Pyrolysis products from industrial waste biomass based on a neural network model

Pyrolysis of pine sawdust, a typical industrial biomass waste, was studied. The effects of operating temperature, biomass particle size, and space velocity on the products of biomass pyrolysis were investigated. A three-layer artificial neural network (ANN) model was developed and trained to simulate and predict the selectivity and yield of gas products. Good agreement was achieved between the experimental and simulated results. The major gas products of biomass pyrolysis are CO, CO2, H-2, and CH4. The ANN model showed that the major gas products depended mainly on the temperature, and the total selectivity of CO, CO2, H-2, and CH4 increased from 2.91% at 300 degrees C to 34.31% at 900 degrees C. The selectivity of main gas products increased with increasing space velocity. When the space velocity increased from 45 min(-1) to 85 min(-1), the selectivity of major gas products increased from 29.12% to 34.03%. Within the sample particle size range from 0.1 to 1.7 mm, there was no significant difference in the selectivity of major gas products. The pyrolysis temperature also influenced the composition of the tar in the biomass pyrolysis product. In the temperature range investigated, the benzene composition was favored at lower temperatures, such as 400 degrees C, however, the light-weight PAHs were preferably generated at higher temperatures above 600 degrees C. (C) 2016 Elsevier B.V. All rights reserved.