کد مقاله | کد نشریه | سال انتشار | مقاله انگلیسی | نسخه تمام متن |
---|---|---|---|---|
1710881 | 1519518 | 2016 | 11 صفحه PDF | دانلود رایگان |
• Simulation of the co-digestion of two agricultural substrates was performed.
• To predict the biogas flow rate the neural logic was employed.
• The optimisation was done with the help of metaheuristics, based on variable selection approach.
The aim of this study was to develop a fast and robust methodology to analyse the biogas production process. The Anaerobic Digestion Model No.1 was used to simulate the co-digestion of agricultural substrates. Neural network models were used to predict the biogas flow rate. With the help of the ant colony optimisation algorithm, the significant process variables were identified. Thus the model dimension was reduced and the model performance was improved. The achieved results showed that the approach gave a reliable way to analyse the biogas production process with respect to the significant process variables. This methodology could be further implemented to control the biogas production process and to manage the substrate composition.
Journal: Biosystems Engineering - Volume 143, March 2016, Pages 68–78