Dhande, D. Y.
Evaluation of emission characteristics and performance of pomegranate ethanol blended S. I. Engine using artificial neural network and rule learner classifier - Vol.103(2), June - New York Springer 2022 - 453-466p.
Waste pomegranate fruit is one of the new sources of ethanol. Using four different ethanol mixes, the emission performance of S.I. engine was measured at varied running speeds. Ethanol mixed gasoline enhances the quality of engine exhaust emissions, except for nitrogen oxides. Engine performance was found optimum using a 15% ethanol blend and a 1500 rpm speed. The emission characteristics were further examined using artificial neural network and rule learner classifiers. Experiments yielded data sets in which emission characteristics of engines were mapped in relation to engine speed and ethanol/petrol mixtures. These datasets were utilised to train artificial neural networks and rule learner classifiers to establish relationships among emission characteristics, speeds, and ethanol combinations. Both models were tested, and the rule learner classifier was found to be more accurate than the artificial neural network. Emission characteristics, speed, and ethanol combinations can all be correlated using the proposed rule learner algorithm.
Humanities and Applied Sciences
Evaluation of emission characteristics and performance of pomegranate ethanol blended S. I. Engine using artificial neural network and rule learner classifier - Vol.103(2), June - New York Springer 2022 - 453-466p.
Waste pomegranate fruit is one of the new sources of ethanol. Using four different ethanol mixes, the emission performance of S.I. engine was measured at varied running speeds. Ethanol mixed gasoline enhances the quality of engine exhaust emissions, except for nitrogen oxides. Engine performance was found optimum using a 15% ethanol blend and a 1500 rpm speed. The emission characteristics were further examined using artificial neural network and rule learner classifiers. Experiments yielded data sets in which emission characteristics of engines were mapped in relation to engine speed and ethanol/petrol mixtures. These datasets were utilised to train artificial neural networks and rule learner classifiers to establish relationships among emission characteristics, speeds, and ethanol combinations. Both models were tested, and the rule learner classifier was found to be more accurate than the artificial neural network. Emission characteristics, speed, and ethanol combinations can all be correlated using the proposed rule learner algorithm.
Humanities and Applied Sciences