Fuzzy neural network genetic approach to design the SOC estimator for battery powered electric scooter

Yuang Shung Lee, Tsung Yuan Kuo, Wei-Yen Wang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

11 Citations (Scopus)

Abstract

This paper presents a new method for estimating the individual battery state-of-charge (SOC) of electric scooter (ES). The proposed method is to model ES batteries by using the fuzzy inference neural network system. A reduced form genetic algorithm (RGA) is employed to tune control point of the B-spline membership functions (BMFs) and the weightings of the fuzzy neural network (FNN). The proposed FNN with RGA (FNNRGA) optimization approach can achieve the faster learning rate and lower estimating error than the conventional gradient descent method. The validity of the SOC estimator is further verified by a constructed multiple input multiple output (MIMO) FNN structure for estimating the SOCs of battery powered ES. A fixed velocity discharging profiles of the ES batteries are investigated to train the FNN for precise estimating the SOCs of the battery strings. Furthermore, a testing data profile is used to demonstrate the superior robust and over-fitting suppressed performance of the proposed method. The estimated SOCs are directly compared with the actual SOCs under different FNN methods, verifying the accuracy and the effectiveness of the proposed intelligent modeling method.

Original languageEnglish
Title of host publication2004 IEEE 35th Annual Power Electronics Specialists Conference, PESC04
Pages2759-2765
Number of pages7
DOIs
Publication statusPublished - 2004 Nov 29
Event2004 IEEE 35th Annual Power Electronics Specialists Conference, PESC04 - Aachen, Germany
Duration: 2004 Jun 202004 Jun 25

Publication series

NamePESC Record - IEEE Annual Power Electronics Specialists Conference
Volume4
ISSN (Print)0275-9306

Other

Other2004 IEEE 35th Annual Power Electronics Specialists Conference, PESC04
CountryGermany
CityAachen
Period04/6/2004/6/25

Fingerprint

Fuzzy neural networks
Fuzzy Neural Network
estimators
Battery
electric batteries
Charge
Estimator
estimating
genetic algorithms
Genetic algorithms
Genetic Algorithm
Gradient Descent Method
B-spline Function
Learning Rate
Fuzzy Inference
Overfitting
spline functions
membership functions
Control Points
Fuzzy inference

ASJC Scopus subject areas

  • Modelling and Simulation
  • Condensed Matter Physics
  • Energy Engineering and Power Technology
  • Electrical and Electronic Engineering

Cite this

Lee, Y. S., Kuo, T. Y., & Wang, W-Y. (2004). Fuzzy neural network genetic approach to design the SOC estimator for battery powered electric scooter. In 2004 IEEE 35th Annual Power Electronics Specialists Conference, PESC04 (pp. 2759-2765). (PESC Record - IEEE Annual Power Electronics Specialists Conference; Vol. 4). https://doi.org/10.1109/PESC.2004.1355270

Fuzzy neural network genetic approach to design the SOC estimator for battery powered electric scooter. / Lee, Yuang Shung; Kuo, Tsung Yuan; Wang, Wei-Yen.

2004 IEEE 35th Annual Power Electronics Specialists Conference, PESC04. 2004. p. 2759-2765 (PESC Record - IEEE Annual Power Electronics Specialists Conference; Vol. 4).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Lee, YS, Kuo, TY & Wang, W-Y 2004, Fuzzy neural network genetic approach to design the SOC estimator for battery powered electric scooter. in 2004 IEEE 35th Annual Power Electronics Specialists Conference, PESC04. PESC Record - IEEE Annual Power Electronics Specialists Conference, vol. 4, pp. 2759-2765, 2004 IEEE 35th Annual Power Electronics Specialists Conference, PESC04, Aachen, Germany, 04/6/20. https://doi.org/10.1109/PESC.2004.1355270
Lee YS, Kuo TY, Wang W-Y. Fuzzy neural network genetic approach to design the SOC estimator for battery powered electric scooter. In 2004 IEEE 35th Annual Power Electronics Specialists Conference, PESC04. 2004. p. 2759-2765. (PESC Record - IEEE Annual Power Electronics Specialists Conference). https://doi.org/10.1109/PESC.2004.1355270
Lee, Yuang Shung ; Kuo, Tsung Yuan ; Wang, Wei-Yen. / Fuzzy neural network genetic approach to design the SOC estimator for battery powered electric scooter. 2004 IEEE 35th Annual Power Electronics Specialists Conference, PESC04. 2004. pp. 2759-2765 (PESC Record - IEEE Annual Power Electronics Specialists Conference).
@inproceedings{e0d9448318c44dc0bf38d79bef7752cb,
title = "Fuzzy neural network genetic approach to design the SOC estimator for battery powered electric scooter",
abstract = "This paper presents a new method for estimating the individual battery state-of-charge (SOC) of electric scooter (ES). The proposed method is to model ES batteries by using the fuzzy inference neural network system. A reduced form genetic algorithm (RGA) is employed to tune control point of the B-spline membership functions (BMFs) and the weightings of the fuzzy neural network (FNN). The proposed FNN with RGA (FNNRGA) optimization approach can achieve the faster learning rate and lower estimating error than the conventional gradient descent method. The validity of the SOC estimator is further verified by a constructed multiple input multiple output (MIMO) FNN structure for estimating the SOCs of battery powered ES. A fixed velocity discharging profiles of the ES batteries are investigated to train the FNN for precise estimating the SOCs of the battery strings. Furthermore, a testing data profile is used to demonstrate the superior robust and over-fitting suppressed performance of the proposed method. The estimated SOCs are directly compared with the actual SOCs under different FNN methods, verifying the accuracy and the effectiveness of the proposed intelligent modeling method.",
author = "Lee, {Yuang Shung} and Kuo, {Tsung Yuan} and Wei-Yen Wang",
year = "2004",
month = "11",
day = "29",
doi = "10.1109/PESC.2004.1355270",
language = "English",
isbn = "0780383990",
series = "PESC Record - IEEE Annual Power Electronics Specialists Conference",
pages = "2759--2765",
booktitle = "2004 IEEE 35th Annual Power Electronics Specialists Conference, PESC04",

}

TY - GEN

T1 - Fuzzy neural network genetic approach to design the SOC estimator for battery powered electric scooter

AU - Lee, Yuang Shung

AU - Kuo, Tsung Yuan

AU - Wang, Wei-Yen

PY - 2004/11/29

Y1 - 2004/11/29

N2 - This paper presents a new method for estimating the individual battery state-of-charge (SOC) of electric scooter (ES). The proposed method is to model ES batteries by using the fuzzy inference neural network system. A reduced form genetic algorithm (RGA) is employed to tune control point of the B-spline membership functions (BMFs) and the weightings of the fuzzy neural network (FNN). The proposed FNN with RGA (FNNRGA) optimization approach can achieve the faster learning rate and lower estimating error than the conventional gradient descent method. The validity of the SOC estimator is further verified by a constructed multiple input multiple output (MIMO) FNN structure for estimating the SOCs of battery powered ES. A fixed velocity discharging profiles of the ES batteries are investigated to train the FNN for precise estimating the SOCs of the battery strings. Furthermore, a testing data profile is used to demonstrate the superior robust and over-fitting suppressed performance of the proposed method. The estimated SOCs are directly compared with the actual SOCs under different FNN methods, verifying the accuracy and the effectiveness of the proposed intelligent modeling method.

AB - This paper presents a new method for estimating the individual battery state-of-charge (SOC) of electric scooter (ES). The proposed method is to model ES batteries by using the fuzzy inference neural network system. A reduced form genetic algorithm (RGA) is employed to tune control point of the B-spline membership functions (BMFs) and the weightings of the fuzzy neural network (FNN). The proposed FNN with RGA (FNNRGA) optimization approach can achieve the faster learning rate and lower estimating error than the conventional gradient descent method. The validity of the SOC estimator is further verified by a constructed multiple input multiple output (MIMO) FNN structure for estimating the SOCs of battery powered ES. A fixed velocity discharging profiles of the ES batteries are investigated to train the FNN for precise estimating the SOCs of the battery strings. Furthermore, a testing data profile is used to demonstrate the superior robust and over-fitting suppressed performance of the proposed method. The estimated SOCs are directly compared with the actual SOCs under different FNN methods, verifying the accuracy and the effectiveness of the proposed intelligent modeling method.

UR - http://www.scopus.com/inward/record.url?scp=8744241487&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=8744241487&partnerID=8YFLogxK

U2 - 10.1109/PESC.2004.1355270

DO - 10.1109/PESC.2004.1355270

M3 - Conference contribution

SN - 0780383990

T3 - PESC Record - IEEE Annual Power Electronics Specialists Conference

SP - 2759

EP - 2765

BT - 2004 IEEE 35th Annual Power Electronics Specialists Conference, PESC04

ER -