Application of Artificial Intelligence in Safety Management to Mitigate Risks During Construction Site Mobilization
Application of Artificial Intelligence in Safety Management to Mitigate Risks During Construction Site Mobilization
Dariush Jamali1 Alireza Valipour2
1) M.Sc. in Civil Engineering – Construction Engineering and Management, Shiraz Branch, Islamic Azad University, Shiraz, Iran.
2) Associate Professor, Civil Engineering – Construction Management, Shiraz Branch, Islamic Azad University, Shiraz, Iran
IOI Code
:
ACFE-ACAAAD
Publication :
8th.International Conference & 9th.National Conference on Civil Engineering, Architecture, Art and Urban Design(9iccacs.ir)
Abstract :
Construction site setup safety represents one of the most critical phases of civil engineering projects; due to the simultaneous execution of activities, the interaction of equipment, and the presence of personnel, it contributes significantly to the occurrence of accidents. While traditional risk assessment methods are widely used, they are largely static, reliant on individual judgment, and lack dynamic predictive capabilities. This research aims to propose an intelligent framework for managing safety during construction site setup by leveraging artificial intelligence to mitigate workplace hazards. A mixed-methods (quantitative-qualitative) approach was employed. In the quantitative phase, data were collected from construction and HSE (Health, Safety, and Environment) experts using standardized questionnaires and a risk assessment checklist based on the Failure Mode and Effects Analysis (FMEA) method. Following the calculation of the Risk Priority Number (RPN) for key site setup hazards, an Artificial Neural Network (ANN) was utilized to predict risk levels, and a Genetic Algorithm (GA) was applied to optimize the layout of site equipment with the objective of minimizing risk. The results indicated that hazards related to machinery collisions and the falling of materials yielded the highest RPN values; the AI-based model successfully achieved a significant reduction in the risk levels associated with these hazards. In the qualitative phase, semi-structured interviews were conducted with experts, and the data were analyzed using open and axial coding. The qualitative findings underscored the pivotal role of site layout, the limitations of traditional methods, the existence of gaps in safety data, and the substantial potential of artificial intelligence in safety management. Overall, the results of this research indicate that the application of intelligent models can be an effective step toward enhancing safety and proactive decision-making in the setup of construction sites.
Keywords : construction site safety artificial intelligence failure mode and effects analysis (fmea) artificial neural network (ann) genetic algorithm (ga)