Battery state-of-charge estimator using the SVM technique

Anton, J.C.; Nieto, P.J. Garcı́a; Juez, Francisco Javier de Cos; Lasheras, Fernando Sánchez; González, Miguel Ángel Álvarez; Gutiérrez, M.N. Roqueñí

doi:10.1016/j.apm.2013.01.024

Cited by 148 publications

(29 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This method requires large Random Access Memory (RAM) storage to train the system for the learning process of the neural network [7]. Other machine learning methods such as the fuzzy logic, support vector machine and genetic algorithm have been extensively researched for battery SoC estimation [8][9][10][11]. The machine learning method improves the intelligence of the system but the results are difficult to interpret and hence is not convenient in real practice.…”

Section: Of 21mentioning

confidence: 99%

See 1 more Smart Citation

State of Charge Estimation of a Composite Lithium-Based Battery Model Based on an Improved Extended Kalman Filter Algorithm

et al. 2019

View full text Add to dashboard Cite

The battery State of Charge (SoC) estimation is one of the basic and significant functions for Battery Management System (BMS) in Electric Vehicles (EVs). The SoC is the key to interoperability of various modules and cannot be measured directly. An improved Extended Kalman Filter (iEKF) algorithm based on a composite battery model is proposed in this paper. The approach of the iEKF combines the open-circuit voltage (OCV) method, coulomb counting (Ah) method and EKF algorithm. The mathematical model of the iEKF is built and four groups of experiments are conducted based on LiFePO4 battery for offline parameter identification of the model. The iEKF is verified by real battery data. The simulation results with the proposed iEKF algorithm under both static and dynamic operation conditions show a considerable accuracy of SoC estimation.

show abstract

Section: Of 21mentioning

confidence: 99%

“…where i is positive when discharging, but negative when charging. The coefficient of charging/discharging rate (η i ) and temperature (η T ) are obtained by Equations (8a), (8b) and (9), respectively.…”

mentioning

confidence: 99%

State of Charge Estimation of a Composite Lithium-Based Battery Model Based on an Improved Extended Kalman Filter Algorithm

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Further unscented Kalman filter is used to reduce the errors in the neural network-based SOC estimation [8]. SVM based methods for estimation of SOC are developed [9][10]. The inputs to SVM were voltage, current and temperature, and output was SOC, with training data and testing data under the same loading condition.…”

Section: Introductionmentioning

confidence: 99%

System Level Modelling of Batteries in Spacecraft Power System in Multiple Source and Multiple Load Configuration

Prasad

Ananda

Mahanta

et al. 2019

INCOSE International Symp

View full text Add to dashboard Cite

In present day spacecraft applications, power system uses solar arrays as the primary source of power generation and rechargeable Lithium ion batteries as secondary source of power. In normal orbits, during sunlit period, solar arrays support the power requirement from all the subsystems and payloads along with the charge power requirement of batteries. During eclipse period, entire load should be supported by batteries. In addition to the eclipse support, starting from launch pad to till deployment of solar panels, all loads will be on batteries. Contingency loads should also be taken care by batteries. So, battery sizing is very critical part in designing the power system of spacecraft. In multiple source and multiple load configuration where two or more batteries are connected to same Spacecraft power bus, current sharing between the batteries is expected, which needs to be considered for optimized sizing and designing of batteries. The scenario becomes complex with additional constraints namely some loads can come on one battery and not on others or vice versa. Even in a configuration where potential difference exists between batteries, current sharing will start as soon as this difference vanishes. A system level simulation model is developed, using network equations, to analyze in-circuit performance of batteries in multiple source and multiple load power system. The simulation model uses actual current sharing and predicts State of Charge (SOC) of each battery from which Open Circuit Voltage (OCV) is derived. This OCV of batteries is used periodically for finding actual current sharing which runs in a loop for analyzing battery performance in multisource system. Currently a configuration in which two batteries are connected to two buses, which are paralleled and having different loads, is simulated. Optimized battery sizing, actual current sharing and SOC of each battery are derived. This model can also be extended to a system where more than two batteries are present. Two different approaches are used for simulation and results are compared. The developed generic model has features to use in multiple battery configuration. He has served as Project Manager and Deputy Project Director for several spacecraft projects. He steered the development of modular design of high energy lithium ion batteries, Nickel hydrogen and Nickel cadmium batteries. He has been involved in Design, fabrication, testing and on orbit Management of Satellite Batteries and power system since Sept 1985. Sankaran M, currently Outstanding Scientist and Deputy Director, Communications and Power Systems Area, U R Rao Satellite Centre, Indian Space Research Organization. He joined ISRO in 1986 after his M.Sc., degree in Physics from RSGC, under Bharathidasan University, Tiruchirappalli. During his past 32.5 years in ISRO, he has contributed mainly in the area of solar arrays, power systems and RF communication systems for spacecraft. He has served as Project Manager and Deputy Project Director for several spacecraft projects. He steered the...

show abstract

“…Nonetheless, all Kalman filter based methods require the knowledge of process and measurement noise that can lead to poor filter convergence rate if not determine correctly. Lastly, artificial intelligence methods using fuzzy logic and neural networks have also been used [16][17][18]. Although it tackles well on the nonlinearity aspects of battery model, the computational cost is heavy and significantly large training data is needed to ensure its accuracy.…”

Section: Introductionmentioning

confidence: 99%

State-of-charge estimation using particle swarm optimization with inverse barrier constraint in a nanosatellite

Aung

Low

Soon

2015

2015 IEEE 10th Conference on Industrial Electronics and Applications (ICIEA)

View full text Add to dashboard Cite

Lithium ion batteries have become the preferred choice for many applications due to their high energy density and low self-discharge rate. State-of-charge (SOC) information is required in many applications to optimize and safeguard the performance of the batteries. Different methods of SOC estimation such as Ampere counting and model-based estimation have been used in SOC estimation. Among the model based estimation, Kalman filter based method is one of the most commonly used method. However, it requires linearization, an accurate battery model and information on measurement and process noise. In this paper, a SOC estimation based on particle swarm optimization (PSO) with inverse barrier constraint is proposed. This method overcomes the need to linearize the model and does not require the information on measurement and process noise. The proposed method has been verified experimentally. From the experimental results, the root mean square error (RMSE) is 1.03% and absolute maximum error is 3.35%.

show abstract

Battery state-of-charge estimator using the SVM technique

Cited by 148 publications

References 16 publications

State of Charge Estimation of a Composite Lithium-Based Battery Model Based on an Improved Extended Kalman Filter Algorithm

State of Charge Estimation of a Composite Lithium-Based Battery Model Based on an Improved Extended Kalman Filter Algorithm

System Level Modelling of Batteries in Spacecraft Power System in Multiple Source and Multiple Load Configuration

State-of-charge estimation using particle swarm optimization with inverse barrier constraint in a nanosatellite

Contact Info

Product

Resources

About