Artificial bee colony Based Bayesian Regularization Artificial Neural Network approach to model transient flammable cloud dispersion in congested area

摘要

Recently, the Bayesian Regularization Artificial Neural Network (BRANN) approach has been used for flammable cloud estimation in a congested offshore setting. These authors observed that BRANN exhibits lower accuracy under specific release and dispersion scenarios. To improve BRANN's accuracy and robustness, the authors have proposed the integration of the Artificial Bee Colony (ABC) algorithm with the BRANN approach. The new ABC-BRANN approach is tested for a wide range of scenarios. The performance of ABC-BRANN approach is compared with the Particle Swarm Optimization (PSO)-BRANN and BRANN approach. The results demonstrate the proposed ABC-BRANN approach is more accurate and robust. It provides an effective alternative for transient dispersion study in congested areas such as an offshore platform. (C) 2019 Institution of Chemical Engineers. Published by Elsevier B.V. All rights reserved.