Gasification characteristics of MSW and an ANN prediction model

Gasification characteristics make up the important parts of municipal solid waste (MSW) gasification and melting technology. These characteristics are closely related to the composition of MSW, which alters with climates and seasons. It is important to find a practical way to predict gasification characteristics. In this paper, five typical kinds of organic components (wood, paper, kitchen garbage, plastic, and textile) and three representative types of simulated MSW are gasified in a fluidized-bed at 400–800 °C with the equivalence ratio (ER) in the range of 0.2–0.6. The lower heating value (LHV) of gas, gasification products, and gas yield are reported. The results indicate that gasification characteristics are different from sample to sample. Based on the experimental data, an artificial neural networks (ANN) model is developed to predict gasification characteristics. The training and validating relative errors are within ±15% and ±20%, respectively, and predicting relative errors of an industrial sample are below ±25%. This indicates that it is acceptable to predict gasification characteristics via ANN model.