AI Article Synopsis
- The research aimed to create a model to assess airflow resistance through composted organic materials, specifically testing organic material under 80mm from municipal waste.
- The study varied key parameters like hydraulic load and airflow direction over 19 to 25 days while maintaining a consistent material humidity of around 45%.
- A neural network model (MLP/5-9-1) was chosen for its strong performance, indicated by a high correlation coefficient (0.906) and a range of standardized residuals (4.082 to 5.453).
Article Abstract
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 80mm separated from municipal waste. The range of process parameters values treated as independent variables was: for hydraulic load 8.49÷50.96m·m·h, thickening coefficient 0.69÷0.94 and airflow direction from the bottom upwards and vice versa. The research work lasting 19÷25days 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÷5.453).
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.scitotenv.2019.04.155 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!