With the rapid development of new energy technologies, lithium batteries are widely used in the field of energy storage systems and electric vehicles. The accurate prediction for the state of health(SOH) has an import...With the rapid development of new energy technologies, lithium batteries are widely used in the field of energy storage systems and electric vehicles. The accurate prediction for the state of health(SOH) has an important role in maintaining a safe and stable operation of lithium-ion batteries. To address the problems of uncertain battery discharge conditions and low SOH estimation accuracy in practical applications, this paper proposes a SOH estimation method based on constant-current battery charging section characteristics with a back-propagation neural network with an improved atom search optimization algorithm. A temperature characteristic, equal-time temperature variation(Dt_DT), is proposed by analyzing the temperature data of the battery charging section with the incremental capacity(IC) characteristics obtained from an IC analysis as an input to the data-driven prediction model. Testing and analysis of the proposed prediction model are carried out using publicly available datasets. Experimental results show that the maximum error of SOH estimation results for the proposed method in this paper is below 1.5%.展开更多
State of health(SoH) estimation plays a key role in smart battery health prognostic and management.However,poor generalization,lack of labeled data,and unused measurements during aging are still major challenges to ac...State of health(SoH) estimation plays a key role in smart battery health prognostic and management.However,poor generalization,lack of labeled data,and unused measurements during aging are still major challenges to accurate SoH estimation.Toward this end,this paper proposes a self-supervised learning framework to boost the performance of battery SoH estimation.Different from traditional data-driven methods which rely on a considerable training dataset obtained from numerous battery cells,the proposed method achieves accurate and robust estimations using limited labeled data.A filter-based data preprocessing technique,which enables the extraction of partial capacity-voltage curves under dynamic charging profiles,is applied at first.Unsupervised learning is then used to learn the aging characteristics from the unlabeled data through an auto-encoder-decoder.The learned network parameters are transferred to the downstream SoH estimation task and are fine-tuned with very few sparsely labeled data,which boosts the performance of the estimation framework.The proposed method has been validated under different battery chemistries,formats,operating conditions,and ambient.The estimation accuracy can be guaranteed by using only three labeled data from the initial 20% life cycles,with overall errors less than 1.14% and error distribution of all testing scenarios maintaining less than 4%,and robustness increases with aging.Comparisons with other pure supervised machine learning methods demonstrate the superiority of the proposed method.This simple and data-efficient estimation framework is promising in real-world applications under a variety of scenarios.展开更多
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 t...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.展开更多
Though the lithium-ion battery is universally applied,the reliability of lithium-ion batteries remains a challenge due to various physicochemical reactions,electrode material degradation,and even thermal runaway.Accur...Though the lithium-ion battery is universally applied,the reliability of lithium-ion batteries remains a challenge due to various physicochemical reactions,electrode material degradation,and even thermal runaway.Accurate estimation and prediction of battery health conditions are crucial for battery safety management.In this paper,an end-cloud collaboration method is proposed to approach the track of battery degradation process,integrating end-side empirical model with cloud-side data-driven model.Based on ensemble learning methods,the data-driven model is constructed by three base models to obtain cloud-side highly accurate results.The double exponential decay model is utilized as an empirical model to output highly real-time prediction results.With Kalman filter,the prediction results of end-side empirical model can be periodically updated by highly accurate results of cloud-side data-driven model to obtain highly accurate and real-time results.Subsequently,the whole framework can give an accurate prediction and tracking of battery degradation,with the mean absolute error maintained below 2%.And the execution time on the end side can reach 261μs.The proposed end-cloud collaboration method has the potential to approach highly accurate and highly real-time estimation for battery health conditions during battery full life cycle in architecture of cyber hierarchy and interactional network.展开更多
In the field of energy storage,it is very important to predict the state of charge and the state of health of lithium-ion batteries.In this paper,we review the current widely used equivalent circuit and electrochemica...In the field of energy storage,it is very important to predict the state of charge and the state of health of lithium-ion batteries.In this paper,we review the current widely used equivalent circuit and electrochemical models for battery state predictions.The review demonstrates that machine learning and deep learning approaches can be used to construct fast and accurate data-driven models for the prediction of battery performance.The details,advantages,and limitations of these approaches are presented,compared,and summarized.Finally,future key challenges and opportunities are discussed.展开更多
When considering the mechanism of the batteries,the capacity reduction at storage(when not in use)and cycling(during use)and increase of internal resistance is because of degradation in the chemical composition inside...When considering the mechanism of the batteries,the capacity reduction at storage(when not in use)and cycling(during use)and increase of internal resistance is because of degradation in the chemical composition inside the batteries.To optimize battery usage,a battery management system(BMS)is used to estimate possible aging effects while different load profiles are requested from the grid.This is specifically seen in a case when the vehicle is connected to the net(online through BMS).During this process,the BMS chooses the optimized load profiles based on the least aging effects on the battery pack.The major focus of this paper is to design an algorithm/model for lithium iron phosphate(LiFePO4)batteries.The model of the batteries is based on the accelerated aging test data(data from the beginning of life till the end of life).The objective is to develop an algorithm based on the actual battery trend during the whole life of the battery.By the analysis of the test data,the complete trend of the battery aging and the factors on which the aging is depending on is identified,the aging model can then be recalibrated to avoid any differences in the production process during cell manufacturing.The validation of the model was carried out at the end by utilizing different driving profiles at different C-rates and different ambient temperatures.A Linear and non-linear model-based approach is used based on statistical data.The parameterization was carried out by dividing the data into small chunks and estimating the parameters for the individual chunks.Self-adaptive characteristic map using a lookup table was also used.The nonlinear model was chosen as the best candidate among all other approaches for longer validation of 8-month data with real driving data set.展开更多
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 e...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.展开更多
The state of health(SOH) plays a significant role in the mileage and safety of an electric vehicle(EV). In recent years, many methods based on data-driven analysis and laboratory measurements have been developed for S...The state of health(SOH) plays a significant role in the mileage and safety of an electric vehicle(EV). In recent years, many methods based on data-driven analysis and laboratory measurements have been developed for SOH estimation. However, most of these proposed methods cannot be applied to real-world EVs. Here, we present a method for SOH estimation based on realworld EV data. A battery-aging evaluation health index(HI) with a strong correlation to the SOH is retrieved from battery-aging data and then modified with thermal factors to depict the former SOH. Afterward, a local weighted linear-regression algorithm is used to qualitatively characterize the declining trend of the HI, which eliminates the local HI fluctuation caused by data noise.Subsequently, a series of features-of-interest(FOIs) is extracted according to the battery consistency, cell-voltage extrema, and cumulative mileage, and validated using the grey relational analysis. Finally, a battery-degradation model is built using the extreme gradient-boosting algorithm with the selected FOIs. The experimental results from real-world data indicate that the proposed method has high estimation accuracy and generalization, and the maximum error is around 2% for batteries in realworld EVs.展开更多
As the lithium-ion battery is widely applied,the reliability of the battery has become a high-profile content in recent years.Accurate estimation and prediction of state of health(SOH)and remaining useful life(RUL)pre...As the lithium-ion battery is widely applied,the reliability of the battery has become a high-profile content in recent years.Accurate estimation and prediction of state of health(SOH)and remaining useful life(RUL)prediction are crucial for battery management systems.In this paper,the core contribution is the construction of a datadriven model with the long short-term memory(LSTM)network applicable to the time-series regression prediction problem with the integration of two methods,data-driven methods and feature signal analysis.The input features of model are extracted from differential thermal voltammetry(DTV)curves,which could characterize the battery degradation characteristics,so that the accurate prediction of battery capacity fade could be accomplished.Firstly,the DTV curve is smoothed by the Savitzky-Golay filter,and six alternate features are selected based on the connection between DTV curves and battery degradation characteristics.Then,a correlation analysis method is used to further filter the input features and three features that are highly associated with capacity fade are selected as input into the data driven model.The LSTM neural network is trained by using the root mean square propagation(RMSprop)technique and the dropout technique.Finally,the data of four batteries with different health levels are deployed for model construction,verification and comparison.The results show that the proposed method has high accuracy in SOH and RUL prediction and the capacity rebound phenomenon can be accurately estimated.This method can greatly reduce the cost and complexity,and increase the practicability,which provides the basis and guidance for battery data collection and the application of cloud technology and digital twin.展开更多
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 m...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.展开更多
Using electric vehicles(EVs)for transportation is considered as a necessary component for managing sustainable development and environmental issues.The present concerns regarding the environment,such as rapid fossil f...Using electric vehicles(EVs)for transportation is considered as a necessary component for managing sustainable development and environmental issues.The present concerns regarding the environment,such as rapid fossil fuel depletion,increases in air pollution,accelerating energy demands,global warming,and climate change,have paved the way for the electrification of the transport sector.EVs can address all of the aforementioned issues.Portable power supplies have become the lifeline of the EV world,especially lithium-ion(Li-ion)batteries.Li-ion batteries have attracted considerable attention in the EV industry,owing to their high energy density,power density,lifespan,nominal voltage,and cost.One major issue with such batteries concerns providing a quick and accurate estimation of a battery’s state and health;therefore,accurate determinations of the battery’S performance and health,as well as an accurate prediction of its life,are necessary to ensure reliability and efficiency.This study conducts a review of the technological briefs of EVs and their types,as well as the corresponding battery characteristics.Various aspects of recent research and developments in Li-ion battery prognostics and health monitoring are summarized,along with the techniques,algorithms,and models used for current/voltage estimations,state-of-charge(SoC)estimations,capacity estimations,and remaining-useful-life predictions.展开更多
Battery packs are applied in various areas(e.g.,electric vehicles,energy storage,space,mining,etc.),which requires the state of health(SOH)to be accurately estimated.Inconsistency,also known as cell variation,is consi...Battery packs are applied in various areas(e.g.,electric vehicles,energy storage,space,mining,etc.),which requires the state of health(SOH)to be accurately estimated.Inconsistency,also known as cell variation,is considered a significant evaluation index that greatly affects the degradation of battery pack.This paper proposes a novel joint inconsistency and SOH estimation method under cycling,which fills the gap of joint estimation based on the fast-charging process for electric vehicles.First,fifteen features are extracted from current change points during the partial charging process.Then,a joint estimation system is designed,where fusion weights are obtained by the analytic hierarchy process and multi-scale sample entropy to evaluate inconsistency.A wrapper is used to select the optimal feature subset,and Gaussian process regression is implemented to estimate the SOH.Finally,the estimation performance is assessed by the test data.The results show that the inconsistency evaluation can reflect the aging conditions,and the inconsistency does affect the aging process.The wrapper selection method improves the accuracy of SOH estimation by about 75.8%compared to the traditional filter method when only 10%of data is used for model training.The maximum absolute error and root mean square error are 2.58%and 0.93%,respectively.展开更多
Addressing climate change demands a significant shift away from fossil fuels,with sectors like electricity and transportation relying heavily on renewable energy.Integral to this transition are energy storage systems,...Addressing climate change demands a significant shift away from fossil fuels,with sectors like electricity and transportation relying heavily on renewable energy.Integral to this transition are energy storage systems,notably lithium-ion batteries.Over time,these batteries degrade,affecting their efficiency and posing safety risks.Monitoring and predicting battery aging is essential,especially estimating its state of health(SOH).Various SOH estimation methods exist,from traditional model-based approaches to machine learning approaches.展开更多
This paper analyzes the system-level state of health(SOH)and its dependence on the SOHs of its component battery modules.Due to stochastic natures of battery aging processes and their dependence on charge/discharge ra...This paper analyzes the system-level state of health(SOH)and its dependence on the SOHs of its component battery modules.Due to stochastic natures of battery aging processes and their dependence on charge/discharge rate and depth,operating temperature,and environment conditions,capacities of battery modules decay unevenly and randomly.Based on estimated SOHs of battery modules during battery operation,we analyze how the SOH of the entire system deteriorates when battery modules age and become increasingly diverse in their capacities.A rigorous mathematical analysis of system-level capacity utilization is conducted.It is shown that for large battery strings with uniformly distributed capacities,the average string capacity approaches the minimum,implying an asymptotically near worst-case capacity utility without reorganization.It is demonstrated that the overall battery usable capacities can be more efficiently utilized to achieve extended operational ranges by using battery reconfiguration.An optimal regrouping algorithm is introduced.Analysis methods,simulation examples,and a case study using real-world battery data are presented.展开更多
Lithium-ion batteries are key drivers of the renewable energy revolution,bolstered by progress in battery design,modelling,and management.Yet,achieving high-performance battery health prognostics is a significant chal...Lithium-ion batteries are key drivers of the renewable energy revolution,bolstered by progress in battery design,modelling,and management.Yet,achieving high-performance battery health prognostics is a significant challenge.With the availability of open data and software,coupled with automated simulations,deep learning has become an integral component of battery health prognostics.We offer a comprehensive overview of potential deep learning techniques specifically designed for modeling and forecasting the dynamics of multiphysics and multiscale battery systems.Following this,we provide a concise summary of publicly available lithium-ion battery test and cycle datasets.By providing illustrative examples,we emphasize the efficacy of five techniques capable of enhancing deep learning for accurate battery state prediction and health-focused management.Each of these techniques offers unique benefits.(1)Transformer models address challenges using self-attention mechanisms and positional encoding methods.(2) Transfer learning improves learning tasks within a target domain by leveraging knowledge from a source domain.(3) Physics-informed learning uses prior knowledge to enhance learning algorithms.(4)Generative adversarial networks(GANs) earn praise for their ability to generate diverse and high-quality outputs,exhibiting outstanding performance with complex datasets.(5) Deep reinforcement learning enables an agent to make optimal decisions through continuous interactions with its environment,thus maximizing cumulative rewards.In this Review,we highlight examples that employ these techniques for battery health prognostics,summarizing both their challenges and opportunities.These methodologies offer promising prospects for researchers and industry professionals,enabling the creation of specialized network architectures that autonomously extract features,especially for long-range spatial-temporal connections across extended timescales.The outcomes could include improved accuracy,faster training,and enhanced generalization.展开更多
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 p...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.展开更多
Capacity estimation plays a crucial role in battery management systems,and is essential for ensuring the safety and reliability of lithium-sulfur(Li-S)batteries.This paper proposes a method that uses a long short-term...Capacity estimation plays a crucial role in battery management systems,and is essential for ensuring the safety and reliability of lithium-sulfur(Li-S)batteries.This paper proposes a method that uses a long short-term memory(LSTM)neural network to estimate the state of health(SOH)of Li-S batteries.The method uses health features extracted from the charging curve and incre-mental capacity analysis(ICA)as input for the LSTM network.To enhance the robustness and accuracy of the network,the Adam algorithm is employed to optimize specific hyperparameters.Experimental data from three different groups of batteries with varying nominal capac-ities are used to validate the proposed method.The results demonstrate the effectiveness of the method in accurately estimating the capacity degradation of all three batteries.Also,the study examines the impact of different lengths of network training sets on capacity estimation.The results reveal that the ICA-LSTM model achieves a prediction accuracy of mean absolute error 4.6%and mean squared error 0.21%with three different training set lengths of 20%,40%,and 60%.The analysis demonstrates that the lightweight model maintains high SOH estimation accu-racy even with a small training set,and exhibits strong adaptive and generalization capabilities when applied to different Li-S batteries.Overall,the proposed method,supported by experimental validation and analysis,demonstrates its efficacy in ensuring accurate and reliable SOH estimation,thereby enhancing the safety and per-formance of Li-S batteries.Index Terms—Adam algorithm,incremental capacity analysis,Li-S battery,long short-term memory,state of health.展开更多
In the long-term prediction of battery degradation,the data-driven method has great potential with historical data recorded by the battery management system.This paper proposes an enhanced data-driven model for Lithiu...In the long-term prediction of battery degradation,the data-driven method has great potential with historical data recorded by the battery management system.This paper proposes an enhanced data-driven model for Lithium-ion(Li-ion)battery state of health(SOH)estimation with a superior modeling procedure and optimized features.The Gaussian process regression(GPR)method is adopted to establish the data-driven estimator,which enables Li-ion battery SOH estimation with the uncertainty level.A novel kernel function,with the prior knowledge of Li-ion battery degradation,is then introduced to improve the mod-eling capability of the GPR.As for the features,a two-stage processing structure is proposed to find a suitable partial charging voltage profile with high efficiency.In the first stage,an optimal partial charging voltage is selected by the grid search;while in the second stage,the principal component analysis is conducted to increase both estimation accuracy and computing efficiency.Advantages of the proposed method are validated on two datasets from different Li-ion batteries:Compared with other methods,the proposed method can achieve the same accuracy level in the Oxford dataset;while in Maryland dataset,the mean absolute error,the root-mean-squared error,and the maximum error are at least improved by 16.36%,32.43%,and 45.46%,respectively.展开更多
The estimation of state of health(SOH)of a lithium-ion battery(LIB)is of great significance to system safety and economic development.This paper proposes a SOH estimation method based on the SSA-Elman model for the fi...The estimation of state of health(SOH)of a lithium-ion battery(LIB)is of great significance to system safety and economic development.This paper proposes a SOH estimation method based on the SSA-Elman model for the first time.To improve the correlation rates between features and battery capacity,a method combining median absolute deviation filtering and Savitzky-Golay filtering is proposed to process the data.Based on the aging characteristics of the LIB,five features with correlation rates above 0.99 after data processing are then proposed.Addressing the defects of the Elman model,the sparrow search algorithm(SSA)is used to optimize the network parameters.In addition,a data incremental update mechanism is added to improve the generalization of the SSA-Elman model.Finally,the performance of the proposed model is verified based on NASA dataset,and the outputs of the Elman,LSTM and SSA-Elman models are compared.The results show that the proposed method can accurately estimate the SOH,with the root mean square error(RMSE)being as low as 0.0024 and the mean absolute percentage error(MAPE)being as low as 0.25%.In addition,RMSE does not exceed 0.0224 and MAPE does not exceed 2.21%in high temperature and low temperature verifications.展开更多
Accurate battery capacity prediction is important to ensure reliable battery operation and reduce the cost.However,the complex nature of battery degradation and the presence of capacity regeneration phenomenon render ...Accurate battery capacity prediction is important to ensure reliable battery operation and reduce the cost.However,the complex nature of battery degradation and the presence of capacity regeneration phenomenon render the prediction task very challenging.To address this problem,this paper proposes a novel and efficient algorithm to predict the battery capacity trajectory in a multi-cell setting.The proposed method is a new variant of Gaussian process regression(GPR)model,and it utilizes similar trajectories in the historical data to enhance the prediction of desired capacity trajectory.More importantly,the proposed method adds no extra computation cost to the standard GPR.To demonstrate the effectiveness of the proposed method,validation tests on two different battery datasets are implemented in the case studies.The prediction results and the computation cost are carefully benchmarked with cuttingedge GPR approaches for battery capacity prediction.展开更多
基金supported by National Natural Science Foundation of China (Grant No. 51677058)。
文摘With the rapid development of new energy technologies, lithium batteries are widely used in the field of energy storage systems and electric vehicles. The accurate prediction for the state of health(SOH) has an important role in maintaining a safe and stable operation of lithium-ion batteries. To address the problems of uncertain battery discharge conditions and low SOH estimation accuracy in practical applications, this paper proposes a SOH estimation method based on constant-current battery charging section characteristics with a back-propagation neural network with an improved atom search optimization algorithm. A temperature characteristic, equal-time temperature variation(Dt_DT), is proposed by analyzing the temperature data of the battery charging section with the incremental capacity(IC) characteristics obtained from an IC analysis as an input to the data-driven prediction model. Testing and analysis of the proposed prediction model are carried out using publicly available datasets. Experimental results show that the maximum error of SOH estimation results for the proposed method in this paper is below 1.5%.
基金funded by the “SMART BATTERY” project, granted by Villum Foundation in 2021 (project number 222860)。
文摘State of health(SoH) estimation plays a key role in smart battery health prognostic and management.However,poor generalization,lack of labeled data,and unused measurements during aging are still major challenges to accurate SoH estimation.Toward this end,this paper proposes a self-supervised learning framework to boost the performance of battery SoH estimation.Different from traditional data-driven methods which rely on a considerable training dataset obtained from numerous battery cells,the proposed method achieves accurate and robust estimations using limited labeled data.A filter-based data preprocessing technique,which enables the extraction of partial capacity-voltage curves under dynamic charging profiles,is applied at first.Unsupervised learning is then used to learn the aging characteristics from the unlabeled data through an auto-encoder-decoder.The learned network parameters are transferred to the downstream SoH estimation task and are fine-tuned with very few sparsely labeled data,which boosts the performance of the estimation framework.The proposed method has been validated under different battery chemistries,formats,operating conditions,and ambient.The estimation accuracy can be guaranteed by using only three labeled data from the initial 20% life cycles,with overall errors less than 1.14% and error distribution of all testing scenarios maintaining less than 4%,and robustness increases with aging.Comparisons with other pure supervised machine learning methods demonstrate the superiority of the proposed method.This simple and data-efficient estimation framework is promising in real-world applications under a variety of scenarios.
基金supported in part by the National Natural Science Foundation of China(92167201,62273264,61933007)。
文摘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.
基金financially supported by the National Natural Science Foundation of China(No.52102470)。
文摘Though the lithium-ion battery is universally applied,the reliability of lithium-ion batteries remains a challenge due to various physicochemical reactions,electrode material degradation,and even thermal runaway.Accurate estimation and prediction of battery health conditions are crucial for battery safety management.In this paper,an end-cloud collaboration method is proposed to approach the track of battery degradation process,integrating end-side empirical model with cloud-side data-driven model.Based on ensemble learning methods,the data-driven model is constructed by three base models to obtain cloud-side highly accurate results.The double exponential decay model is utilized as an empirical model to output highly real-time prediction results.With Kalman filter,the prediction results of end-side empirical model can be periodically updated by highly accurate results of cloud-side data-driven model to obtain highly accurate and real-time results.Subsequently,the whole framework can give an accurate prediction and tracking of battery degradation,with the mean absolute error maintained below 2%.And the execution time on the end side can reach 261μs.The proposed end-cloud collaboration method has the potential to approach highly accurate and highly real-time estimation for battery health conditions during battery full life cycle in architecture of cyber hierarchy and interactional network.
基金funding support from the Department of Science and Technology of Guangdong Province(2019A050510043)the Department of Science and Technology of Zhuhai City(ZH22017001200059PWC)+1 种基金the National Natural Science Foundation of China(2210050123)the China Postdoctoral Science Foundation(2021TQ0161 and 2021M691709)。
文摘In the field of energy storage,it is very important to predict the state of charge and the state of health of lithium-ion batteries.In this paper,we review the current widely used equivalent circuit and electrochemical models for battery state predictions.The review demonstrates that machine learning and deep learning approaches can be used to construct fast and accurate data-driven models for the prediction of battery performance.The details,advantages,and limitations of these approaches are presented,compared,and summarized.Finally,future key challenges and opportunities are discussed.
文摘When considering the mechanism of the batteries,the capacity reduction at storage(when not in use)and cycling(during use)and increase of internal resistance is because of degradation in the chemical composition inside the batteries.To optimize battery usage,a battery management system(BMS)is used to estimate possible aging effects while different load profiles are requested from the grid.This is specifically seen in a case when the vehicle is connected to the net(online through BMS).During this process,the BMS chooses the optimized load profiles based on the least aging effects on the battery pack.The major focus of this paper is to design an algorithm/model for lithium iron phosphate(LiFePO4)batteries.The model of the batteries is based on the accelerated aging test data(data from the beginning of life till the end of life).The objective is to develop an algorithm based on the actual battery trend during the whole life of the battery.By the analysis of the test data,the complete trend of the battery aging and the factors on which the aging is depending on is identified,the aging model can then be recalibrated to avoid any differences in the production process during cell manufacturing.The validation of the model was carried out at the end by utilizing different driving profiles at different C-rates and different ambient temperatures.A Linear and non-linear model-based approach is used based on statistical data.The parameterization was carried out by dividing the data into small chunks and estimating the parameters for the individual chunks.Self-adaptive characteristic map using a lookup table was also used.The nonlinear model was chosen as the best candidate among all other approaches for longer validation of 8-month data with real driving data set.
文摘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.
基金supported by the National Natural Science Foundation of China (Grant Nos. 61903114 and 62203423)the Anhui Provincial Natural Science Foundation (Grant No. 2008085QF301)+2 种基金the Youth Science and Technology Talents Support Program (2020) by Anhui Association for Science and Technology (Grant No. RCTJ202008)the Fundamental Research Funds for the Central Universities (Grant No. JZ2021HGTB0076)the Education and Scientific Research Project for Young and Middleaged Teachers in Fujian Province (Grant No. JAT201276)。
文摘The state of health(SOH) plays a significant role in the mileage and safety of an electric vehicle(EV). In recent years, many methods based on data-driven analysis and laboratory measurements have been developed for SOH estimation. However, most of these proposed methods cannot be applied to real-world EVs. Here, we present a method for SOH estimation based on realworld EV data. A battery-aging evaluation health index(HI) with a strong correlation to the SOH is retrieved from battery-aging data and then modified with thermal factors to depict the former SOH. Afterward, a local weighted linear-regression algorithm is used to qualitatively characterize the declining trend of the HI, which eliminates the local HI fluctuation caused by data noise.Subsequently, a series of features-of-interest(FOIs) is extracted according to the battery consistency, cell-voltage extrema, and cumulative mileage, and validated using the grey relational analysis. Finally, a battery-degradation model is built using the extreme gradient-boosting algorithm with the selected FOIs. The experimental results from real-world data indicate that the proposed method has high estimation accuracy and generalization, and the maximum error is around 2% for batteries in realworld EVs.
基金financially supported by the National Natural Science Foundation of China(No.52102470)the Science and Technology Development Project of Jilin province(No.20200501012GX)。
文摘As the lithium-ion battery is widely applied,the reliability of the battery has become a high-profile content in recent years.Accurate estimation and prediction of state of health(SOH)and remaining useful life(RUL)prediction are crucial for battery management systems.In this paper,the core contribution is the construction of a datadriven model with the long short-term memory(LSTM)network applicable to the time-series regression prediction problem with the integration of two methods,data-driven methods and feature signal analysis.The input features of model are extracted from differential thermal voltammetry(DTV)curves,which could characterize the battery degradation characteristics,so that the accurate prediction of battery capacity fade could be accomplished.Firstly,the DTV curve is smoothed by the Savitzky-Golay filter,and six alternate features are selected based on the connection between DTV curves and battery degradation characteristics.Then,a correlation analysis method is used to further filter the input features and three features that are highly associated with capacity fade are selected as input into the data driven model.The LSTM neural network is trained by using the root mean square propagation(RMSprop)technique and the dropout technique.Finally,the data of four batteries with different health levels are deployed for model construction,verification and comparison.The results show that the proposed method has high accuracy in SOH and RUL prediction and the capacity rebound phenomenon can be accurately estimated.This method can greatly reduce the cost and complexity,and increase the practicability,which provides the basis and guidance for battery data collection and the application of cloud technology and digital twin.
基金supported by China Postdoctoral Science Foundation(2021M690740)supported by project of the study on the gradient utilization and industrialization demonstration of lithium-ion power battery(ZH01110405180053PWC).
文摘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.
基金by Department of Science and Technology,New Delhi(Indo-Norway consortium)project entitled“Integrated Renewable Resources and Storage Operation and Management”program.
文摘Using electric vehicles(EVs)for transportation is considered as a necessary component for managing sustainable development and environmental issues.The present concerns regarding the environment,such as rapid fossil fuel depletion,increases in air pollution,accelerating energy demands,global warming,and climate change,have paved the way for the electrification of the transport sector.EVs can address all of the aforementioned issues.Portable power supplies have become the lifeline of the EV world,especially lithium-ion(Li-ion)batteries.Li-ion batteries have attracted considerable attention in the EV industry,owing to their high energy density,power density,lifespan,nominal voltage,and cost.One major issue with such batteries concerns providing a quick and accurate estimation of a battery’s state and health;therefore,accurate determinations of the battery’S performance and health,as well as an accurate prediction of its life,are necessary to ensure reliability and efficiency.This study conducts a review of the technological briefs of EVs and their types,as well as the corresponding battery characteristics.Various aspects of recent research and developments in Li-ion battery prognostics and health monitoring are summarized,along with the techniques,algorithms,and models used for current/voltage estimations,state-of-charge(SoC)estimations,capacity estimations,and remaining-useful-life predictions.
基金This work was supported in part by the National Natural Science Foundation of China(Grant No.51875054 and Grant No.U1864212)Graduate research and innovation foundation of Chongqing,China(Grant No.CYS20018)Chongqing Natural Science Foundation for Distinguished Young Scholars(Grant No.cstc2019jcyjjq0010),and Chongqing Science and Technology Bureau,China.
文摘Battery packs are applied in various areas(e.g.,electric vehicles,energy storage,space,mining,etc.),which requires the state of health(SOH)to be accurately estimated.Inconsistency,also known as cell variation,is considered a significant evaluation index that greatly affects the degradation of battery pack.This paper proposes a novel joint inconsistency and SOH estimation method under cycling,which fills the gap of joint estimation based on the fast-charging process for electric vehicles.First,fifteen features are extracted from current change points during the partial charging process.Then,a joint estimation system is designed,where fusion weights are obtained by the analytic hierarchy process and multi-scale sample entropy to evaluate inconsistency.A wrapper is used to select the optimal feature subset,and Gaussian process regression is implemented to estimate the SOH.Finally,the estimation performance is assessed by the test data.The results show that the inconsistency evaluation can reflect the aging conditions,and the inconsistency does affect the aging process.The wrapper selection method improves the accuracy of SOH estimation by about 75.8%compared to the traditional filter method when only 10%of data is used for model training.The maximum absolute error and root mean square error are 2.58%and 0.93%,respectively.
基金supported by the National Natural Science Foundation of China(72201152 and 52207229)。
文摘Addressing climate change demands a significant shift away from fossil fuels,with sectors like electricity and transportation relying heavily on renewable energy.Integral to this transition are energy storage systems,notably lithium-ion batteries.Over time,these batteries degrade,affecting their efficiency and posing safety risks.Monitoring and predicting battery aging is essential,especially estimating its state of health(SOH).Various SOH estimation methods exist,from traditional model-based approaches to machine learning approaches.
基金supported in part by the Army Research Office(W911NF-19-1-0176).
文摘This paper analyzes the system-level state of health(SOH)and its dependence on the SOHs of its component battery modules.Due to stochastic natures of battery aging processes and their dependence on charge/discharge rate and depth,operating temperature,and environment conditions,capacities of battery modules decay unevenly and randomly.Based on estimated SOHs of battery modules during battery operation,we analyze how the SOH of the entire system deteriorates when battery modules age and become increasingly diverse in their capacities.A rigorous mathematical analysis of system-level capacity utilization is conducted.It is shown that for large battery strings with uniformly distributed capacities,the average string capacity approaches the minimum,implying an asymptotically near worst-case capacity utility without reorganization.It is demonstrated that the overall battery usable capacities can be more efficiently utilized to achieve extended operational ranges by using battery reconfiguration.An optimal regrouping algorithm is introduced.Analysis methods,simulation examples,and a case study using real-world battery data are presented.
文摘Lithium-ion batteries are key drivers of the renewable energy revolution,bolstered by progress in battery design,modelling,and management.Yet,achieving high-performance battery health prognostics is a significant challenge.With the availability of open data and software,coupled with automated simulations,deep learning has become an integral component of battery health prognostics.We offer a comprehensive overview of potential deep learning techniques specifically designed for modeling and forecasting the dynamics of multiphysics and multiscale battery systems.Following this,we provide a concise summary of publicly available lithium-ion battery test and cycle datasets.By providing illustrative examples,we emphasize the efficacy of five techniques capable of enhancing deep learning for accurate battery state prediction and health-focused management.Each of these techniques offers unique benefits.(1)Transformer models address challenges using self-attention mechanisms and positional encoding methods.(2) Transfer learning improves learning tasks within a target domain by leveraging knowledge from a source domain.(3) Physics-informed learning uses prior knowledge to enhance learning algorithms.(4)Generative adversarial networks(GANs) earn praise for their ability to generate diverse and high-quality outputs,exhibiting outstanding performance with complex datasets.(5) Deep reinforcement learning enables an agent to make optimal decisions through continuous interactions with its environment,thus maximizing cumulative rewards.In this Review,we highlight examples that employ these techniques for battery health prognostics,summarizing both their challenges and opportunities.These methodologies offer promising prospects for researchers and industry professionals,enabling the creation of specialized network architectures that autonomously extract features,especially for long-range spatial-temporal connections across extended timescales.The outcomes could include improved accuracy,faster training,and enhanced generalization.
文摘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.
基金This work is supported by the Zhejiang Province Natural Science Foundation(No.LY22E070007)National Natural Science Foundation of China(No.52007170).
文摘Capacity estimation plays a crucial role in battery management systems,and is essential for ensuring the safety and reliability of lithium-sulfur(Li-S)batteries.This paper proposes a method that uses a long short-term memory(LSTM)neural network to estimate the state of health(SOH)of Li-S batteries.The method uses health features extracted from the charging curve and incre-mental capacity analysis(ICA)as input for the LSTM network.To enhance the robustness and accuracy of the network,the Adam algorithm is employed to optimize specific hyperparameters.Experimental data from three different groups of batteries with varying nominal capac-ities are used to validate the proposed method.The results demonstrate the effectiveness of the method in accurately estimating the capacity degradation of all three batteries.Also,the study examines the impact of different lengths of network training sets on capacity estimation.The results reveal that the ICA-LSTM model achieves a prediction accuracy of mean absolute error 4.6%and mean squared error 0.21%with three different training set lengths of 20%,40%,and 60%.The analysis demonstrates that the lightweight model maintains high SOH estimation accu-racy even with a small training set,and exhibits strong adaptive and generalization capabilities when applied to different Li-S batteries.Overall,the proposed method,supported by experimental validation and analysis,demonstrates its efficacy in ensuring accurate and reliable SOH estimation,thereby enhancing the safety and per-formance of Li-S batteries.Index Terms—Adam algorithm,incremental capacity analysis,Li-S battery,long short-term memory,state of health.
基金This work is financially supported by the Natural Science Foundation of China under Grant 52107229the Fundamental Research Funds for the Sichuan Science and Technology Program under Grant 2021YJ0063+2 种基金the China Postdoctoral Science Foundation under Grant 2020M673218Hunan High-tech Industry Science and Technology Innovation Plan under Grant 2020GK2081the Fund of Robot Technology Used for Special Environment Key Laboratory of Sichuan Province under Grant 20KFKT02.
文摘In the long-term prediction of battery degradation,the data-driven method has great potential with historical data recorded by the battery management system.This paper proposes an enhanced data-driven model for Lithium-ion(Li-ion)battery state of health(SOH)estimation with a superior modeling procedure and optimized features.The Gaussian process regression(GPR)method is adopted to establish the data-driven estimator,which enables Li-ion battery SOH estimation with the uncertainty level.A novel kernel function,with the prior knowledge of Li-ion battery degradation,is then introduced to improve the mod-eling capability of the GPR.As for the features,a two-stage processing structure is proposed to find a suitable partial charging voltage profile with high efficiency.In the first stage,an optimal partial charging voltage is selected by the grid search;while in the second stage,the principal component analysis is conducted to increase both estimation accuracy and computing efficiency.Advantages of the proposed method are validated on two datasets from different Li-ion batteries:Compared with other methods,the proposed method can achieve the same accuracy level in the Oxford dataset;while in Maryland dataset,the mean absolute error,the root-mean-squared error,and the maximum error are at least improved by 16.36%,32.43%,and 45.46%,respectively.
基金supported by the Youth Fund of Shandong Province Natural Science Foundation (No.ZR2020QE212)Key Projects of Shandong Province Natural Science Foundation (No.ZR2020KF020)+2 种基金the Guangdong Provincial Key Lab of Green Chemical Product Technology (GC202111)Zhejiang Province Natural Science Foundation (No.LY22E070007)National Natural Science Foundation of China (No.52007170).
文摘The estimation of state of health(SOH)of a lithium-ion battery(LIB)is of great significance to system safety and economic development.This paper proposes a SOH estimation method based on the SSA-Elman model for the first time.To improve the correlation rates between features and battery capacity,a method combining median absolute deviation filtering and Savitzky-Golay filtering is proposed to process the data.Based on the aging characteristics of the LIB,five features with correlation rates above 0.99 after data processing are then proposed.Addressing the defects of the Elman model,the sparrow search algorithm(SSA)is used to optimize the network parameters.In addition,a data incremental update mechanism is added to improve the generalization of the SSA-Elman model.Finally,the performance of the proposed model is verified based on NASA dataset,and the outputs of the Elman,LSTM and SSA-Elman models are compared.The results show that the proposed method can accurately estimate the SOH,with the root mean square error(RMSE)being as low as 0.0024 and the mean absolute percentage error(MAPE)being as low as 0.25%.In addition,RMSE does not exceed 0.0224 and MAPE does not exceed 2.21%in high temperature and low temperature verifications.
文摘Accurate battery capacity prediction is important to ensure reliable battery operation and reduce the cost.However,the complex nature of battery degradation and the presence of capacity regeneration phenomenon render the prediction task very challenging.To address this problem,this paper proposes a novel and efficient algorithm to predict the battery capacity trajectory in a multi-cell setting.The proposed method is a new variant of Gaussian process regression(GPR)model,and it utilizes similar trajectories in the historical data to enhance the prediction of desired capacity trajectory.More importantly,the proposed method adds no extra computation cost to the standard GPR.To demonstrate the effectiveness of the proposed method,validation tests on two different battery datasets are implemented in the case studies.The prediction results and the computation cost are carefully benchmarked with cuttingedge GPR approaches for battery capacity prediction.
