| Classification of biogas digesters based on their substrate using biogas patterns and machine learning (a case study on livestock manures of cow and chicken) |
| Paper ID : 1431-NICAME1402 |
| Authors: |
|
Ehsan Savand-Roumi1, seyed saeid Mohtasebi *2 1Department of Agricultural Machinery Engineering, Faculty of Agricultural Engineering and Technology, University College of Agriculture and Natural Resources, University of Tehran, Karaj, Iran 2university of Tehran |
| Abstract: |
| Agricultural waste management in the right way can contribute to saving energy and recycling valuable organic material, but unfortunately, agro-waste is a main source of environmental pollution. Livestock manure is a large portion of agricultural waste that can be treated through anaerobic digestion (AD) as sustainable waste management. As waste type is an important factor in the AD process, this study focuses on the potential of classifying the biogas patterns of cow and chicken manures as substrates using e-nose. The batch digesters were fed by three substrates including cow manure, chicken manure, and a combination of them in a 1:1 ratio. The digesters of chicken manure and the combination produced high biogas on the first day but declined the production rate by over days and failed less than 9 days. The digesters of cow manure produced biogas at a stable rate for more than 11 days. The biogas patterns were introduced to PCA and LDA. PCA plot showed that the Mq-136 sensor, which is high sensitivity to H2S and NH4, was the most effective sensor to separate the digesters. The confusion matrix of the PCA-LDA model showed an overall classification accuracy of 77.6% with P value: 0.00001, and recall of 100% for the classifier of the digesters of chicken manure. Also, the biogas patterns were classified by different algorithms and validated by the k-fold cross-validation method. The SVM model presented the best accuracy of 75.9% by 5-fold cross-validation. |
| Keywords: |
| biogas, digester, cow manure, chicken manure, e-nose, classification, k-fold |
| Status : Paper Accepted (Poster Presentation) |
