DocumentCode :
2086824
Title :
Battery State-Of-Charge estimation in Electric Vehicle using Elman neural network method
Author :
Shi Qingsheng ; Zhang Chenghui ; Cui Naxin ; Zhang Xiaoping
Author_Institution :
Coll. of Electr. Eng., Henan Univ. of Technol., Zhengzhou, China
fYear :
2010
fDate :
29-31 July 2010
Firstpage :
5999
Lastpage :
6003
Abstract :
To accurately estimate the battery State-Of-Charge (SOC) during the Electric Vehicle driving process is an important problem, which urgently awaits to be solved. Elman neural network, which has good dynamic property, quick approximate rate and high prediction accuracy, is adopted to estimate battery SOC. First, the training data and the test data required in the estimation operation are collected using the ADVISOR software, which include the attributes, such as the battery current, voltage, required power and SOC. Then, to avoid attributes in greater numeric ranges dominate those in smaller numeric ranges and the numerical difficulties during the calculation, data scaling should be operated before applying the Elman neural network. Finally, compared to the BP neural network method, simulation experiments have been carried on. The results indicate that, under different drive cycles, using Elman neural network can more accurately approximate the actual SOC value and then obtain a better estimation performance.
Keywords :
electric vehicles; neural nets; secondary cells; ADVISOR software; Elman neural network method; battery state-of-charge estimation; electric vehicle; Artificial neural networks; Batteries; Brain modeling; Estimation; System-on-a-chip; Training data; Vehicle dynamics; BP Neural Network; Electric Vehicle; Elman Neural Network; State-Of-Charge;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Control Conference (CCC), 2010 29th Chinese
Conference_Location :
Beijing
Print_ISBN :
978-1-4244-6263-6
Type :
conf
Filename :
5572641
Link To Document :
بازگشت