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
N1 - Funding Information:
Manuscript received September 12, 2005; revised April 17, 2006. This work was supported in part by the National Science Council of Taiwan under Grant NSC 91-2213-E-030-007, and in part by the Material Research Laboratories (MRL), Industrial Technology Research Institute (ITRI) of Taiwan. Paper no. TEC-00311-2005.
PY - 2007/9
Y1 - 2007/9
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
SN - 0885-8969
VL - 22
SP - 697
EP - 708
JO - IEEE Transactions on Energy Conversion
JF - IEEE Transactions on Energy Conversion
IS - 3
ER -
