Advanced Machine Learning Approach for Lithium-Ion Battery State Estimation in Electric Vehicles

Hu, Xiaosong; Li, Shengbo Eben; Yang, Yalian

doi:10.1109/tte.2015.2512237

Cited by 296 publications

(120 citation statements)

References 34 publications

Supporting

Mentioning

111

Contrasting

Unclassified

Order By: Relevance

“…Coils are connected in series and self-inductance of the combination for each position is determined. Finally, mutual inductance is calculated using (7). Table 3 provides mutual inductance values for different positions found by experiment and by simulation.…”

Section: Simulation and Experiments Resultsmentioning

confidence: 99%

“…Moreover, general public interest has motivated car manufacturers towards the development of various electric vehicles [2,5], such as battery electric vehicles (BEV), hybrid electric vehicles (HEV), fuel cell electric vehicles (FCEV), and fuel cell hybrid vehicles (FCHV) [6]. The development and improvement of battery storage systems as well as implementation of various techniques for the monitoring and control of battery states facilitates the attractiveness of EVs [7,8]. EV charging can be accomplished either using cables (wired) or wirelessly.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Precise Analysis on Mutual Inductance Variation in Dynamic Wireless Charging of Electric Vehicle

et al. 2018

View full text Add to dashboard Cite

Abstract:Wireless power transfer provides an opportunity to charge electric vehicles (EVs) without electrical cables. Two categories of this technique are distinguished: Stationary Wireless Charging (SWC) and Dynamic Wireless Charging (DWC) systems. Implementation of DWC is more desirable than SWC as it can potentially eliminate challenges associated with heavy weight batteries and time-consuming charging processes. However, power transfer efficiency and range, lateral misalignment of coils as well as implementation cost are issues affecting DWC. These issues need to be addressed through developing coil architectures and topologies as well as operating novel semiconductor switches at higher frequencies. This study presents a small-scale dynamic wireless power transfer system for EV. It specifically concentrates on analyzing the dynamic mutual inductance between the coils due to the misalignment as it has significant influence on the EV charging process, particularly, over the output power and overall efficiency. A simulation study is carried out to explore dynamic mutual inductance profile between the transmitter and receiver coils. Mutual inductance simulation results are then verified through practical measurements on fabricated coils. Integrating the practical results into the model, an EV DWC power transfer simulation is conducted and the relation between dynamic mutual inductance and output power are discussed technically.

show abstract

Section: Simulation and Experiments Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Precise Analysis on Mutual Inductance Variation in Dynamic Wireless Charging of Electric Vehicle

et al. 2018

View full text Add to dashboard Cite

show abstract

“…In particular, the battery-based ESS is usually used [3][4][5][6]. There are a lot of studies carried out to store energy into battery efficiently [7][8][9]. The ESS in a DG system based on RES plays various roles [10,11].…”

Section: Introductionmentioning

confidence: 99%

Implementation of a Smart Power Conditioning System for Energy Storage System with a Novel Seamless Transfer Strategy

Kim

et al. 2018

Energies

View full text Add to dashboard Cite

Implementation of a smart power conditioning system with a novel seamless transfer method for an energy storage system (ESS) was proposed in this paper. The power conditioning system is to control the power quality or protect the grid system. Therefore, it requires various functions. One of the these functions, the uninterruptible power supply (UPS) function, was applied to proposed power conditioning system. In order for the grid-interactive power conditioning system to continuously supply power to the load, two operation modes are required depending on the grid state. One is the grid connected (GC) mode and the other is the stand-alone (SA) mode. Under normal grid condition, the power conditioning system is operated in GC mode and controls the current. On the other hand, under abnormal grid conditions such as grid outage, the power conditioning system operates in SA mode and supplies power to the load. Unintentional sudden changes in operating mode cause unwanted phenomena (e.g., voltage/current spike, inrush current) which can make system degradation or failure. To improve this situation, the seamless transfer function became necessary. In this paper, by adding seamless function to power conditioning system, it is possible to supply power to the load stably regardless of grid state. In addition, it is possible to prevent secondary accident and to operate stably even if non-detection zone condition occurs by using an active frequency method. The proposed control algorithm was verified through field experiments.

show abstract

“…Several machine learning approaches involving artificial neural networks, support vector machines, relevance vector machine, and Fuzzy K-means [6,[20][21][22] have also been used in the recent past. Other approaches include the use of the Wiener process for RUL prediction with the maximum likelihood estimation and Bayesian updated expectation and maximization algorithm, which potentially gave a good fit for the experimental results for Li-ion battery charge decay [23].…”

Section: Introductionmentioning

confidence: 99%

“…Although the work of numerous researchers on lithium-ion battery prognosis, RUL and SOH estimation as summarized above [2][3][4]8,17,22,27,28] have gained sufficient ground, our aim here is to add a new dimension to the study by accounting for uncertainty, using the random effect model, to enhance the predictability of RUL for lithium-ion batteries under real-life test. It is important to note that the prognostic studies on Li-ion batteries carried out by most of the reviewed papers here, did not account for uncertainties in the charge decay patterns and their impact on the prediction accuracy.…”

Section: Introductionmentioning

confidence: 99%

Statistical Characterization of the State-of-Health of Lithium-Ion Batteries with Weibull Distribution Function—A Consideration of Random Effect Model in Charge Capacity Decay Estimation

Ossai

Raghavan

2017

Batteries

View full text Add to dashboard Cite

Effective prognosis of lithium-ion batteries involves the inclusion of the influences of uncertainties that can be incorporated through random effect parameters in a nonlinear mixed effect degradation model framework. This study is geared towards the estimation of the reliability of lithium-ion batteries, using parametric effects determination involving uncertainty, using a multiphase decay patterned sigmoidal model, experimental data and the Weibull distribution function. The random effect model, which uses Maximum Likelihood Estimation (MLE) and Stochastic Approximation Expectation Maximization (SAEM) algorithm to predict the parametric values, was found to estimate the remaining useful life (RUL) to an accuracy of more than 98%. The State-of-Health (SOH) of the batteries was estimated using the Weibull distribution function, which is found to be an appropriate formulation to use.

show abstract

Advanced Machine Learning Approach for Lithium-Ion Battery State Estimation in Electric Vehicles

Cited by 296 publications

References 34 publications

Precise Analysis on Mutual Inductance Variation in Dynamic Wireless Charging of Electric Vehicle

Precise Analysis on Mutual Inductance Variation in Dynamic Wireless Charging of Electric Vehicle

Implementation of a Smart Power Conditioning System for Energy Storage System with a Novel Seamless Transfer Strategy

Statistical Characterization of the State-of-Health of Lithium-Ion Batteries with Weibull Distribution Function—A Consideration of Random Effect Model in Charge Capacity Decay Estimation

Contact Info

Product

Resources

About