Title :
Estimation of power battery SOC based on improved BP neural network
Author :
Chao Dong ; Guanlan Wang
Author_Institution :
Tianjin Key Lab. of Control Theor. & Applic. in Complicated Syst., Tianjin Univ. of Technol., Tianjin, China
Abstract :
According to the limitations and shortcomings of BP neural network in estimating the battery state of charge(State of Charge, SOC), such as slow convergence speed and poor generalization, this paper puts forward an improved BP neural network method of battery SOC estimation. Train the improved BP neural network with the experimental data. It compares the trained neural network of SOC with the real values, and uses Matlab to simulate in order to verify the correctness of the algorithm.
Keywords :
backpropagation; battery powered vehicles; neural nets; power engineering computing; secondary cells; BP neural network method; Matlab; battery state of charge; convergence speed; electric vehicles; lithium-ion battery; power battery SOC estimation; Algorithm design and analysis; Batteries; Biological neural networks; Genetic algorithms; System-on-chip; Training; BP neural network; SOC; power battery;
Conference_Titel :
Mechatronics and Automation (ICMA), 2014 IEEE International Conference on
Conference_Location :
Tianjin
Print_ISBN :
978-1-4799-3978-7
DOI :
10.1109/ICMA.2014.6886014