Management of higher heating value sensitivity of biomass by hybrid learning technique

Recently, biomass sources are important for energy applications. Therefore, there is need for analyzing the biomass model based on different components such as carbon, ash, and moisture content. Since the biomass modeling could be very challenging task for conventional mathematical, it is suitable to apply soft computing models which could overcome the nonlinearities of the process. The main attempt in the study was to develop a soft computing model for the prediction of the higher heating values of biomass based on the proximate analysis. Adaptive neuro-fuzzy inference system (ANFIS) was used as soft computing methodology. According to the prediction accuracy of the higher heating value of the biomass, the inputs’ influence was determined on the higher heating value. According to the obtained results, fixed carbon has a correlation coefficient of 0.7644, the volatile matter has a correlation coefficient of 0.7225, and ash has a correlation coefficient of 0.9317. Therefore, the ash percentage weight has the highest relevance on the higher heating value of the biomass. On the contrary, the volatile matter has the smallest relevance on the higher heating value of the biomass.