On the exergetic optimization of continuous photobiological hydrogen production using hybrid ANFIS-NSGA-II (adaptive neuro-fuzzy inference system-non-dominated sorting genetic algorithm-II)

The aim of this work was to exergetically optimize the performance of a continuous photobioreactor for hydrogen production from syngas via water gas shift reaction by Rhodospirillum rubrum. To achieve this, a new multi-objective hybrid optimization technique was developed by coupling the elitist NSGA-II (non dominated sorting genetic algorithm) with the ANFIS (adaptive neuro-fuzzy inference system) to optimize the operational conditions of the photobioreactor. The syngas flow rate and culture agitation speed were independent variables, while rational and process exergy efficiencies as well as normalized exergy destruction were dependent variables. The ANFIS was used to establish an objective function for each dependent variable individually based on the independent variables. The developed ANFIS model was then utilized by the NSGA-II approach to find the optimal operating conditions simultaneously leading to the highest rational and process exergy efficiencies and the lowest normalized exergy destruction. Consequently, the best operating conditions for the photobioreactor were extracted using a Pareto optimal front set consisting of seven optimum points. Accordingly, syngas flow rate of 13.34 mL/min and culture agitation speed of 38333 rpm yielding process exergy efficiency of 21.66%, rational exergy efficiency of 85.64%, and normalized exergy destruction of 1.55 were found as the best operating conditions. (C) 2015 Elsevier Ltd. All rights reserved.