Modelling Energy Content Of Municipal Solid Waste Using Artificial Neural Network

The application of artificial neural network on energy modeling needs to be researched more extensively in order to appreciate and fulfill the potential of this modeling approach. The estimation of lower heating value is required to know the actual available energy to be converted to heat or electricity. In this study, a feed forward artificial neural network, trained by error back propagation algorithm was used to predict the lower heating value of municipal solid waste. Plastic, paper, glass, textile and food were found to be essential for prediction of lower heating value of municipal solid waste. The lower heating value has strong relationship with plastic, paper, glass, textile and food. Using 60 dataset divided into 37 training dataset and 23 validating dataset, gathered from Abuja waste stream, artificial neural network was trained and validated. The efficiency and accuracy of the artificial neural network was measured based on absolute average error and determination coefficient. The artificial neural network produced results with an absolute average percentage error less than 9.13% and 9.4% for training and validating dataset, respectively, when compared to measured data. The model provided the best fit and the predicted trend followed the observed data closely; the determination coefficient for training and validating dataset were 0.992 and 0.981, respectively. These results show that artificial neural network is an effective tool in forecasting energy content.

Keywords
Neural networks, Municipal solid waste, Lower heating value, Artificial neural networks, Energy content