Construction safety accidents have emerged in an endless stream in recent years, causing many casualties and property losses. Among them are caused by insufficient supervision on the construction sites and workers’ low safety awareness. However, the traditional manual management method which consumes manpower and resources is no longer applicable. Thus, in this study, a novel single-stage model based on YOLOv8s was suggested, mainly used for two purposes: for one thing, workers’ personal protective equipment detection, and for another, monitoring and recognizing whether workers enter dangerous areas, feeding back the detection results in real-time to reduce the occurrence of construction accidents. Besides, a brief design of distance calculation was proposed. The model was trained for 200 iterations on a dataset originating from Roboflow, consisting of 103,500 annotated images. According to experiment results, YOLOv8s outperformed YOLOv8n, YOLOv5s, and YOLOv5n in terms of detection performance. It achieved mAP50 of 84%, precision of 85%, and recall of 60.5% in nine detection classes. With the aid of artificial intelligence technology, this study seeks to provide an effective method for managing construction site safety, which might be improved even further with additional images and a more robust network architecture.

Structural health monitoring commonly uses natural frequency analysis to assess structural conditions, but direct frequency shifts are often insensitive to minor damage and susceptible to environmental influences like temperature variations. Traditional methods, whether based on absolute frequency changes or theoretical models like PCA and GMM, face challenges in robustness and reliance on model selection. These limitations highlight the need for a more adaptive and data-driven approach to capturing the intrinsic nonlinear correlations among multi-order modal frequencies. This study proposes a novel approach that leverages the nonlinear correlations among multi-order natural frequencies, which are more sensitive to structural state changes. A deep learning framework integrating CNN-BiLSTM-Attention is designed to capture the spatiotemporal dependencies of multi-order frequency data, enabling the precise modeling of intrinsic correlations. The model was trained exclusively on healthy-state frequency data and validated on both healthy and damaged conditions. A probabilistic modeling approach, incorporating Gaussian distribution and cumulative probability functions, was used to evaluate the estimation accuracy and detect correlation shifts indicative of structural damage. To enhance the robustness, a moving average smoothing technique was applied to reduce random noise interference, and damage identification rates over extended time segments were calculated to mitigate transient false alarms. Validation experiments on a mass-spring system and the Z24 bridge dataset demonstrated that the proposed method achieved over 95% damage detection accuracy while maintaining a false alarm rate below 5%. The results validate the ability of the CNN-BiLSTM-Attention framework to effectively capture both structural and environmental nonlinearities, reducing the dependency on explicit theoretical models. By leveraging multi-order frequency correlations, the proposed method provides a robust and highly sensitive approach to structural damage identification. These findings confirm the practical applicability of deep learning in damage identification during the operational phase of structures.

Structural Health Monitoring relies on accurate modal identification and effective damage detection to assess structural performance and safety. However, traditional sensor placement methods struggle to balance modal identification uncertainty, which arises from limited sensor coverage and measurement noise and damage detection sensitivity, which requires sensors to be optimally positioned to capture structural stiffness variations. To address this challenge, this study proposes a multi-objective sensor placement optimization method based on the Non-Dominated Sorting Genetic Algorithm. The method introduces two key objective functions: minimizing modal identification uncertainty by leveraging Bayesian modal identification theory and information entropy and maximizing damage detection sensitivity by incorporating an entropy-based measure to quantify the uncertainty in stiffness variation estimation. By formulating the problem as Pareto-based multi-objective optimization, the method efficiently explores a trade-off between the two competing objectives and provides a diverse set of optimal sensor placement solutions. The proposed approach is validated through numerical experiments on a simply supported beam and a benchmark bridge structure, demonstrating that different optimization objectives lead to distinct sensor placement patterns. The results show that solutions prioritizing modal identification distribute sensors across the structure to improve global response estimation, while solutions favoring damage detection concentrate sensors in critical areas to enhance sensitivity. The proposed method significantly improves sensor placement strategies by offering a systematic and flexible framework for SHM applications, enabling engineers to tailor monitoring strategies based on specific structural assessment needs.

The dimensional quality inspection of prefabricated concrete (PC) elements is crucial for ensuring overall assembly quality and enhancing on-site construction efficiency. However, current practices remain heavily reliant on manual inspection, which results in high operator dependency and low efficiency. Existing Light Detection and Ranging (LiDAR)-based methods also require skilled professionals for scanning and subsequent point cloud processing, thereby presenting technical challenges. This study developed a 3D LiDAR system for the automatic identification and measurement of the dimensional quality of PC elements. The system consists of (1) a hardware system integrated with camera and LiDAR components to acquire 3D point cloud data and (2) a user-friendly graphical user interface (GUI) software system incorporating a series of algorithms for automated point cloud processing using PyQt5. Field experiments comparing the system’s measurements with manual measurements on prefabricated bridge columns demonstrated that the system’s average measurement error was approximately 5 mm. The developed system can provide a quick, accurate, and automated inspection tool for dimensional quality assessment of PC elements, thereby enhancing on-site construction efficiency.