Forecast of lower heating value of municipal solid waste via adaptive neuro-fuzzy inference system

Abstract

The rapid increment of world population and modern civilization have been causing to increase the amount of municipal solid waste (MSW) every year. In addition to emitting disturbing odor, the MSW poses great risks to the environment and human health, and requires an efficient utilization. Before evaluating MSW in any application, determining the energy content is critical for process efficiency. However, ingredients of MSW varies considerably and is influenced by the socio-economic conditions of the urban area. Therefore, in this study, the lower heating value (LHV) of MSW is calculated via adaptive neuro-fuzzy inference system (ANFIS) that is an advanced artificial intelligence method. Food, paper, plastic, wood, textile, and moisture content of MSW were assigned as input parameters. The LHV of MSW can be easily calculated via the newly developed ANFIS model without the need for any experimental procedure.