Simplified Least Squares - Support Vector Machines for Lead-Acid Batteries SOC Estimation

Li Chuan Zheng; Li Xue Li; Yi Hui Zheng; Xin Wang; Jian Ming Zhao; Hong Tao Chen

doi:10.4028/www.scientific.net/AMM.672-674.680

Paper Titles

Preparation of Pd-Cu-Ce Hydrogen Separation Membrane Alloys
p.661

Pyrolysis of Hailar Lignite: Experiments with a Tubular Reactor and a Continuous Screw Kiln Reactor
p.665

Research on the Microwave Pyrolysis of Coal under N₂ Atmosphere
p.672

Research Progress on Polyoxymethylene Dimethyl Ethers as the Additive Component of Diesel Fuel
p.676

Simplified Least Squares - Support Vector Machines for Lead-Acid Batteries SOC Estimation
p.680

Study on Synthesis of Alkynoxymethyl Benzyl Quaternary Ammonium Salt and its Corrosion Inhibition for Blast Furnace Gas Pipeline
p.684

Study on Synthesis of Polycarboxylate Superplasticizer at Room Temperature
p.688

Synthesis of La_1-xSr_xGa_1-yMg_y-zM_zO_3−δ (M=Cr, Mn, Fe, Ni, Co) Electrolyte for IT-SOFCs by Laser Rapid Sintering
p.691

Synthesis, Electrical Conductivity and Electrochemical Properties of SrFe₁₋_xSb_xO₃₋_δ as Cathode Materials for IT-SOFCs
p.696

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 672-674Simplified Least Squares - Support Vector Machines...

Simplified Least Squares - Support Vector Machines for Lead-Acid Batteries SOC Estimation

Abstract:

Lead-acid batteries are widely used in all walks of life, the State-of-Charge is the most important part of the battery management system. On account of the strong coupling, multivariable, nonlinear characteristics of the batteries, this paper adopts the LS-SVM method to predict remaining battery capacity. The nonlinear POLYnomial (POLY) kernel is employed to design the LS-SVM. Aiming at predigesting the hardware requirement of the LS-SVM application, this paper uses the deduced induction of the input vector to simplify the POLY kernel, greatly reducing the memory capacity of the practical application. At last, simulation on MATLAB was done to verify the validity of the proposed model, the simulation results show that the LS-SVM based on the simplified PLOY kernel is applicable to battery SOC estimation, and the estimation error can be controlled within 5%.

You might also be interested in these eBooks

Renewable Energy and Power Technology II

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 672-674)

Pages:

680-683

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.672-674.680

Citation:

Cite this paper

Online since:

October 2014

Authors:

Li Chuan Zheng, Li Xue Li, Yi Hui Zheng*, Xin Wang, Jian Ming Zhao, Hong Tao Chen

Keywords:

Ls-SVM, POLY Kernel, SoC, SVM

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] K.K. Cadirci, Y.C. Ozkazanc and Y.S. Cadirci: IEEE Transactions on Industrial Electronics, Vol. 52(2005), p.1315.

Google Scholar

[2] J.J. Sun: Research on the VRLA battery online testing and fault prediction algorithm [D]. Shandong University(in Chinese), (2007).

Google Scholar

[3] C.H. Liang: Hybrid vehicles remaining battery capacity prediction [D]. Jilin University(in Chinese), (2006).

Google Scholar

[4] R. Xiong, H.W. He, F.C. Sun and K. Zhao: IEEE Transactions on Vehicular Technology, Vol. 62( 2013), p.108.

Google Scholar

[5] C.H. Cai, D. Du, Z.Y. Liu and J.T. Ge: IEEE Conference on Neural Information Processing, Vol. 2 ( 2002) pp.18-22.

Google Scholar

[6] H.X. Lu: IEEE Conference on Intelligent Systems Design and Applications , Vol. 1( 2006) p.137.

Google Scholar