossing capability and motion stability.

The Nanjing City Wall represents the pinnacle of ancient Chinese city wall construction and holds significant cultural heritage value. However， due to the deterioration of its structural integrity and external environmental factors， it faces substantial safety concerns requiring urgent restoration and reinforcement. First， this study examined the structural configuration and damage conditions of the section from Jiefang Gate to Xuanwu Gate based on field surveys and literature review. Second， finite element analysis using ANSYS software was conducted on the wall structure. The analysis focused on evaluating the mechanical properties and safety under various combined conditions， including the effects of air-raid shelters and moisture absorption/expansion of internal brick-rubble-soil fill， to identify potential hazards. Finally， adaptive restoration and conservation measures were proposed， balancing both the preservation of historical appearance and the reinforcement of structural safety. This study implemented targeted reinforcement measures for different types and grades of deterioration， including structural strengthening of wall bodies， rampart top surfaces， and arches. Under the premise of preserving historical appearance， the wall structure was reinforced to achieve minimal intervention conservation for cultural heritage buildings， providing valuable insights and references for the preservation and restoration of ancient city walls.

A vision-based detection method for bolt missing and loosening using the optimal hexagon rule is proposed. High-quality images are obtained through preprocessing operations such as perspective transformation and distortion correction. Based on the optimal hexagon rule， combined with a regional attention mechanism and a residual efficient layer aggregation network， a keypoint detection algorithm based on YOLOv26 is developed to precisely locate the six vertex coordinates of the head of standard hexagonal-head bolts. The Graham scan algorithm is adopted to obtain the convex hull of the circumcircle of the six bolt vertices. Taking the centroid of the convex hull as the center， the sum of deviations between the actual and estimated values of the six vertices is minimized. The Broyden-Fletcher-Goldfarb-Shanno （BFGS） quasi-Newton optimization algorithm is used to adjust the vertex coordinates and generate optimized regular hexagon vertex coordinates. By comparing the coordinate states of bolts， the rotation angle of the bolt can be calculated. Bolt joint rotation tests using 16-hole three-color bolt heads （gray， blue， and red） showed that within the loosening angle range of 0–60°， the absolute error of the identified bolt loosening angle ranged from -2° to 2°， with a maximum relative error of 8%， demonstrating that the proposed optimal hexagon method provided high detection accuracy and stability.

This study investigated the structural response of a 24-year-old， 160 m span concrete-filled steel tubular （CFST） arch bridge after the fracture of a single tie rod. By comparing monitoring data before and after the tie rod fracture， this study systematically analyzed the variation characteristics of key mechanical indicators， including arch foot displacement， suspender cable force， and the alignment of the arch ribs and the bridge deck. Furthermore， it evaluated the influence pattern of the tie rod fracture on the bridge structure. The results showed that after the fracture of a single tie rod， the arch feet underwent outward displacement， and both the arch ribs and the bridge deck experienced downward deflection， with the deformation values on the fractured side being significantly larger than those on the non-fractured side. The suspender cable force showed no obvious change. The deformations of the arch ribs and the deck exhibited an asymmetric distribution： the vertical deflection of the free-end half-span on the fractured side was larger than that of the fixed-end half-span， while the opposite was true for the non-fractured side. Furthermore， a full-bridge finite element model was established to simulate the structural response of the bridge induced by the tie rod fracture， and the calculated results reproduced the monitoring data of the actual bridge well. Based on this model， a dynamic amplification factor was introduced to evaluate the stress state of the remaining tie rods and the arch ribs upon the sudden fracture of multiple tie rods.

To enhance the intelligent supervision of photovoltaic （PV） project progress and address the issue of low recognition accuracy caused by component occlusion in complex scenarios， this study proposed an automated recognition approach for key PV components that integrates UAV images with an improved object detection algorithm. In response to common challenges such as small-scale targets and occlusion interference in UAV images， this study developed an optimized non-maximum suppression mechanism and a dynamic screening strategy based on target size and category features. Experimental results showed that the improved model achieved stable convergence of the loss function during training. Its key performance indicators， including detection precision， recall， mAP50， and mAP50-95， reached 94.8%， 93.2%， 94.8%， and 96.5%， respectively. In the practical application of the Anduo PV project in Nagqu， Tibet， the average recognition accuracy for core components such as pile foundations， PV supports， and PV modules exceeded 95%， significantly outperforming traditional manual inspection methods. These findings demonstrated that the proposed approach effectively reduces target omission under occlusion through dynamic detection optimization， providing a feasible technical solution for intelligent progress monitoring in complex PV construction environments and possessing considerable practical engineering value.