Accurately predicting the knee point cycle number,marking the onset of accelerated capacity degradation,is the first critical signal for managing lithium-ion battery life cycles in electric vehicles and stationary ene...Accurately predicting the knee point cycle number,marking the onset of accelerated capacity degradation,is the first critical signal for managing lithium-ion battery life cycles in electric vehicles and stationary energy storage systems.However,the inherent electrochemo-mechanical-thermal complexities of battery aging present significant challenges for physics-based models and machine-learning models,often leading to reduced predictive accuracy.Our study developed a comprehensive dataset comprising 20 lithium nickel manganese cobalt oxide(NCM)/graphite cells(0.5-1 C)from our lab and 162 commercial lithium iron phosphate(LFP)/graphite cells(3-6 C)from the public database,with knee point observed between 100 and 1000 cycles.We proposed a new strategy to extract novel features with strong physical context from early-cycle voltage curves,enabling precise knee point predictions across the chemistries without the need for extensive cycling histories.Our model achieved a mean absolute percentage error(MAPE)of 7%for knee point prediction using five selected features.Remarkably,the model yielded 8%MAPE with only one single feature across the initial 200 cycles,and 10%MAPE when applying five features across the initial 50 cycles,spanning different battery chemistries.This work highlights the potential of integrating multi-chemistry datasets with data-driven modeling to forecast aging patterns across diverse battery chemistries,advancing battery longevity and reliability.展开更多
The development of battery electric(BE)heavy-duty trucks(HDTs)is highly limited to the short cycling life of batteries.In this paper,we propose a battery aging-conscious control strategy for extended battery life by o...The development of battery electric(BE)heavy-duty trucks(HDTs)is highly limited to the short cycling life of batteries.In this paper,we propose a battery aging-conscious control strategy for extended battery life by optimizing the speed trajectory of BE HDT.A state-space model is constructed by connecting the vehicle dynamics and battery state of charge,and a mechanism-based aging model of battery is then introduced to formulate the optimization problem for minimal battery aging and energy consumption.The optimization problem is solved within a model predictive control framework for the real-time speed control of the vehicle.A non-cooperative platooning controller is further developed for the vehicle in adaptation to the traffic,where the intervehicular distance is controlled for reducing the air drag coefficient so that both the energy consumption and battery aging are improved.Simulation results show that for the single-vehicle controller,the battery degradation and energy consumption are,respectively,reduced by up to 25.7%and 3.2%compared with the cruise control strategy.Based on the non-cooperative controller,the HDT is able to follow preceding vehicles with different parameters with battery aging and energy consumption further,respectively,reduced by 2%–5%and 9%–10%compared with those of the single-vehicle controller.展开更多
One battery energy storage system(BESS)can be used to provide different services,such as energy arbitrage(EA)and frequency regulation(FR)support,etc.,which have different revenues and lead to different battery degrada...One battery energy storage system(BESS)can be used to provide different services,such as energy arbitrage(EA)and frequency regulation(FR)support,etc.,which have different revenues and lead to different battery degradation profiles.This paper proposes a whole-lifetime coordinated service strategy to maximize the total operation profit of BESS.A multi-stage battery aging model is developed to characterize the battery aging rates during the whole lifetime.Considering the uncertainty of electricity price in EA service and frequency deviation in FR service,the whole problem is formulated as a twostage stochastic programming problem.At the first stage,the optimal service switching scheme between the EA and FR services are formulated to maximize the expected value of the whole-lifetime operation profit.At the second stage,the output power of BESS in EA service is optimized according to the electricity price in the hourly timescale,whereas the output power of BESS in FR service is directly determined according to the frequency deviation in the second timescale.The above optimization problem is then converted as a deterministic mixed-integer nonlinear programming(MINLP)model with bilinear items.Mc Cormick envelopes and a bound tightening algorithm are used to solve it.Numerical simulation is carried out to validate the effectiveness and advantages of the proposed strategy.展开更多
In order to suppress the battery aging of electric vehicles(EVs),a multi-objective optimization function is established to describe the battery aging behavior based on a high-precision battery aging model,and the stat...In order to suppress the battery aging of electric vehicles(EVs),a multi-objective optimization function is established to describe the battery aging behavior based on a high-precision battery aging model,and the state–space equation is then constructed to reveal the intrinsic relationship between vehicle speed,acceleration,and battery state-of-charge(SOC).The constructed optimization model is solved by using a sequential quadratic programming(SQP)algorithm,and based on the model predictive control(MPC)theory,the efficient real-time control of vehicle speed is achieved.Simulation results show that the developed strategy extends the battery life by 10.33%compared to the baseline strategy when the traffic flow is not involved.In the case of involving the traffic flow,the optimization results of battery aging improves as the look-ahead time period increases,while the computational burden increases.The results show that the developed strategy reduces the battery aging of the target vehicle by 33.02%compared to the preceding vehicle while meeting the real-time requirement.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
With the assistance of artificial intelligence,advanced health prognosis technique plays a critical role in the lithium-ion(Li-ion) batteries management system.However,conventional data-driven early aging prediction e...With the assistance of artificial intelligence,advanced health prognosis technique plays a critical role in the lithium-ion(Li-ion) batteries management system.However,conventional data-driven early aging prediction exhibited dramatic drawbacks,i.e.,volatile capacity nonlinear fading trajectories create obstacles to the accurate multistep ahead prediction due to the complex working conditions of batteries.Herein,a novel deep learning model is proposed to achieve a universal and accurate Li-ion battery aging prognosis.Two battery datasets with various electrode types and cycling conditions are developed to validate the proposed approaches.Knee-point probability(KPP),extracted from the capacity loss curve,is first proposed to detect knee points and improve state-of-health(SOH) predictive accuracy,especially during periods of rapid capacity decline.Using one-cycle data of partial raw voltage as the model input,the SOH and KPP can be simultaneously predicted at multistep ahead,whereas the conventional method showed worse accuracy.Furthermore,to explore the underlying characteristics among various degradation tendencies,an online model update strategy is developed by leveraging the adversarial adaptationinduced transfer learning technique.This work gains new sights into the comprehensive Li-ion battery management and prognosis framework through decomposing capacity degradation trajectories and adversarial learning on the unlabeled samples.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
With the wide application of the LFP lithium-ion batteries,more attention is paid to the battery life and future aging behaviors as the safety and performance of the battery are guaranteed by accurate battery aging mo...With the wide application of the LFP lithium-ion batteries,more attention is paid to the battery life and future aging behaviors as the safety and performance of the battery are guaranteed by accurate battery aging monitoring.In recent years,long-term aging trajectory prediction of the lithium-ion battery is always a challenge due to its complex nonlinear aging behaviors especially the aging behaviors in the two aging stages are quite different when the battery experiences the two-stage aging process under fast-charging conditions.Thus,it is harder to achieve accurate long-term aging trajectory prediction of the LFP lithium-ion batteries on the condition of the two-stage aging process.To address it,a novel transfer learning strategy combined with the cycle life prediction technology is presented in this paper.Specifically,a new cycle life prediction method is proposed based on feature extraction and deep learning technology and achieves accurate cycle life prediction.The transfer learning is started by developing a base aging model offline to learn the information of the two-stage aging process.Then,taking the predicted cycle life as its prior information,the Bayesian model migration technology is employed to predict the aging trajectory accurately,and the uncertainty of the aging trajectory is quantified.Two batches of the battery datasets are used for performance evaluation and comparison with two benchmarks.It is novel to combine the cycle life prediction and transfer learning technique to achieve accurate two-stage aging trajectory prediction with only a few data available(first 30%).展开更多
As lithium-ion batteries(LIBs)become increasingly widespread,ensuring their safety has become a primary concern.Particularly,battery aging has been reported to significantly impact major battery safety behaviors,inclu...As lithium-ion batteries(LIBs)become increasingly widespread,ensuring their safety has become a primary concern.Particularly,battery aging has been reported to significantly impact major battery safety behaviors,including the internal short circuit(ISC)and thermal runaway(TR).Over the past decade,despite consider-able research into the thermal hazards of aged batteries,the complexity of battery aging and TR mecha-nisms,along with the challenges posed by extreme experimental conditions,necessitates a systematic under-standing.Aiming to provide a comprehensive review of safety issues related to aged batteries,this paper begins by exploring the fundamental aging mechanisms and factors that accelerate aging.It then investi-gates how aging affects battery safety issues,including swelling and off-gassing behaviors.Furthermore,we discuss the impact of aging on TR problems induced by abusive conditions,covering safety issues from inter-nal sources to external abusive scenarios.This review offers valuable insights into understanding and predict-ing the thermal hazards of aged LIBs,which provides guidelines for designing and manufacturing safer LIBs and accurate and rapid battery safety prognostics in the future.展开更多
The vanadium redox flow battery(VRFB)is an emerging energy storage technology featuring long cycle life.During its operation,VRFB requires periodic maintenance to restore its capacity.To thoroughly understand and anal...The vanadium redox flow battery(VRFB)is an emerging energy storage technology featuring long cycle life.During its operation,VRFB requires periodic maintenance to restore its capacity.To thoroughly understand and analyse its aging characteristics,accurate modelling of VRFB is crucial.In this paper,a hybrid physics-based and data-driven modelling framework is proposed for VRFB.First,a reduced-order electrochemical model for VRFB is established considering two main aging mechanisms:electrolyte volume transfer and ion crossover.Then,two key empirical parameters related to the aging dynamic are fully analysed.Finally,a Kolmogorov-Arnold network(KAN)is constructed with prior information from the electrochemical model to produce high-precision voltage prediction.A real-world test platform is built to validate the proposed method.It achieves the maximum prediction error of less than 1%in short,middle,and long-term aging experiments.展开更多
Accurate estimation of lithium-ion battery state of charge(SOC)is crucial for the safe and efficient operation of electric vehicles(EVs).However,both data-driven and model-driven SOC estimation methods face significan...Accurate estimation of lithium-ion battery state of charge(SOC)is crucial for the safe and efficient operation of electric vehicles(EVs).However,both data-driven and model-driven SOC estimation methods face significant challenges under battery aging,which alters internal resistance and electrochemical properties,especially across complex aging trajectories.Most existing deep learning and model-based approaches operate in an open-loop manner,lacking mechanisms for uncertainty quantification,accuracy prediction,or adaptive correction—leading to uncontrolled estimation errors during aging.To address this,we propose an innovative closed-loop SOC estimation framework that integrates active learning with uncertainty-aware correction into deep learning networks,enabling real-time feedback on SOC prediction confidence levels without the need for additional sensors or reference data.Specifically,we quantify the performance degradation of mainstream data-driven methods,including long short-term memory(LSTM)networks and Gaussian process regression(GPR),under complex aging paths.We demonstrate that our model-disagreement-based active learning correction strategy maintains robustness throughout the battery lifecycle.Experimental results show that with only four active retraining sessions over the full aging process,our method reduces average SOC estimation error to below 1.5%,and maximum cycle-based average error to below 2%.This work establishes a path toward uncertaintyinformed,lifecycle-resilient,and data-efficient SOC estimation,marking a significant advancement in battery management systems for real-world EV applications.展开更多
The increasing use of lithium-ion cells in large-scale,long-term applications drives a need for design methods that considers aging and accurate state of health estimation.A common approach is to rely on an empirical ...The increasing use of lithium-ion cells in large-scale,long-term applications drives a need for design methods that considers aging and accurate state of health estimation.A common approach is to rely on an empirical or semiempirical aging model fit to experimental data to estimate the evolution of capacity and power fade.Because aging data are costly to collect,pack designers either use Design of Experiment(DOE)techniques to define a set of efficient tests,or use existing aging data to calibrate aging models.Given the increasing quantity of available aging data,the question arises:how can experimental aging campaigns be quickly compared?However,a methodology for the comparison of sets of aging experiments is not discussed in the literature.As a result,pack designers usually rely on intuition to select between multiple aging studies proposed by DOE techniques or in the literature.This work proposes metrics to quantitatively capture the alignment between a set of aging experiments and a target application.These metrics allow pack designers to quickly compare many sets of aging experiments to evaluate those which have tested conditions relevant to the application.Case studies are presented to illustrate the application of these metrics using aging campaign data from the literature.To validate these metrics,this work examines the relationship between these metric values and aging model validation error for calendar aging data for 18650 NMC battery cells.It is demonstrated that greater metric values correspond to reduced model error for an empirical capacity fade model.展开更多
An accurate driving cycle prediction is a vital function of an onboard energy management strategy(EMS)for a battery/ultracapacitor hybrid energy storage system(HESS)in electric vehicles.In this paper,we address the re...An accurate driving cycle prediction is a vital function of an onboard energy management strategy(EMS)for a battery/ultracapacitor hybrid energy storage system(HESS)in electric vehicles.In this paper,we address the requirements to achieve better EMS performances for a HESS.First,a long short-term niemory・based method is proposed to predict driving cycles under the framework of a model predictive control(MPC)algorithm.Secondly,the performances of three EMSs based on fuzzy logic,MPC,and dynamic programming are systematically evaluated and analyzed.For online implementation,the MPC-based EMS can alleviate the stress on the battery in the HESS and significantly reduce energy dissipation by up to 15.3% in comparison with the fuzzy logic-based EMS.Thirdly,the impact of battery aging on EMS performances is explored;it indicates that battery aging consciousness can slightly extend battery life.Finally,a hardware-in-the-loop test platform is established to verify the effectiveness of the MPC-based EMS for the power allocation of a HESS in electric vehicles.展开更多
基金supported by Startup funding from the University of Delaware。
文摘Accurately predicting the knee point cycle number,marking the onset of accelerated capacity degradation,is the first critical signal for managing lithium-ion battery life cycles in electric vehicles and stationary energy storage systems.However,the inherent electrochemo-mechanical-thermal complexities of battery aging present significant challenges for physics-based models and machine-learning models,often leading to reduced predictive accuracy.Our study developed a comprehensive dataset comprising 20 lithium nickel manganese cobalt oxide(NCM)/graphite cells(0.5-1 C)from our lab and 162 commercial lithium iron phosphate(LFP)/graphite cells(3-6 C)from the public database,with knee point observed between 100 and 1000 cycles.We proposed a new strategy to extract novel features with strong physical context from early-cycle voltage curves,enabling precise knee point predictions across the chemistries without the need for extensive cycling histories.Our model achieved a mean absolute percentage error(MAPE)of 7%for knee point prediction using five selected features.Remarkably,the model yielded 8%MAPE with only one single feature across the initial 200 cycles,and 10%MAPE when applying five features across the initial 50 cycles,spanning different battery chemistries.This work highlights the potential of integrating multi-chemistry datasets with data-driven modeling to forecast aging patterns across diverse battery chemistries,advancing battery longevity and reliability.
基金funded by the Research Start-Up Funding of Chongqing University(Grant No.02090011044160)the National Natural Science Foundation of China(Grant No.51907136)。
文摘The development of battery electric(BE)heavy-duty trucks(HDTs)is highly limited to the short cycling life of batteries.In this paper,we propose a battery aging-conscious control strategy for extended battery life by optimizing the speed trajectory of BE HDT.A state-space model is constructed by connecting the vehicle dynamics and battery state of charge,and a mechanism-based aging model of battery is then introduced to formulate the optimization problem for minimal battery aging and energy consumption.The optimization problem is solved within a model predictive control framework for the real-time speed control of the vehicle.A non-cooperative platooning controller is further developed for the vehicle in adaptation to the traffic,where the intervehicular distance is controlled for reducing the air drag coefficient so that both the energy consumption and battery aging are improved.Simulation results show that for the single-vehicle controller,the battery degradation and energy consumption are,respectively,reduced by up to 25.7%and 3.2%compared with the cruise control strategy.Based on the non-cooperative controller,the HDT is able to follow preceding vehicles with different parameters with battery aging and energy consumption further,respectively,reduced by 2%–5%and 9%–10%compared with those of the single-vehicle controller.
基金partially supported by T-RECs Energy Pte.Ltd.under project(No.04IDS000719N014)。
文摘One battery energy storage system(BESS)can be used to provide different services,such as energy arbitrage(EA)and frequency regulation(FR)support,etc.,which have different revenues and lead to different battery degradation profiles.This paper proposes a whole-lifetime coordinated service strategy to maximize the total operation profit of BESS.A multi-stage battery aging model is developed to characterize the battery aging rates during the whole lifetime.Considering the uncertainty of electricity price in EA service and frequency deviation in FR service,the whole problem is formulated as a twostage stochastic programming problem.At the first stage,the optimal service switching scheme between the EA and FR services are formulated to maximize the expected value of the whole-lifetime operation profit.At the second stage,the output power of BESS in EA service is optimized according to the electricity price in the hourly timescale,whereas the output power of BESS in FR service is directly determined according to the frequency deviation in the second timescale.The above optimization problem is then converted as a deterministic mixed-integer nonlinear programming(MINLP)model with bilinear items.Mc Cormick envelopes and a bound tightening algorithm are used to solve it.Numerical simulation is carried out to validate the effectiveness and advantages of the proposed strategy.
基金Research Start-Up Funding of Chongqing University under Grant 02090011044160.
文摘In order to suppress the battery aging of electric vehicles(EVs),a multi-objective optimization function is established to describe the battery aging behavior based on a high-precision battery aging model,and the state–space equation is then constructed to reveal the intrinsic relationship between vehicle speed,acceleration,and battery state-of-charge(SOC).The constructed optimization model is solved by using a sequential quadratic programming(SQP)algorithm,and based on the model predictive control(MPC)theory,the efficient real-time control of vehicle speed is achieved.Simulation results show that the developed strategy extends the battery life by 10.33%compared to the baseline strategy when the traffic flow is not involved.In the case of involving the traffic flow,the optimization results of battery aging improves as the look-ahead time period increases,while the computational burden increases.The results show that the developed strategy reduces the battery aging of the target vehicle by 33.02%compared to the preceding vehicle while meeting the real-time requirement.
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 by the financial support from the National Key Research and Development Program of China(2022YFB3807200)the Fundamental Research Funds for the Central Universities(2242022K330047)+3 种基金the dual creative talents from Jiangsu Province(JSSCBS20210152,JSSCBS20210100)the National Natural Science Foundation of Jiangsu Province(BK20221456,BK20200375)the Natural Science Foundation of China with(22109021)the Research Fund Program of Guangdong Provincial Key Lab of Green Chemical Product Technology(6802008024)。
文摘With the assistance of artificial intelligence,advanced health prognosis technique plays a critical role in the lithium-ion(Li-ion) batteries management system.However,conventional data-driven early aging prediction exhibited dramatic drawbacks,i.e.,volatile capacity nonlinear fading trajectories create obstacles to the accurate multistep ahead prediction due to the complex working conditions of batteries.Herein,a novel deep learning model is proposed to achieve a universal and accurate Li-ion battery aging prognosis.Two battery datasets with various electrode types and cycling conditions are developed to validate the proposed approaches.Knee-point probability(KPP),extracted from the capacity loss curve,is first proposed to detect knee points and improve state-of-health(SOH) predictive accuracy,especially during periods of rapid capacity decline.Using one-cycle data of partial raw voltage as the model input,the SOH and KPP can be simultaneously predicted at multistep ahead,whereas the conventional method showed worse accuracy.Furthermore,to explore the underlying characteristics among various degradation tendencies,an online model update strategy is developed by leveraging the adversarial adaptationinduced transfer learning technique.This work gains new sights into the comprehensive Li-ion battery management and prognosis framework through decomposing capacity degradation trajectories and adversarial learning on the unlabeled samples.
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.
基金the National Natural Science Foundation of China(No.52172400).
文摘With the wide application of the LFP lithium-ion batteries,more attention is paid to the battery life and future aging behaviors as the safety and performance of the battery are guaranteed by accurate battery aging monitoring.In recent years,long-term aging trajectory prediction of the lithium-ion battery is always a challenge due to its complex nonlinear aging behaviors especially the aging behaviors in the two aging stages are quite different when the battery experiences the two-stage aging process under fast-charging conditions.Thus,it is harder to achieve accurate long-term aging trajectory prediction of the LFP lithium-ion batteries on the condition of the two-stage aging process.To address it,a novel transfer learning strategy combined with the cycle life prediction technology is presented in this paper.Specifically,a new cycle life prediction method is proposed based on feature extraction and deep learning technology and achieves accurate cycle life prediction.The transfer learning is started by developing a base aging model offline to learn the information of the two-stage aging process.Then,taking the predicted cycle life as its prior information,the Bayesian model migration technology is employed to predict the aging trajectory accurately,and the uncertainty of the aging trajectory is quantified.Two batches of the battery datasets are used for performance evaluation and comparison with two benchmarks.It is novel to combine the cycle life prediction and transfer learning technique to achieve accurate two-stage aging trajectory prediction with only a few data available(first 30%).
基金support from the research project from FM and startup funds provided by the University of Delaware.
文摘As lithium-ion batteries(LIBs)become increasingly widespread,ensuring their safety has become a primary concern.Particularly,battery aging has been reported to significantly impact major battery safety behaviors,including the internal short circuit(ISC)and thermal runaway(TR).Over the past decade,despite consider-able research into the thermal hazards of aged batteries,the complexity of battery aging and TR mecha-nisms,along with the challenges posed by extreme experimental conditions,necessitates a systematic under-standing.Aiming to provide a comprehensive review of safety issues related to aged batteries,this paper begins by exploring the fundamental aging mechanisms and factors that accelerate aging.It then investi-gates how aging affects battery safety issues,including swelling and off-gassing behaviors.Furthermore,we discuss the impact of aging on TR problems induced by abusive conditions,covering safety issues from inter-nal sources to external abusive scenarios.This review offers valuable insights into understanding and predict-ing the thermal hazards of aged LIBs,which provides guidelines for designing and manufacturing safer LIBs and accurate and rapid battery safety prognostics in the future.
基金supported by the National Natural Science Foundation of China[grant number 62325306][grant number62273237].
文摘The vanadium redox flow battery(VRFB)is an emerging energy storage technology featuring long cycle life.During its operation,VRFB requires periodic maintenance to restore its capacity.To thoroughly understand and analyse its aging characteristics,accurate modelling of VRFB is crucial.In this paper,a hybrid physics-based and data-driven modelling framework is proposed for VRFB.First,a reduced-order electrochemical model for VRFB is established considering two main aging mechanisms:electrolyte volume transfer and ion crossover.Then,two key empirical parameters related to the aging dynamic are fully analysed.Finally,a Kolmogorov-Arnold network(KAN)is constructed with prior information from the electrochemical model to produce high-precision voltage prediction.A real-world test platform is built to validate the proposed method.It achieves the maximum prediction error of less than 1%in short,middle,and long-term aging experiments.
基金funding support by the National Key R&D Program of China(Grant No.2022YFE0208000)the Shanghai Key Laboratory of Aerodynamics and Thermal Environment Simulation for Ground Vehicles(Grant No.23DZ2229029)+1 种基金the Shanghai Automotive Wind Tunnel Technical Service Platform(Grant No.19DZ2290400)the Fundamental Research Funds for the Central Universities.N.M.gratefully acknowledges the support of the Interna-tional Institute for Carbon Neutral Energy Research,sponsored by the Japanese Ministry of Education,Culture,Sports,Science and Technology.
文摘Accurate estimation of lithium-ion battery state of charge(SOC)is crucial for the safe and efficient operation of electric vehicles(EVs).However,both data-driven and model-driven SOC estimation methods face significant challenges under battery aging,which alters internal resistance and electrochemical properties,especially across complex aging trajectories.Most existing deep learning and model-based approaches operate in an open-loop manner,lacking mechanisms for uncertainty quantification,accuracy prediction,or adaptive correction—leading to uncontrolled estimation errors during aging.To address this,we propose an innovative closed-loop SOC estimation framework that integrates active learning with uncertainty-aware correction into deep learning networks,enabling real-time feedback on SOC prediction confidence levels without the need for additional sensors or reference data.Specifically,we quantify the performance degradation of mainstream data-driven methods,including long short-term memory(LSTM)networks and Gaussian process regression(GPR),under complex aging paths.We demonstrate that our model-disagreement-based active learning correction strategy maintains robustness throughout the battery lifecycle.Experimental results show that with only four active retraining sessions over the full aging process,our method reduces average SOC estimation error to below 1.5%,and maximum cycle-based average error to below 2%.This work establishes a path toward uncertaintyinformed,lifecycle-resilient,and data-efficient SOC estimation,marking a significant advancement in battery management systems for real-world EV applications.
基金supported by The Center for Automotive Research at The Ohio State University and the Department of Mechanical and Aerospace Engineering at The Ohio State University.
文摘The increasing use of lithium-ion cells in large-scale,long-term applications drives a need for design methods that considers aging and accurate state of health estimation.A common approach is to rely on an empirical or semiempirical aging model fit to experimental data to estimate the evolution of capacity and power fade.Because aging data are costly to collect,pack designers either use Design of Experiment(DOE)techniques to define a set of efficient tests,or use existing aging data to calibrate aging models.Given the increasing quantity of available aging data,the question arises:how can experimental aging campaigns be quickly compared?However,a methodology for the comparison of sets of aging experiments is not discussed in the literature.As a result,pack designers usually rely on intuition to select between multiple aging studies proposed by DOE techniques or in the literature.This work proposes metrics to quantitatively capture the alignment between a set of aging experiments and a target application.These metrics allow pack designers to quickly compare many sets of aging experiments to evaluate those which have tested conditions relevant to the application.Case studies are presented to illustrate the application of these metrics using aging campaign data from the literature.To validate these metrics,this work examines the relationship between these metric values and aging model validation error for calendar aging data for 18650 NMC battery cells.It is demonstrated that greater metric values correspond to reduced model error for an empirical capacity fade model.
基金supported by the National Science Foundation for Excellent Young Scholars of China(Grant No.51922006).
文摘An accurate driving cycle prediction is a vital function of an onboard energy management strategy(EMS)for a battery/ultracapacitor hybrid energy storage system(HESS)in electric vehicles.In this paper,we address the requirements to achieve better EMS performances for a HESS.First,a long short-term niemory・based method is proposed to predict driving cycles under the framework of a model predictive control(MPC)algorithm.Secondly,the performances of three EMSs based on fuzzy logic,MPC,and dynamic programming are systematically evaluated and analyzed.For online implementation,the MPC-based EMS can alleviate the stress on the battery in the HESS and significantly reduce energy dissipation by up to 15.3% in comparison with the fuzzy logic-based EMS.Thirdly,the impact of battery aging on EMS performances is explored;it indicates that battery aging consciousness can slightly extend battery life.Finally,a hardware-in-the-loop test platform is established to verify the effectiveness of the MPC-based EMS for the power allocation of a HESS in electric vehicles.
