Applications of ANFIS-Type Methods in Simulation of Systems in Marine Environments

ANFIS-type algorithms have been used in various modeling and simulation problems. With the help of with more accuracy adaptability, it is possible to obtain better real-life emulating models. A critical environmental problem discharge saline industrial effluents form buoyant jets into water bodies. Given potentially harmful effects from desalination plants on marine environment coastal ecosystem, minimizing such an effect crucial. Hence, important design outfall system properly reduce these impacts. To best authors’ knowledge, a study that formulates effluent find optimum numerical model under conditions considered here using AI methods has not completed before. In this study, submerged discharges, specifically, negatively are modeled. The objective compare artificial intelligence along multivariate regression models fit determine less computational time. This achieved by training testing Adaptive Neuro-Fuzzy Inference System (ANFIS), ANFIS-Genetic Algorithm (GA), ANFIS-Particle Swarm Optimization (PSO) ANFIS-Firefly (FFA) input parameters, which obtained realizable k-ε turbulence model, simulated after turbulent jet OpenFOAM platform. comparison outputs algorithms’ conducted study. Statistical parameters as least error, coefficient determination (R2), Mean Absolute Error (MAE), Average Deviation (AED) measured evaluate performance work, found ANFIS-PSO performs compared other four model. It shown provides R2, MAE, AED, however, non-hybrid ANFIS reasonably acceptable results lower costs. demonstrate error 6.908% best-case scenario