Identification of risk features using text mining and BERT-based models: Application to an oil refinery

Abstract

The uncontrollable release of hazardous substances may lead to catastrophic accidents. In this context, risk studies are aimed at recommending either preventive measures or designing safeguards to mitigate the consequences. To that end, risk experts postulate possible leakages, then identify their causes and consequences, and finally evaluate and classify the risks into categories. These analyses rely on examination different engineering textual documents and attendance numerous meetings, which is very time consuming. Moreover, this qualitative process of hazard identification and assessment are usually the first steps of quantitative risk analysis (QRA) and is paramount to ensure its quality. Therefore, we here propose to use text mining and fine-tuned trained bidirectional encoder representations from transformers (BERT) models to support and reduce the efforts required for completing the early stages of QRA. Our idea is to apply these techniques to identify the potential consequences of accidents related to the operation of an oil refinery and classify each scenario in terms of severity of the consequence and likelihood of occurrence. The proposed method was applied to an actual oil refinery and presented very promising results. The potential consequences, the severity and likelihood categories were predicted with a mean accuracy of 97.42%, 86.44%, and 94.34% respectively. The models resulting from this research were embedded into a web-based app that is called HALO (hazard analysis based on language processing for oil refineries).