期刊
INTERNATIONAL CONFERENCE ON DESIGN AND MANUFACTURING (ICONDM2013)
卷 64, 期 -, 页码 993-1002出版社
ELSEVIER SCIENCE BV
DOI: 10.1016/j.proeng.2013.09.176
关键词
Low heat rejection engine; Biodiesel; Thermal barrier coatings; Lanthanum Zirconate; Artificial neural networks
Different techniques are being attempted over the years to use low pollution emitting fuels in diesel engines to reduce tail pipe emissions with improved engine efficiency. Especially. Biodiesel fuel, derived from different vegetable oils, animal fat and waste cooking oil has received a great attention in the recent past. Transesterification is a proven simplest process to prepare biodiesel in labs with little infrastructure. Application of thermal barrier coatings (TBC) on the engine components is a seriously perused area of interest with low grade fuels like biodiesel fuels. Artificial neural networks (ANN) are gaining popularity to predict the performance and emissions of diesel engines with fairly accurate results besides the thermodynamic models with considerably less complexity and lower computing time. In the present study, experiments have been conducted on a single cylinder diesel engine whose combustion elements are coated with an experimental thermal barrier coating material made from Lanthanum Zirconate.. Biodiesel has been prepared from Pongamia Pinnata oil through transesterification process. A series of experiments are conducted on the engine with and without thermal barrier coating using diesel and biodiesel fuels. Performance and emissions data from the experiments is used to train the network with the load, fuel type and coating being the input layer and the brake specific fuel consumption, brake thermal efficiency, CO, HC and NOx emissions being the output layer. Results showed that the coating of engine components with lanthanum zirconate TBC resulted in improved engine efficiency with reduced emissions. ANN model is tested for its accuracy to predict the performance and emissions of the engine with the R values of 0.99 for both the training and test data with a mean square error of 0.002 and a mean relative error of 6.8% (C) 2013 The Authors. Published by Elsevier Ltd.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据