Maximizing Bio-Hydrogen Production from an Innovative Microbial Electrolysis Cell Using Artificial Intelligence

In this research work, the best operating conditions of microbial electrolysis cells (MECs) were identified using artificial intelligence and modern optimization. MECs are innovative materials that can be used for simultaneous wastewater treatment bio-hydrogen production. The main objective is maximization production during process by MECs. suggested strategy contains two stages: modelling optimal parameter identification. Firstly, adaptive neuro-Fuzzy inference system (ANFIS) modelling, an accurate model MES was created. Secondly, parameters determined jellyfish optimizer (JO). Three variables studied: incubation temperature (°C), initial potential hydrogen (pH), influent chemical oxygen demand (COD) concentration (%). Using some measured data points, ANFIS built simulating output MFC considering parameters. Afterward, a applied to determine temperature, pH, COD values. To demonstrate accuracy proposed strategy, comparison with previous approaches conducted. For stage, compared response surface methodology (RSM), coefficient determination increased from 0.8953 RSM 0.963 ANFIS, around 7.56%. addition, RMSE decreased 0.1924 (using RSM) 0.0302 whereas identification values 30.2 °C, 6.53, 59.98 (%), respectively, concentration. Under condition, maximum rate 1.252 m3H2/m3d. Therefore, successfully 1.1747 m3H2/m3d 1.253 6.7% RSM.