Environmental Risk Assessment Using Neural Network in Liquefied Petroleum Gas Terminal

Abstract

The accidental release of toxic gases leads to fire, explosion, and acute toxicity, and may result in severe problems for people and the environment. The risk analysis of hazardous chemicals using consequence modelling is essential to improve the process reliability and safety of the liquefied petroleum gas (LPG) terminal. The previous researchers focused on single-mode failure for risk assessment. No study exists on LPG plant multimode risk analysis and threat zone prediction using machine learning. This study aims to evaluate the fire and explosion hazard potential of one of Asia’s biggest LPG terminals in India. Areal locations of hazardous atmospheres (ALOHA) software simulations are used to generate threat zones for the worst scenarios. The same dataset is used to develop the artificial neural network (ANN) prediction model. The threats of flammable vapour cloud, thermal radiations from fire, and overpressure blast waves are estimated in two different weather conditions. A total of 14 LPG leak scenarios involving a 19 kg capacity cylinder, 21 tons capacity tank truck, 600 tons capacity mounded bullet, and 1350 tons capacity Horton sphere in the terminal are considered. Amongst all scenarios, the catastrophic rupture of the Horton sphere of 1350 MT capacity presented the most significant risk to life safety. Thermal flux of 37.5 kW/ m2 from flames will damage nearby structures and equipment and spread fire by the domino effect. A novel soft computing technique called a threat and risk analysis-based ANN model has been developed to predict threat zone distances for LPG leaks. Based on the significance of incidents in the LPG terminal, 160 attributes were collected for the ANN modelling. The developed ANN model predicted the threat zone distance with an accuracy of R2 value being 0.9958, and MSE being 202.9061 in testing. These results are evident in the reliability of the proposed framework for safety distance prediction. The LPG plant authorities can adopt this model to assess the safety distance from the hazardous chemical explosion based on the prior forecasted atmosphere conditions from the weather department.

Development of a Data-Based Machine Learning Model for Classifying and Predicting Property Damage Caused by Fire

“…The activation function converts the sum of the weight values into an output signal and transmits the related information to the next layer [17]. Examples that use this technique can be found in [18][19][20][21].…”

Dynamic Process and Damage Evaluation Subject to Explosion Consequences Resulting from a LPG Tank Trailer Accident

“…where R 0 is certain range between the explosion source and involved site, m. The previous studies [35,36] have proposed the relationships between the shock wave and distance, which are based on large-scale experiment data and CFD method of the similarity theories. From Equations ( 9) and (10), it can be combined with the TNT equivalence method to determine the shock wave and its propagation range caused by the LPG tank trailer explosion.…”

“…LPG expansion near the ground occurs along the gaps between structural congestions, while continuous large-scale congestion has a significant enhancement effect on LPG expansion and concentration accumulation [8]. LPG tanks are exposed to fires for research to support the prevention of catastrophic scenarios [9][10][11]. It is of great importance to analyze the flame and overpressure caused by LPG/air explosion, and mainly study the coupling relationship among the flame structures and propagation [12].…”

Gas-Sensing Properties and Mechanisms of 3D Networks Composed of ZnO Tetrapod Micro-Nano Structures at Room Temperature

“…Air pollution, which has a serious impact on both ecosystems and human health, is increasingly becoming a pressing global issue alongside water and soil pollution [ 1 , 2 , 3 ]. Furthermore, gas leaks and explosions are also prevalent in both production and daily life [ 4 , 5 , 6 ]. For the sake of environmental protection, production safety, and public health, it is crucial to develop highly sensitive methods for detecting toxic, harmful, flammable, and explosive gases or volatile organic compounds (VOCs) [ 7 , 8 , 9 ].…”