The increase in energy demand due to industrial development and urbanization has resulted in the development of large-scale energy facilities. Republic of Korea’s petrochemical industrial complexes serve as prime examples of this phenomenon. However, because of complex processes and aging facilities, many of which have been in operation for over a decade, these industrial complexes are prone to process-deviation-related accidents. Chemical accidents in energy facilities involving high-pressure liquids or gases are especially dangerous; therefore, proactive accident prevention is critical. This study is also relevant to corporate environment, social, and governance (ESG) management. Preventing chemical accidents to protect workers from injury is critical for business and preventing damage to surrounding areas from chemical accidents is a key component of ESG safety. In this study, we collected accident data, specifically injury-related incidents, from Republic of Korea’s petrochemical industrial complexes, which are the foundation of the energy industry. We analyzed the causes of accidents in a step-by-step manner. Furthermore, we conducted a risk analysis by categorizing accident data based on the level of risk associated with each analysis result; we identified the main causes of accidents and “high-risk process stages” that posed significant risk. The analysis reveals that the majority of accidents occur during general operations (50%, 167 cases) and process operations (39%, 128 cases). In terms of incident types, fire/explosion incidents accounted for the highest proportion (43%, 144 cases), followed by leakage incidents (24%, 78 cases). Furthermore, we propose a disaster safety artificial intelligence (AI) model to prevent major and fatal accidents during these high-risk process stages. A detailed analysis reveals that human factors such as accumulated worker fatigue, insufficient safety training, and non-compliance with operational procedures can significantly increase the likelihood of accidents in petrochemical facilities. This finding emphasizes the importance of introducing measurement sensors and AI convergence technologies to help humans predict and detect any issues. Therefore, we selected representative accident cases for implementing our disaster safety model.
This work was supported by Korea Environment Industry & Technology Institute (KEITI) through Advanced technology development project for predicting and preventing chemical accidents Program (or Project), funded by Korea Ministry of Environment (MOE) (RS-2022-KE002224).
