Current research on personal protective equipment (PPE) detection has mainly focused on hard hats, overlooking the detection of reflective clothing. Therefore, this study aims to address this research gap comprehensively. We achieve this by creating a novel dataset using semi-automatic labeling techniques and enhancing the YOLOv5 model. The dataset consists of four categories, assessing the presence of hard hats and reflective clothing. Additionally, we introduce an attention mechanism and an improved loss function to tackle challenges related to detecting reflective clothing and overlapping detection frames. Through extensive multi-model comparison experiments, our improved model, AL-YOLOv5, outperforms the baseline model with remarkable advancements of 0.9 AP in the data-limited category and 0.4 mAP overall. Notably, our improved model shows substantial progress in detecting reflective clothing, significantly reducing false detections, and improving overlapping bounding frames. In conclusion, this study contributes to PPE detection accuracy through a novel dataset and an improved model.

Due to factors such as the availability of assembly equipment, technology, and site management level, prefabricated building construction safety accidents often occur. To ensure the safety of prefabricated buildings and effectively reduce the accident rate, the concept of resilience is introduced into the safety management of prefabricated buildings. Based on the resilience absorption capacity, adaptation capacity, recovery capacity, and optimization capacity, a comprehensive evaluation index system for the safety resilience of prefabricated buildings is established. By combining prior knowledge with structural learning and parameter learning, a dynamic Bayesian network (DBN) model is constructed to dynamically evaluate the safety resilience of prefabricated buildings. Through forward causal reasoning and backward diagnostic reasoning, the dynamic safety resilience value of prefabricated buildings and the chain of maximum failure causes are obtained. Finally, by conducting a sensitivity analysis on the target nodes, the key influencing factors of the safety resilience of prefabricated construction are identified, and improvement suggestions for enhancing resilience are proposed. The results indicate that establishing a resilience safety culture, preventing unsafe behaviors of personnel, safety management, and supervision on the construction site, emergency management actions, and building a risk management information system are crucial factors influencing the safety resilience of prefabricated buildings. The enhancement of absorption capacity has the greatest impact on the safety resilience of prefabricated buildings.

Construction accident investigation reports contain critical information, but extracting useful insights from the voluminous Chinese text is challenging. Traditional methods rely on expert judgment, which leads to time-consuming and potentially inaccurate results. To overcome this problem, we propose a novel approach that combines text mining techniques and latent Dirichlet allocation (LDA) models to analyze standardized accident investigation reports in the Chinese construction industry. The proposed method integrates an information entropy term frequency-inverse document frequency (TF-IDF) weighting scheme to evaluate term importance and accounts for word and model uncertainty. The method was applied to a set of construction industry accident reports to identify the key factors leading to safety accidents. The results show that the causal factors of accidents in Chinese accident investigation reports consist of keywords and negative expressions, including “failure to timely identify safety hazards” and “inadequate site safety management”. Failure to timely identify safety hazards is the most common factor in accident investigation reports, and the negative expressions commonly used in the reports include “not timely” and “not in place”. The information entropy TF-IDF method is superior to traditional methods in terms of accuracy and efficiency, and the LDA model that considers word frequency and feature weights is better able to capture the underlying themes in the Chinese corpus. And the subject terms that make up the themes contain more information about the causes of accidents. This approach helps site managers more quickly and effectively understand the causal factors and key messages that lead to accidents from incident reports. It gives site managers insight into common patterns and themes associated with safety incidents, such as unsafe practices, hazardous work environments, and non-compliance with safety regulations. This enables them to make informed decisions to improve safety management practices.

As an efficient measure to protect the environment and reduce energy consumption, promoting prefabricated buildings can lead to the sustainable development of the world economy and long-term economic benefits for society. Nevertheless, for China, it is immature because of the high cost and difficulties in the promotion. The government’s strategies in economy and management are crucial to promoting prefabricated building policies. This paper establishes a quadripartite evolutionary game model composed of construction units, property developers, homebuyers, and government departments under the government supervision system by analyzing the entire interest chain of prefabricated buildings projects. It aims to study the impact of government management and economic strategies on promoting prefabricated building policies. The results show that: (1) The government should ensure the construction safety of projects through mature supervision systems to reduce citizens’ resistant moods caused by project quality problems; (2) The government should improve the reward and punishment mechanism to motivate construction units and developers; (3) The government should invite supervision consulting companies to increase information transparency, avoiding the economic losses of the people and the obstruction of policy implementation caused by information imbalance.

In order to achieve a comprehensive evaluation of the environmental impact of ecological restoration projects (ERP) under the current destruction and restoration of coastal ecological areas, this paper takes into account the impact of positive and negative indicators on the environment; analyzes the positive and negative benefits of ERP; and establishes a comprehensive environmental impact index system for marine ERP from ecological, economic, and social perspectives through the DPSIR model. On this basis, the cloud model and Monte Carlo simulation are used to obtain the comprehensive assessment grade of the construction period, short-term operation, and long-term operation in the project life cycle. The results show that the benefits of ERP, considering the impact of negative factors, are significantly reduced, and the benefits of ERP will increase remarkably in the long-term operation period. In engineering practice, the environmental pressure factor caused by excessive human activities during construction and operation periods is a key negative factor affecting the overall benefits of ERP. For project decision makers and other stakeholders, the comprehensive assessment grade considering negative impacts is more practical. At the same time, decision makers should take active response measures in the framework of long-term sustainable development, set a tolerance threshold for negative pressure indicators, and strengthen the management of ERP.

As countries around the world pay more and more attention to the sustainable development of the construction industry, the prefabricated building model has become the best construction type to achieve energy conservation and emission reduction. However, the prefabricated building entails higher technical requirements, and the workers involved in the construction must be trained to reduce the risks. For China, where the demographic dividend is gradually disappearing, how to quickly promote the industrializing workers process has become an urgent issue. This research focuses on the training and management of industrializing workers in prefabricated building. First, the facial images of the participants were collected from the actual test data, and the changes of participants’ facial expressions were analyzed through multitask convolutional neural network-Lighten Facial Expression Recognition (MTCNN-LFER). The results of the analysis were plugged into the facial expression recognition and evaluation model for industrializing workers training in this research to calculate the weights, and then all the weights were clustered through the improved SWEM-SAM method. The results show the following: (1) the values of objective data were used to judge the participating workers’ mastery of each knowledge and to evaluate whether they are qualified. (2) The evaluation results were used to analyze the risk events that may be caused by participating workers.