Predicting the heating value of MSW with a feed forward neural network

The influence of the heating value of municipal solid waste (MSW) is very important on the combustion efficiency of MSW incinerators. The heating value of MSW is determined by the elementary chemical composition of its various components. Commonly, calorimetric measurement and empirical methods are available for this determination. In this analysis, the relationship between the physical composition and the low heating value (LHV) was studied. A feed forward neural network (FFNN) can be very helpful in predicting the heating value of MSW from its physical composition. The results of this analysis show that the prediction of LHV of MSW with FFNN is much better than conventional models.