Prediction of hemicellulose content of biomass by means of adaptive neuro-fuzzy inference system

Abstract

It has become a global responsibility to reduce the damage of fossil fuels on the environment and human health, such as greenhouse gas emissions, particulate matter emissions, formation of harmful gases like SOx and NOx, etc. On the other hand, biomass proves to be a sustainable solution as it is carbon neutral, cheaply available in various forms, and is a renewable fuel. Although biomasses have various compounds, their organic structures are mainly composed of three biopolymers: Hemicellulose, Cellulose, and Lignin. Hemicellulose is an essential component of plant cell walls and consists of glucose along with several water-soluble sugars. Hemicellulose is converted into various forms of biorenewable chemicals, pharmaceuticals, fuels, and other materials in industrial applications. Therefore, determining the amount of hemicellulose in biomass is valuable in determining fuel efficiency. In this paper, the hemicellulose content of biomass is predicted using an adaptive neuro-fuzzy inference system (ANFIS) which uses the results of biomass proximity analysis. The results demonstrated that the ANFIS model can be operated effortlessly in hemicellulose prediction.