Predictive system for diesel vehicle fuel consumption using a decision tree and artificial neural networks

• Main Authors: Song, Di-En, 宋狄恩
• Other Authors: Wu, Jian-Da
• Format: Others
• Language: en_US
• Published: 2013
• Online Access: http://ndltd.ncl.edu.tw/handle/84431752714719327929

碩士 === 國立彰化師範大學 === 車輛科技研究所 === 101 === This study presents a system for the prediction of the fuel consumption of diesel vehicles using a decision tree and an artificial neural network. This system consists of three main parts: data acquisition, fuel consumption forecasting and performance analysis. During normal driving, the fuel consumption of a diesel vehicle is affected by many factors. However, using this system, the only factors that affect the fuel consumption are vehicle make, vehicle type, vehicle weight, vehicle type, transmission type, common-rail systems, turbocharging systems and transmission mode. In accordance with current fuel consumption norms, eight conditions are used as the system inputs for neural network training and fuel consumption prediction. In this study, the back-propagation neural network (BPNN), the radial basis function neural network (RBFNN), the generalized regression neural network (GRNN) and the classification and regression tree (CART) are used and compared, using the expert system, to predict the fuel consumption of diesel vehicles. The prediction results show that the neural network and the decision tree predictive system effectively predict the fuel consumption of diesel vehicles. The GRNN demonstrates better performance in terms of prediction time, but the CART demonstrates a better accuracy rate.