A merged fuzzy neural network and its applications in battery state-of-charge estimation

I. Hum Li, Wei Yen Wang, Shun Feng Su, Yuang Shung Lee

Research output: Contribution to journalArticle

112 Citations (Scopus)

Abstract

To solve learning problems with vast number of inputs, this paper proposes a novel learning structure merging a number of small fuzzy neural networks (FNNs) into a hierarchical learning structure called a merged-FNN. In this paper, the merged-FNN is proved to be a universal approximator. This computing approach uses a fusion of FNNs using B-spline membership functions (BMFs) with a reduced-form genetic algorithm (RGA). RGA is employed to tune all free parameters of the merged-FNN, including both the control points of the BMFs and the weights of the small FNNs. The merged-FNN can approximate a continuous nonlinear function to any desired degree of accuracy. For a practical application, a battery state-of-charge (BSOC) estimator, which is a twelve input, one output system, in a lithium-ion battery string is proposed to verify the effectiveness of the merged-FNN. From experimental results, the learning ability of the newly proposed merged-FNN with RGA is superior to that of the traditional neural networks with back-propagation learning.

Original languageEnglish
Pages (from-to)697-708
Number of pages12
JournalIEEE Transactions on Energy Conversion
Volume22
Issue number3
DOIs
Publication statusPublished - 2007 Sep 1

Fingerprint

Fuzzy neural networks
Genetic algorithms
Membership functions
Splines
Backpropagation
Merging
Fusion reactions
Neural networks

Keywords

  • B-spline membership functions (BMFs)
  • Battery state-of-charge (BSOC)
  • Battery string
  • Fuzzy neural networks (FNNs)
  • Merged-FNN
  • Reduced-form genetic algorithm (RGA)

ASJC Scopus subject areas

  • Energy Engineering and Power Technology
  • Electrical and Electronic Engineering

Cite this

A merged fuzzy neural network and its applications in battery state-of-charge estimation. / Li, I. Hum; Wang, Wei Yen; Su, Shun Feng; Lee, Yuang Shung.

In: IEEE Transactions on Energy Conversion, Vol. 22, No. 3, 01.09.2007, p. 697-708.

Research output: Contribution to journalArticle

@article{bf61a738867d4f1aa6d5e40d85cf3acd,
title = "A merged fuzzy neural network and its applications in battery state-of-charge estimation",
abstract = "To solve learning problems with vast number of inputs, this paper proposes a novel learning structure merging a number of small fuzzy neural networks (FNNs) into a hierarchical learning structure called a merged-FNN. In this paper, the merged-FNN is proved to be a universal approximator. This computing approach uses a fusion of FNNs using B-spline membership functions (BMFs) with a reduced-form genetic algorithm (RGA). RGA is employed to tune all free parameters of the merged-FNN, including both the control points of the BMFs and the weights of the small FNNs. The merged-FNN can approximate a continuous nonlinear function to any desired degree of accuracy. For a practical application, a battery state-of-charge (BSOC) estimator, which is a twelve input, one output system, in a lithium-ion battery string is proposed to verify the effectiveness of the merged-FNN. From experimental results, the learning ability of the newly proposed merged-FNN with RGA is superior to that of the traditional neural networks with back-propagation learning.",
keywords = "B-spline membership functions (BMFs), Battery state-of-charge (BSOC), Battery string, Fuzzy neural networks (FNNs), Merged-FNN, Reduced-form genetic algorithm (RGA)",
author = "Li, {I. Hum} and Wang, {Wei Yen} and Su, {Shun Feng} and Lee, {Yuang Shung}",
year = "2007",
month = "9",
day = "1",
doi = "10.1109/TEC.2007.895457",
language = "English",
volume = "22",
pages = "697--708",
journal = "IEEE Transactions on Energy Conversion",
issn = "0885-8969",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "3",

}

TY - JOUR

T1 - A merged fuzzy neural network and its applications in battery state-of-charge estimation

AU - Li, I. Hum

AU - Wang, Wei Yen

AU - Su, Shun Feng

AU - Lee, Yuang Shung

PY - 2007/9/1

Y1 - 2007/9/1

N2 - To solve learning problems with vast number of inputs, this paper proposes a novel learning structure merging a number of small fuzzy neural networks (FNNs) into a hierarchical learning structure called a merged-FNN. In this paper, the merged-FNN is proved to be a universal approximator. This computing approach uses a fusion of FNNs using B-spline membership functions (BMFs) with a reduced-form genetic algorithm (RGA). RGA is employed to tune all free parameters of the merged-FNN, including both the control points of the BMFs and the weights of the small FNNs. The merged-FNN can approximate a continuous nonlinear function to any desired degree of accuracy. For a practical application, a battery state-of-charge (BSOC) estimator, which is a twelve input, one output system, in a lithium-ion battery string is proposed to verify the effectiveness of the merged-FNN. From experimental results, the learning ability of the newly proposed merged-FNN with RGA is superior to that of the traditional neural networks with back-propagation learning.

AB - To solve learning problems with vast number of inputs, this paper proposes a novel learning structure merging a number of small fuzzy neural networks (FNNs) into a hierarchical learning structure called a merged-FNN. In this paper, the merged-FNN is proved to be a universal approximator. This computing approach uses a fusion of FNNs using B-spline membership functions (BMFs) with a reduced-form genetic algorithm (RGA). RGA is employed to tune all free parameters of the merged-FNN, including both the control points of the BMFs and the weights of the small FNNs. The merged-FNN can approximate a continuous nonlinear function to any desired degree of accuracy. For a practical application, a battery state-of-charge (BSOC) estimator, which is a twelve input, one output system, in a lithium-ion battery string is proposed to verify the effectiveness of the merged-FNN. From experimental results, the learning ability of the newly proposed merged-FNN with RGA is superior to that of the traditional neural networks with back-propagation learning.

KW - B-spline membership functions (BMFs)

KW - Battery state-of-charge (BSOC)

KW - Battery string

KW - Fuzzy neural networks (FNNs)

KW - Merged-FNN

KW - Reduced-form genetic algorithm (RGA)

UR - http://www.scopus.com/inward/record.url?scp=34548289440&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34548289440&partnerID=8YFLogxK

U2 - 10.1109/TEC.2007.895457

DO - 10.1109/TEC.2007.895457

M3 - Article

AN - SCOPUS:34548289440

VL - 22

SP - 697

EP - 708

JO - IEEE Transactions on Energy Conversion

JF - IEEE Transactions on Energy Conversion

SN - 0885-8969

IS - 3

ER -