Design of Safety Zone and Optimal Risk Identification of Undesired Events During Loading and Unloading of LNG Terminal Using TSA-GEO: a Hybrid Strategy

Abstract

Liquefied natural gas (LNG) consumption is continuously rising in both developed and developing countries. Due to relatively cheap pricing and a large gas supply globally, most energy experts believe that major increases in LNG consumption are projected in the next decades. Many novel installations have been designed and are now implemented all over the globe in order to expand the usage of this resource. LNG is more prone to leakage when loading and unloading, thus putting the surrounding areas at greater risk of damage. Therefore, it is important to continue to improve current risk assessment strategies for dealing with safety. The objective of this work is to improve security by detecting failure patterns and minimizing problems. In this paper proposed a scheme to hybrid technique is combination of golden eagle optimizer (GEO) with tunicate swarm algorithm (TSA) and adaptive neuro fuzzy inference system (ANFIS) technique. This hybrid method is used because GEO-TSA detects leaks more accurately compared to other methods. The suggested hybrid technique-based risk assessment model may provide a fresh viewpoint on identifying leaks, hazards, and dangers, as well as assessing the development of LNG accidents from cause to effect. Furthermore, the suggested hybrid approach improves protection by detecting failure patterns and reducing issues. Finally, ANFIS is used as a reliable method for identifying risk, determining SIL rates and designing the safety zone. Predicting risk in overwork requires data on previous problems but not all data are available as all data vary from place to place. So the purpose of this job is to predict the risks from scratch without accurate data and not only that but also to anticipate the risks. This will reduce the risk of loss of life and property during periods of danger. In the proposed method is the implementation MATLAB/Simulink platform. The proposed method is comparable to methods such as particle swarm optimization (PSO) with fuzzy and whale optimization algorithm (WOA) with fuzzy.