Electric Vehicle Li-Ion Battery State of Charge Estimation Using Artificial Neural Network

Chitnis, Mahesh S.; Pandit, Sachin P.; Shaikh, Mohemmed Suleman Noor Mohemmed.

doi:10.1109/icirca.2018.8597234

Cited by 19 publications

(12 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The important parameter is SoC, and SoC is defined as % capacity in the battery. 21 A 100% of SoC indicates the battery is fully charged. 22 Ghufron et al in 2017, reported that the time difference in different capacity values, it shown the highest capacity was obtained 3838 mAh on 2.5 hours charging with the resulting voltage 2.12 V and requiring discharge time of 13779 s, while the lowest capacity was obtained 630 mAh at 0 charging, 5 hours with a voltage of 2.17 V and required discharging time of 1988 second.…”

Section: Introductionmentioning

confidence: 99%

SOC (STATE of CHARGE) THREE-CELL LEAD DYNAMIC BATTERY MODEL

Pranata

Sukma

Ghufron

et al. 2021

Jurnal Fisika dan Aplikasinya

View full text Add to dashboard Cite

Three-cells dynamic lead-acid battery has been widely manufactured as the latest secondary battery technology. It is being carried out by 10 cycles of charge-discharge treatment with a various types of SoC, such as 100% (Full charge 5100 mAh), 50% (2550 mAh), 25% (1275 mAh) and discharge current of 0.8A. This experiment aims to analyze the treatment of SOC conditions on the performance of the lead-acid battery. The cyclicality test has performed using a Battery Management System (BMS) by applying an electric current at charging 1 A and discharging 0.8A. The results of the SOC charging conditions at 100%, 50%, 25% respectively gave a difference in the value of voltage efficiency of 84%, 87%, 88%, capacity efficiency values of 84%, 80%, 69%, energy efficiency values of 70%, 70%, 62%. The 100% and 50% SOC treatments showed better performance and battery energy the 25% SOC treatment. This research can be a recommendation to predict the performance of the lead-acid battery model during the charging and discharging process.

show abstract

Section: Introductionmentioning

confidence: 99%

SOC (STATE of CHARGE) THREE-CELL LEAD DYNAMIC BATTERY MODEL

Pranata

Sukma

Ghufron

et al. 2021

Jurnal Fisika dan Aplikasinya

View full text Add to dashboard Cite

show abstract

“…Moreover, several studies have employed deep learning. In particular, Chitnis et al and Li et al trained a deep neural network in which the inputs were the current and voltage to output SOC [12], [13]. They constructed a simple model that could estimate the SOC using only the current and voltage values.…”

Section: B Data-driven Methodsmentioning

confidence: 99%

Bayesian Estimation of Model Parameters of Equivalent Circuit Model for Detecting Degradation Parts of Lithium-Ion Battery

et al. 2021

View full text Add to dashboard Cite

Nowadays, the use of electric vehicles is increasing leading to a growing demand for more efficient use of lithium-ion batteries. The state-of-charge (SOC) has been estimated in previous studies to optimize energy management of batteries. For more efficient battery utilization, detecting degradation is important. However, it is difficult for conventional methods to distinguish the effect of the model parameters including different time constants. Identifying model parameters of multiple RC parallel branches, which represent the impedance of wider frequency ranges, is a necessary requirement to detect the degradation of parts. In this study, we present a method for estimating the model parameters of multiple RC parallel branches. We designed the Markov Chain Monte Carlo algorithm by setting a search range limit and moving window, which enable estimation of the model parameters of parallel branches of different time constants. Through validation of the algorithm based on simulation, the model parameters of a third-order circuit were estimated to be within the error range of 15.2 %. In addition, impedance was calculated from the estimated model parameters in the test using a real battery dataset. The error of impedance was less than 10 % from 0.01 to 100 Hz which was sufficiently low to monitor the change of the parameters owing to degradation. As the impedance in the high-frequency band above 0.1 Hz is more likely to change because of degradation, the proposed method can be used to monitor the model parameters that change as a result of degradation.INDEX TERMS Battery management systems, Bayes methods, detection of battery degradation parts, equivalent circuit model

show abstract

“…For example, studies in [27] and [28] used the variable forgetting factor recursive least-squares method to estimate the parameters that relate to the SOC. In [29], [30] artificial neural network is used for the SOC estimation. In this work, the Coulomb-counting method is used to estimate the SOC as [1]:…”

Section: System Configurationmentioning

confidence: 99%

Forecast-Based Energy Management for Domestic PV-Battery Systems: A U.K. Case Study

et al. 2021

View full text Add to dashboard Cite

This paper presents a predictive Energy Management System (EMS), aimed to improve the performance of a domestic PV-battery system and maximize self-consumption by minimizing energy exchange with the utility grid. The proposed algorithm facilitates a self-consumption approach, which reduces electricity bills, transmission losses, and the required central generation/storage systems. The proposed EMS uses a combination of Fuzzy Logic (FL) and a rule based-algorithm to optimally control the PV-battery system while considering the day-ahead energy forecast including forecast error and the battery State of Health (SOH). The FL maximizes the lifetime of the battery by using SOH and State of Charge (SOC) in decision making algorithm to charge/discharge the battery. The proposed Battery Management System (BMS) has been tested using Active Office Building (AOB) located in Swansea University, UK. Furthermore, it is compared with three recently published methods and with the current BMS utilized in the AOB to show the effectiveness of the proposed technique. The results show that the proposed BMS achieves a saving of 18% in the total energy cost over six months compared to a similar day-ahead forecast-based work. It also achieves a saving up to 95% compared to other methods (with a similar structure) but without a day-ahead forecast-based management. The proposed BMS enhances the battery's lifetime by reducing the average SOC up to 47% compared to the previous methods through avoiding unnecessary charge and discharge cycles. The impact of the PV system size and the battery capacity on the net exchanged energy with the utility grid is also investigated in this study.INDEX TERMS Battery management system, energy management system, fuzzy logic, state of charge, state of health.

show abstract

Electric Vehicle Li-Ion Battery State of Charge Estimation Using Artificial Neural Network

Cited by 19 publications

References 5 publications

SOC (STATE of CHARGE) THREE-CELL LEAD DYNAMIC BATTERY MODEL

SOC (STATE of CHARGE) THREE-CELL LEAD DYNAMIC BATTERY MODEL

Bayesian Estimation of Model Parameters of Equivalent Circuit Model for Detecting Degradation Parts of Lithium-Ion Battery

Forecast-Based Energy Management for Domestic PV-Battery Systems: A U.K. Case Study

Contact Info

Product

Resources

About