Promoting excellence in mobility engineering

  1. FISITA Store
  2. Technical Papers

Driving Range Accuracy through Redial Basis Function (RBF)
FISITA2016/F2016-APSI-002

Authors

Listed in main paper

Abstract

Research and/or Engineering Question/Objective

As pure electric vehicle driving range directly is affected by the impact of road conditions, weather, travel conditions and other factors. Preventing pure electric vehicles broke down due to lack of power or other anomalies, timely Estimated driving range during the pure electric vehicle running is a very important task.

Methodology

The method processing data collection through normalization and standardization, the use of RBF neural network design, determine the input layer, a hidden layer and output layer, with K-means clustering analysis method as the RBF neural network learning algorithm, the final data anti-normalization and de-normalization process to obtain driving range of electric vehicles predicted value.

Results

By the use of RBF (Redial Basis Function) Neural Network, when the vehicle running , driving range estimated in the whole period of time could be remained a high degree of accuracy.

Limitations of this study

Due to the limited nature of data collection, estimates may be not accurate

What does the paper offer that is new in the field including in comparison to other work by the authors?

The analysis with RBF (Redial Basis Function) Neural Network in this paper is new as well the resulting which is unloaded to central sever.

Conclusions

By the use of RBF (Redial Basis Function) Neural Network, when the vehicle running , driving range estimated in the whole period of time could be remained a high degree of accuracy.

Key words : DTE ,electric vehicles ,RBF(Redial Basis Function) neural network

Add to basket