An Artificial Neural Network Based Method for Explosion Risk Analysis of Floating Offshore Platform

This study aims to introduce the Artificial Neuron Network (ANN) technique, namely Bayesian Regularization Artificial Neuron Network (BRANN) to Explosion Risk Analysis (ERA) of floating offshore platform and eventually develop the ANN-based ERA procedure. In order to verify the feasibility of this developed procedure, a case study of floating offshore platform is conducted. Firstly, several dispersion simulations and explosion simulations are performed by FLACS. With those simulation results, the corresponding BRANN models are subsequently developed. Furthermore, comparison between BRANN model and widely-used RSM model is conducted. Eventually, the exceedance curve of maximum overpressure is determined. All the results illustrate the more robustness and efficiency of this developed procedure.