A Hazard Index for Chemical Logistic Warehouses with Modified Flammability Rating by Machine Learning Methods

摘要

With the rapid development of chemical processplants worldwide, the safe storage of hazardous chemicalscontinues to be an important topic. Chemical warehouse incidentsrelated to fire and explosion are reported constantly. Theseincidents not only cause direct economic loss but also harm thelocal environment. Therefore, an accurate hazard identificationmethod for a logistic warehouse is valuable since it can help peoplerecognize the potential hazard in the chemical storage area. In thisstudy, a storage hazard factor (SHF) was developed to evaluateand rank the inherent hazards of chemicals stored in logisticwarehouses. In the calculation of SHF, the National FireProtection Association (NFPA) hazard diamond was used toquantify the instability hazard; the U.S. Department of Energy’s Protective Action Criteria (PAC) values were utilized to modifychemical health hazard, and two machine learning based methods were used for the classification of flammability. The SHF andsafety penalty factors (e.g., quantity, population density) were then utilized to create a hazard index of the facilities. This index can beused not only for developing a proper emergency response plan but also for effectively communicating risk with the residents wholive near the facility. In addition, the index can be used by governments to allocate the resources better for first responders to makefire protection strategies, and by stakeholders to improve the risk management.