State-of-health estimation for fast-charging lithium-ion batteries based on a short charge curve using graph convolutional and long short-term memory networks

A fast-charging policy is widely employed to alleviate the inconvenience caused by the extended charging time of electric vehicles. However, fast charging exacerbates battery degradation and shortens battery lifespan. In addition, there is still a lack of tailored health estimations for fast-charging batteries;most existing methods are applicable at lower charging rates. This paper proposes a novel method for estimating the health of lithium-ion batteries, which is tailored for multi-stage constant current-constant voltage fast-charging policies. Initially, short charging segments are extracted by monitoring current switches,followed by deriving voltage sequences using interpolation techniques. Subsequently, a graph generation layer is used to transform the voltage sequence into graphical data. Furthermore, the integration of a graph convolution network with a long short-term memory network enables the extraction of information related to inter-node message transmission, capturing the key local and temporal features during the battery degradation process. Finally, this method is confirmed by utilizing aging data from 185 cells and 81 distinct fast-charging policies. The 4-minute charging duration achieves a balance between high accuracy in estimating battery state of health and low data requirements, with mean absolute errors and root mean square errors of 0.34% and 0.66%, respectively.

State of Health Estimation of Lithium-Ion Batteries Using Support Vector Regression and Long Short-Term Memory

Lithium-ion batteries are the most widely accepted type of battery in the electric vehicle industry because of some of their positive inherent characteristics. However, the safety problems associated with inaccurate estimation and prediction of the state of health of these batteries have attracted wide attention due to the adverse negative effect on vehicle safety. In this paper, both machine and deep learning models were used to estimate the state of health of lithium-ion batteries. The paper introduces the definition of battery health status and its importance in the electric vehicle industry. Based on the data preprocessing and visualization analysis, three features related to actual battery capacity degradation are extracted from the data. Two learning models, SVR and LSTM were employed for the state of health estimation and their respective results are compared in this paper. The mean square error and coefficient of determination were the two metrics for the performance evaluation of the models. The experimental results indicate that both models have high estimation results. However, the metrics indicated that the SVR was the overall best model.

Estimating the State of Health for Lithium-ion Batteries:A Particle Swarm Optimization-Assisted Deep Domain Adaptation Approach

The state of health(SOH)is a critical factor in evaluating the performance of the lithium-ion batteries(LIBs).Due to various end-user behaviors,the LIBs exhibit different degradation modes,which makes it challenging to estimate the SOHs in a personalized way.In this article,we present a novel particle swarm optimization-assisted deep domain adaptation(PSO-DDA)method to estimate the SOH of LIBs in a personalized manner,where a new domain adaptation strategy is put forward to reduce cross-domain distribution discrepancy.The standard PSO algorithm is exploited to automatically adjust the chosen hyperparameters of developed DDA-based method.The proposed PSODDA method is validated by extensive experiments on two LIB datasets with different battery chemistry materials,ambient temperatures and charge-discharge configurations.Experimental results indicate that the proposed PSO-DDA method surpasses the convolutional neural network-based method and the standard DDA-based method.The Py Torch implementation of the proposed PSO-DDA method is available at https://github.com/mxt0607/PSO-DDA.

Transfer learning from synthetic data for open-circuit voltage curve reconstruction and state of health estimation of lithium-ion batteries from partial charging segments

Data-driven models for battery state estimation require extensive experimental training data,which may not be available or suitable for specific tasks like open-circuit voltage(OCV)reconstruction and subsequent state of health(SOH)estimation.This study addresses this issue by developing a transfer-learning-based OCV reconstruction model using a temporal convolutional long short-term memory(TCN-LSTM)network trained on synthetic data from an automotive nickel cobalt aluminium oxide(NCA)cell generated through a mechanistic model approach.The data consists of voltage curves at constant temperature,C-rates between C/30 to 1C,and a SOH-range from 70%to 100%.The model is refined via Bayesian optimization and then applied to four use cases with reduced experimental nickel manganese cobalt oxide(NMC)cell training data for higher use cases.The TL models’performances are compared with models trained solely on experimental data,focusing on different C-rates and voltage windows.The results demonstrate that the OCV reconstruction mean absolute error(MAE)within the average battery electric vehicle(BEV)home charging window(30%to 85%state of charge(SOC))is less than 22 mV for the first three use cases across all C-rates.The SOH estimated from the reconstructed OCV exhibits an mean absolute percentage error(MAPE)below 2.2%for these cases.The study further investigates the impact of the source domain on TL by incorporating two additional synthetic datasets,a lithium iron phosphate(LFP)cell and an entirely artificial,non-existing,cell,showing that solely the shifting and scaling of gradient changes in the charging curve suffice to transfer knowledge,even between different cell chemistries.A key limitation with respect to extrapolation capability is identified and evidenced in our fourth use case,where the absence of such comprehensive data hindered the TL process.

State of health estimation for lithium-ion battery based on particle swarm optimization algorithm and extreme learning machine

Lithium-ion battery State of Health(SOH)estimation is an essential issue in battery management systems.In order to better estimate battery SOH,Extreme Learning Machine(ELM)is used to establish a model to estimate lithium-ion battery SOH.The Swarm Optimization algorithm(PSO)is used to automatically adjust and optimize the parameters of ELM to improve estimation accuracy.Firstly,collect cyclic aging data of the battery and extract five characteristic quantities related to battery capacity from the battery charging curve and increment capacity curve.Use Grey Relation Analysis(GRA)method to analyze the correlation between battery capacity and five characteristic quantities.Then,an ELM is used to build the capacity estimation model of the lithium-ion battery based on five characteristics,and a PSO is introduced to optimize the parameters of the capacity estimation model.The proposed method is validated by the degradation experiment of the lithium-ion battery under different conditions.The results show that the battery capacity estimation model based on ELM and PSO has better accuracy and stability in capacity estimation,and the average absolute percentage error is less than 1%.

Performance simulation method and state of health estimation for lithium-ion batteries based on aging-effect coupling model

Accurate simulation of characteristics performance and state of health(SOH)estimation for lithium-ion batteries are critical for battery management systems(BMS)in electric vehicles.Battery simplified electrochemical model(SEM)can achieve accurate estimation of battery terminal voltage with less computing resources.To ensure the applica-bility of life-cycle usage,degradation physics need to be involved in SEM models.This work conducts deep analysis on battery degradation physics and develops an aging-effect coupling model based on an existing improved single particle(ISP)model.Firstly,three mechanisms of solid electrolyte interface(SEI)film growth throughout life cycle are analyzed,and an SEI film growth model of lithium-ion battery is built coupled with the ISP model.Then,a series of identification conditions for individual cells are designed to non-destructively determine model parameters.Finally,battery aging experiment is designed to validate the battery performance simulation method and SOH estimation method.The validation results under different aging rates indicate that this method can accurately es-timate characteristics performance and SOH for lithium-ion batteries during the whole life cycle.

Life-cycle assessment of batteries for peak demand reduction

At present,a life-cycle assessment of energy storage systems(ESSs)is not widely available in the literature.Such an assessment is increasingly vital nowadays as ESS is recognized as one of the important equipment in power systems to reduce peak demands for deferring or avoiding augmentation in the network and power generation.As the battery cost is still very high at present,a comprehensive assessment is necessary to determine the optimum ESS capacity so that the maximum financial gain is achievable at the end of the batteries’lifespan.Therefore,an effective life-cycle assessment is proposed in this paper to show how the optimum ESS capacity can be determined such that the maximum net financial gain is achievable at the end of the batteries’lifespan when ESS is used to perform peak demand reductions for the customer or utility companies.The findings reveal the positive financial viability of ESS on the power grid,otherwise the projection of the financial viability is often seemingly poor due to the high battery cost with a short battery lifespan.An improved battery degradation model is used in this assessment,which can simulate the battery degradation accurately in a situation whereby the charging current,discharging current,and temperature of the batteries are intermittent on a site during peak demand reductions.This assessment is crucial to determine the maximum financial benefits brought by ESS.

Experimental Study of Energy Consumption Variation in Recurring Driving Trips

With a growing consumer market of battery electric vehicles, customers＇ demand for technology and features is on the rise. The range and, to a certain extent, the range estimation will play a key factor in customers＇ purchase decisions. In order to guarantee a precise range estimation over the usage life of battery electric vehicles, a method is presented that combines adaptive filter algorithms with statistical approaches. The statistical approach uses recurring driving cycles over the lifetime in order to derive the aging status of the traction battery. It is implied that the variance of the energy usage of these driving cycles is within certain bounds. This fact should be proven by an experimental case study. The dataset used in this paper is open to the public.

Multi‑scale Battery Modeling Method for Fault Diagnosis

Fault diagnosis is key to enhancing the performance and safety of battery storage systems.However,it is challenging to realize efficient fault diagnosis for lithium-ion batteries because the accuracy diagnostic algorithm is limited and the features of the different faults are similar.The model-based method has been widely used for degradation mechanism analysis,state estimation,and life prediction of lithium-ion battery systems due to the fast speed and high development efficiency.This paper reviews the mainstream modeling approaches used for battery diagnosis.First,a review of the battery’s degradation mechanisms and the external factors affecting the aging rate is presented.Second,the different modeling approaches are summarized,from microscopic to macroscopic scales,including density functional theory,molecular dynamics,X-ray computed tomography technology,electrochemical model,equivalent circuit model,distributed model and neural network algorithm.Subsequently,the advantages and disadvantages of these model approaches are discussed for fault detection and diagnosis of batteries in different application scenarios.Finally,the remaining challenges of model-based battery diagnosis and the future perspective of using cloud control and battery intelligent networking to enhance diagnostic performance are discussed.