Battery state of charge estimation based on a combined model of Extended Kalman Filter and neural networks

Chen, Zhihang; Qiu, Shiqi; Masrur, M. Abul; Murphey, Yi Lu

doi:10.1109/ijcnn.2011.6033495

Cited by 57 publications

(24 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Normalization data is aimed more efficiency and robust when computational. This is formula of normalization data before training data [5]: (2) Where Xmin and Xmax are X minimum and maximal input vectors in the BPNN. The testing process use same data scale with Xmin and Xmax when training data 5.…”

Section: Back Propagation Neural Networkmentioning

confidence: 99%

“…It is difficult for modeling charge and discharge process of batteries. Neural Networks (NN) is one of method which is compatible for nonlinear systems that simulate in dynamic characteristics of batteries [2]. BPNN algorithm was proposed in 1986 by Rumelhart, Hinton and Williams for setting weight and hence for the training of multi-layer perceptrons [3].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Backpropagation neural network models for LiFePO4 battery

Primadusi

Cahyadi

Prasetyo

et al. 2016

AIP Conference Proceedings

View full text Add to dashboard Cite

Abstract. Neural Networks have been used in system control, medicine, pattern recognition and business. The backpropagation neural network (BPNN) appear to be most popular and have been widely used in many applications. BPNN is a supervised learning technique for training multilayer feedforward neural networks. The gradient or steepest descent method is used to train a BPNN by adjusting the weights . The purpose of update numerical weights is minimize error of network between target and output. In this paper, focus with BPNN modeling with data battery for training and testing. We used discharge and Urban Dynamometer Driving Schedule (UDDS) as training data and testing data, respectively Architecture of BPNN consist of input layer, hidden layer and output layer. The otherhand, using BPNN has problem to define amount of hidden neurons. In this study, we used current or voltage as input in input layer, one hidden layer with 8 neurons and one output layer. We used Levenberg-Marquardt algorithm to get fast iteration when computation. The experiment used 2200 mAh of LiFePO4 battery. Result of this research show that Mean Squared Error (MSE) value when current as input and voltage as target is 0.021135 with regresion is 0.626. Then MSE value when voltage as input and current as target 0.029925 with regresion is 0.5213. In this study relationship between voltage and current battery is nonlinear.

show abstract

Section: Back Propagation Neural Networkmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Backpropagation neural network models for LiFePO4 battery

Primadusi

Cahyadi

Prasetyo

et al. 2016

AIP Conference Proceedings

View full text Add to dashboard Cite

show abstract

“…On the contrary, battery remaining reduces almost uniformly when an EV drives on flat area as shown in Figure 5(b). How to quantify this change and map the road characteristics to the change will be net next problem [16]. 7 (a) driving mountain area (b) driving plain area …”

Section: Figure 2 Road Layoutmentioning

confidence: 99%

Design of a Shape File Index for Fast Map Matching in Electric Vehicle Services

Lee¹,

Park

2013

IJCA

View full text Add to dashboard Cite

show abstract

“…In addition to SOC estimation, an active cell balancing (AB) circuit [43][44][45] is another important element in the battery management system. Most batteries are made up of multiple cells that required AB to prevent each cell from overcharge or discharge after the SOC was determined.…”

Section: Introductionmentioning

confidence: 99%

“…There exist different cell balancing methods using a resistor, capacitor, inductor/transformer, and energy converter balancing method [44,45]. For example, the shuttling capacitors cell balancing method named "charge shuttling cells equalization" used capacitors as external energy storage for alternating the energy between the cells for charge balancing.…”

Section: Introductionmentioning

confidence: 99%

State-of-Charge Estimation and Active Cell Pack Balancing Design of Lithium Battery Power System for Smart Electric Vehicle

Gao

Chin

Toh

et al. 2017

Journal of Advanced Transportation

View full text Add to dashboard Cite

This paper presents an integrated state-of-charge (SOC) estimation model and active cell balancing of a 12-cell lithium iron phosphate (LiFePO4) battery power system. The strong tracking cubature extended Kalman filter (STCEKF) gave an accurate SOC prediction compared to other Kalman-based filter algorithms. The proposed groupwise balancing of the multiple SOC exhibited a higher balancing speed and lower balancing loss than other cell balancing designs. The experimental results demonstrated the robustness and performance of the battery when subjected to current load profile of an electric vehicle under varying ambient temperature.

show abstract

Battery state of charge estimation based on a combined model of Extended Kalman Filter and neural networks

Cited by 57 publications

References 9 publications

Backpropagation neural network models for LiFePO4 battery

Backpropagation neural network models for LiFePO4 battery

Design of a Shape File Index for Fast Map Matching in Electric Vehicle Services

State-of-Charge Estimation and Active Cell Pack Balancing Design of Lithium Battery Power System for Smart Electric Vehicle

Contact Info

Product

Resources

About