Study of machine learning algorithms to state of health estimation of iron phosphate lithium-ion battery used in fully electric vehicles

Santos, Sender Rocha dos; Aranha, Juliana C. M. S.; Nascimento, Thiago Chiachio do; Vieira, Daniel; Eloy, M. O.; Cerri, Fernando

doi:10.4271/2018-36-0178

Cited by 3 publications

(3 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Degradation of single cells is usually invisible in conventional battery systems. [226] x x x Haifeng et al [217] x x DKF Chiang et al [235] x x Adaptive O. Kim et al [19] x x x SMO Plett et al [236] x x WTLS Remmlinger et al [237] x x RLS Hu et al [174] x x DKF Rahimian et al [238] x LAM EKF/UKF Andre et al [192] x x x Feng et al [227] x x x Point Counting Kim et al [189] x x x Nuhic et al [239] x x x Prasad et al [222] x x Diffusion Time LS Remmlinger et al [240] x x KF Schwunk et al [241] x x PF Weng et al [242] x x x x Zheng et al [243] x x GA Eddahech et al [225] x CVCT Empirical Guo et al [223] x CCCT NLS Han et al [244] x x Calibrated O. Hu et al [245] x Sample Entropy Empirical Kim et al [80] x DWT Empirical Zou et al [185] x x DKF Berecibar et al [246] x x x Wu et al [247] x x x Zou et al [186] x x EKF Dubarry et al [248] x LAM, LLI Empirical Gong et al [233] x Gas Production Empirical Huhman et al [231] x x x Sanchez et al [249] Vessel Model x Fuzzy Cai et al [250] x DWT Empirical Chen et al [251] x x RF Lajara et al [232] x x x LS Li et al [228] x x x Li et al [252] x x EKF, PF Santos et al [253] x x x Shen et al [198] x x RLS Smiley et al [254] x x IMM KF Tang et al [255] x x...…”

Section: Online Identification Of State Of Healthmentioning

confidence: 99%

Critical Review of Intelligent Battery Systems: Challenges, Implementation, and Potential for Electric Vehicles

et al. 2021

View full text Add to dashboard Cite

This review provides an overview of new strategies to address the current challenges of automotive battery systems: Intelligent Battery Systems. They have the potential to make battery systems more performant and future-proof for coming generations of electric vehicles. The essential features of Intelligent Battery Systems are the accurate and robust determination of cell individual states and the ability to control the current of each cell by reconfiguration. They enable high-level functions like fault diagnostics, multi-objective balancing strategies, multilevel inverters, and hybrid energy storage systems. State of the art and recent advances in these topics are compiled and critically discussed in this article. A comprising, critical discussion of the implementation aspects of Intelligent Battery Systems complements the review. We touch on sensing, battery topologies and management, switching elements, communication architecture, and impact on the single-cell. This review contributes to transferring the best technologies from research to product development.

show abstract

Section: Online Identification Of State Of Healthmentioning

confidence: 99%

Critical Review of Intelligent Battery Systems: Challenges, Implementation, and Potential for Electric Vehicles

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The BMS is the device in charge of controlling different battery parameters: (i) current, (ii) voltage, (iii) SOC, (iv) SOH, and (v) temperature. CPqD research even includes algorithms for the assessment of SoC [129] and SoH [130].…”

Section: Electromobility Market and Charging Infrastructure Developmentmentioning

confidence: 99%

The New Neighbor across the Street: An Outlook for Battery Electric Vehicles Adoption in Brazil

Vargas

Seabra

Cavaliero

et al. 2020

WEVJ

View full text Add to dashboard Cite

As the automotive industry steers towards electromobility and electric vehicle adoption surges, Brazil and other Latin-American countries remain laggards. The Brazilian scenario exhibits unique features, such as a powerful automotive sector with large investments in internal combustion engine technology and a well-established biofuels market based on flex-fuel technology. Although energy security, urban air pollution, greenhouse gas emissions mitigation, and technological advantage have been common drivers for the adoption of electric vehicles worldwide, the Brazilian immediate motivations are different, and the biofuels business ecosystem is likely to transform the path for electromobility. High tag price and public charging infrastructure absence have deeply discouraged electric vehicles adoption. A lack of regulation and a national consensus about the role of electric vehicles have been notorious. In fact, only in 2018 did the electricity regulatory agency (ANEEL) issue a resolution permitting the sale of electricity for recharging. The objective of this review was to create an outlook of the Brazilian transportation landscape. We identified relevant players, public charging infrastructure initiatives, market and other barriers, and regulation actions by consulting academic literature, media sources, and reports. We do not claim to predict the evolution of electrification. Instead, we aim to consolidate the information which can be used for decision support or strategy definition among entrepreneurs or policymakers. The main findings here are the necessity of a model for electrification able to create a synergy with biofuels and the urgency of having well-defined policies on what Brazil wants from electromobility.

show abstract

“…Phattara Khumprom et al [ 16 ] presented the preliminary development of data-driven prognostics and used deep neural networks (DNNs) and the NASA (PCoE) battery dataset to predict the SoH and the RUL of a lithium-ion battery. Daniel Vieira et al [ 17 ] proposed a general data-driven method for estimating battery SOH. Through continuous experiments on lithium-iron phosphate batteries in the laboratory, the original dataset was obtained, and then a NARX (nonlinear auto-regressive network with exogenous inputs) neural network was explored.…”

Section: Introductionmentioning

confidence: 99%

A Data-Driven Approach to State of Health Estimation and Prediction for a Lithium-Ion Battery Pack of Electric Buses Based on Real-World Data

Xie

et al. 2022

Sensors

View full text Add to dashboard Cite

In the era of big data, using big data to realize the online estimation of battery SOH has become possible. Traditional solutions based on theoretical models cannot take into account driving behavior and complicated environmental factors. In this paper, an approximate SOH degradation model based on real operating data and environmental temperature data of electric vehicles (EVs) collected with a big data platform is proposed. Firstly, the health indicators are extracted from the historical operating data, and the equivalent capacity at 25 °C is obtained based on the capacity–temperature empirical formula and the capacity offset. Then, the attenuation rate during each charging and discharging process is calculated by combining the operating data and the environmental temperature. Finally, the long short-term memory (LSTM) neural network is used to learn the degradation trend of the battery and predict the future decline trend. The test results show that the proposed method has better performance.

show abstract

Study of machine learning algorithms to state of health estimation of iron phosphate lithium-ion battery used in fully electric vehicles

Cited by 3 publications

References 7 publications

Critical Review of Intelligent Battery Systems: Challenges, Implementation, and Potential for Electric Vehicles

Critical Review of Intelligent Battery Systems: Challenges, Implementation, and Potential for Electric Vehicles

The New Neighbor across the Street: An Outlook for Battery Electric Vehicles Adoption in Brazil

A Data-Driven Approach to State of Health Estimation and Prediction for a Lithium-Ion Battery Pack of Electric Buses Based on Real-World Data

Contact Info

Product

Resources

About