Hazard Identification Model (HIM) for Concurrent Works in Steel Plant Maintenance Using Job Safety Analysis (JSA)

During maintenance activities in steel plants, the risk of accidents is heightened when tasks are performed concurrently in both temporal and spatial contexts. This study aims to develop the Hazard Identification Model (HIM) for concurrent works as a safety management tool to identify risk factors associated with such concurrent works. To achieve this, hazards were identified prior to task execution, and hazardous information was standardized using Job Safety Analysis (JSA) data, which included task locations and potential risks. Based on this structured information, a model was proposed to synchronize spatiotemporally related tasks and identify mutual safety risks between tasks. The proposed model was tested using 40 JSAs from maintenance activities at Company A, a steel manufacturing company in South Korea. Performance evaluation results showed an F1-Score of <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$98.33\%$</tex>, demonstrating significant reliability. This research confirms the potential of utilizing individual JSAs as a safety management tool to address the mutual risks of concurrent tasks. Furthermore, zero-accident management is expected to enhance worker safety and contribute to improved operational environments in the maintenance activities of steel plants.