This paper explores the use of artificial neural networks （ANN） to predict performance, combustion and emissions of a single cylinder, four stroke stationary, diesel engine operated by thermal cracked cashew nut she...This paper explores the use of artificial neural networks （ANN） to predict performance, combustion and emissions of a single cylinder, four stroke stationary, diesel engine operated by thermal cracked cashew nut shell liquid （TC-CNSL） as the biodiesel blended with diesel. The tests were performed at three different injection timings （21°, 23°, 25℃A bTDC） by changing the thickness of the advance shim. The ANN was used to predict eight different engine-output responses, namely brake thermal efficiency （BTE）, brake specific fuel consumption （BSFC）, exhaust gas temperature （EGT）, carbon monoxide （CO）, oxide of nitrogen （NOx）, hydrocarbon （HC）, maximum pressure （Pm~,,） and heat release rate （HRR）. Four pertinent engine operating parameters, i.e., injection timing （IT）, injection pressure （IP）, blend percentage and pecentage load were used as the input parameters for this modeling work. The ANN results show that there is a good correlation between the ANN predicted values and the experimental values for various engine performances, combustion parameters and exhaust emission characteristics. The mean square error value （MSE） is 0.005621 and the regression value ofR2 is 0.99316 for training, 0.98812 for validation, 0.9841 for testing while the overall value is 0.99173. Thus the developed ANN model is fairly powerful for predicting the performance, combustion and exhaust emissions of internal combustion engines.展开更多
文摘This paper explores the use of artificial neural networks （ANN） to predict performance, combustion and emissions of a single cylinder, four stroke stationary, diesel engine operated by thermal cracked cashew nut shell liquid （TC-CNSL） as the biodiesel blended with diesel. The tests were performed at three different injection timings （21°, 23°, 25℃A bTDC） by changing the thickness of the advance shim. The ANN was used to predict eight different engine-output responses, namely brake thermal efficiency （BTE）, brake specific fuel consumption （BSFC）, exhaust gas temperature （EGT）, carbon monoxide （CO）, oxide of nitrogen （NOx）, hydrocarbon （HC）, maximum pressure （Pm~,,） and heat release rate （HRR）. Four pertinent engine operating parameters, i.e., injection timing （IT）, injection pressure （IP）, blend percentage and pecentage load were used as the input parameters for this modeling work. The ANN results show that there is a good correlation between the ANN predicted values and the experimental values for various engine performances, combustion parameters and exhaust emission characteristics. The mean square error value （MSE） is 0.005621 and the regression value ofR2 is 0.99316 for training, 0.98812 for validation, 0.9841 for testing while the overall value is 0.99173. Thus the developed ANN model is fairly powerful for predicting the performance, combustion and exhaust emissions of internal combustion engines.
