Prediction of Biogas Yield from Codigestion of Lignocellulosic Biomass Using Adaptive Neuro-Fuzzy Inference System (ANFIS) Model

One of the major challenges confronting researchers is how to predict biogas yield because it a herculean task since research in field modeling and optimization still limited, especially with adaptive neuro-fuzzy inference system (ANFIS). This study used ANFIS model from anaerobic codigestion cow dung, mango pulp, Chromolaena odorata. Asides controls, 13 experiments using various agglomerates selected substrates were carried out. Cumulatively (for 40 days), agglomerate that comprised 50% 25% odorata produced highest volume biogas, 4750 m3/kg, while one 12.5% 37.5% lowest 630 m3/kg. The data articulated for those optimum yield. Data implemented two inputs (temperature Kelvin pressure kN/m2) output (biogas yield). Gaussian membership function (Gauss-mf) was fuzzification input variables, hybrid algorithm learning mapping input-output dataset. developed architecture simulated at varied functions, MFs, epoch numbers determine minimum root mean square error, RMSE, maximum R-squared R2 values. fulfilled conditions considered be optimized model. RMSE values recorded are 14.37 0.99784, respectively. implication able efficiently not less than 99.78% experimental data. These results prove reliable tool predicting biomass digestion process. Therefore, use recommended producers other allies adequately.