The wavelet-based artificial neural network for state of charge estimation in lithium ion battery

Name: W. Phusakulkajorn

Organization : National Science and Technology Development Agency (NSTDA). National Metal and Materials Technology Center (MTEC)

Email : wassamon.phu@mtec.co.th

Name: C. Benyajati

Organization : National Science and Technology Development Agency (NSTDA). National Metal and Materials Technology Center (MTEC)

Name: T. Phraewphiphat

Organization : National Science and Technology Development Agency (NSTDA). National Metal and Materials Technology Center (MTEC)

Name: J. Mongkoltanatas

Organization : National Science and Technology Development Agency (NSTDA). National Metal and Materials Technology Center (MTEC)

keyword: State of Charge (SOC)

ThaSH: Neural networks (Computer science)

ThaSH: Lithium ion batteries

ThaSH: Electric automobiles -- Electric batteries

Abstract: State of charge (SOC) is described as the percentage of the amount of energy available in a battery to the maximum battery energy. It is one of battery parameters that play an important role in providing remaining driving range in electric vehicles with a long term benefit of preventing battery performance deterioration and accelerated ageing. Consequently, models with various approaches have been developed for SOC estimation. However, SOC estimation is very difficult to implement due to complex characteristics of a battery functioning by electrochemical reactions. Accurate SOC estimation requires detailed physical knowledge so that capacitive effects of a battery can be captured. To overcome those parametric uncertainties, a data-driven approach such as an artificial neural network is one strategy used. Therefore, it is the objective of this work to propose a technique that delivers a reliable SOC estimation. The back-propagation neural network was employed with the help of wavelet transformation. Battery current, battery voltage, temperature, and SOC at the previous time steps were considered as inputs to the network. Cylindrical Lithium-Ion batteries with a capacity of 2.6 Ah were used to obtain the experimental data. The results showed that the proposed method was numerically efficient and the obtained SOC estimation was consistent with the associated battery experiments.

King Mongkut's University of Technology North Bangkok. Central Library

Address: BANGKOK

Email: library@kmutnb.ac.th

Created: 2017

Modified: 2026-02-13

Issued: 2026-02-13

บทความ/Article

application/pdf

BibliograpyCitation : In King Mongkut's University of Technology North Bangkok Faculty of Engineering. The 8th TSME International Conference on Mechanical Engineering 2017 (TSME-ICoME8) (p.363-375) Bangkok : King Mongkut's University of Technology North Bangkok

eng

©copyrights King Mongkut's University of Technology North Bangkok

ลำดับที่.	ชื่อแฟ้มข้อมูล	ขนาดแฟ้มข้อมูล	จำนวนเข้าถึง	วัน-เวลาเข้าถึงล่าสุด
1	TSME-ICoME8 2017p.363-375.pdf	500.59 KB

ใช้เวลา

0.033854 วินาที