Journal
SCIENCE OF THE TOTAL ENVIRONMENT
Volume 674, Issue -, Pages 19-25Publisher
ELSEVIER
DOI: 10.1016/j.scitotenv.2019.04.155
Keywords
Neural network; Composting; Airflow; Pressure drop
Categories
Ask authors/readers for more resources
The objective of our research work was to develop a model that could be used to determine resistance of air flow through a bed of organic material processed in composting operation. The raw material used for testing was organic fraction below 80 mm separated from municipal waste. The range of process parameters values treated as independent variables was: for hydraulic load 8.49 divided by 50.96 m(3).m(-2).h(-1), thickening coefficient 0.69 divided by 0.94 and airflow direction from the bottom upwards and vice versa. The research work lasting 19 divided by 25 days was performed in three independent series varying in the bed height. Material humidity was maintained at a constant level of approx. 45%. Analysis of simulation results allowed for selection of MLP/5-9-1 neural network. High quality of such obtained neural network was confirmed by statistical evaluation indicators represented by a coefficient of correlation between the forecast and real values (0.906) and the range of standardized rests of the forecast results (4.082 divided by 5.453). (C) 2019 Published by Elsevier B.V.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available