期刊名称：International Journal of Advanced Research In Computer Science and Software Engineering
印刷版ISSN：2277-6451
电子版ISSN：2277-128X
出版年度：2013
卷号：3
期号：8
出版社：S.S. Mishra
摘要：The experimental determination of various properties of diesel-biodiesel mixtures is very time consuming as well as tedious process. The aim of the present work is to model the vibration characteristics of DI diesel engine using neural networks with mahuwa oil as biodiesel. An Artificial neural network (ANN) model based on the Back-Propagation algorithm is developed for vibration analysis. The data obtained during the experimental process is used to develop the ANN model. The experimental data obtained for the better performance combination of 20 % blend of Mahuwa oil (B20) with 15% hot and 20% cooled exhaust gas recirculation (EGR) and without EGR is used for modelling . Multilayer perceptron neural network with suitable architecture was used for nonlinear mapping between input and output parameters of ANN. Brake power, exhaust gas temperature, brake thermal efficiency, specific fuel consumption and cetane value of diesel and B20 blend of 15% hot and 20 % cooled EGR levels were used as input parameters to train the network using suitable activation functions. The output parameters to be predicted are vibration in various engine parts like the head, bottom and crank of the engine. The results showed that training through back propagation was sufficient enough in predicting the engine vibration. It was found that R (Regression Coefficient) values were 0.97, 0.95 and 0.94 for vibration measured in the head, bottom and crank of the engine respectively. The developed model can be used as a tool for estimating the vibration in the head, bottom and crank of the engine using diesel and biodiesel blends under varying operating conditions
关键词：Vibration; IC Engine; Biodiesel; Artificial neural network
