The growing use of lithium-ion batteries in electric transportation and grid-scale storage systems has intensified the need for accurate and highly generalizable state-of-health(SOH)estimation.Conventional approaches ...The growing use of lithium-ion batteries in electric transportation and grid-scale storage systems has intensified the need for accurate and highly generalizable state-of-health(SOH)estimation.Conventional approaches often suffer from reduced accuracy under dynamically uncertain state-of-charge(SOC)operating ranges and heterogeneous aging stresses.This study presents a unified SOH estimation framework that integrates physics-informed modeling,subspace identification,and Transformer-based learning.A reduced-order model is derived from simplified electrochemical dynamics,providing an interpretable and computationally efficient representation of battery behavior.Subspace identification across a wide SOC and SOH range yields degradation-sensitive features,which the Transformer uses to capture long-range aging dynamics via multi-head self-attention.Experiments on LiFePO4 cells under joint-cell training show consistently accurate SOH estimation,with a maximum error of 1.39%,demonstrating the framework’s effectiveness in decoupling SOC and SOH effects.In cross-cell validation,where training and validation are performed on different cells,the model maintains a maximum error of 2.06%,confirming strong generalization to unseen aging trajectories.Comparative experiments on LiFePO_(4)and public LiCoO_(2)datasets confirm the framework’s cross-chemistry applicability.By extracting low-dimensional,physically interpretable features via subspace identification,the framework significantly reduces training cost while maintaining high SOH estimation accuracy,outperforming conventional data-driven models lacking physical guidance.展开更多
The burgeoning market for lithium-ion batteries has stimulated a growing need for more reliable battery performance monitoring. Accurate state-of-health(SOH) estimation is critical for ensuring battery operational per...The burgeoning market for lithium-ion batteries has stimulated a growing need for more reliable battery performance monitoring. Accurate state-of-health(SOH) estimation is critical for ensuring battery operational performance. Despite numerous data-driven methods reported in existing research for battery SOH estimation, these methods often exhibit inconsistent performance across different application scenarios. To address this issue and overcome the performance limitations of individual data-driven models,integrating multiple models for SOH estimation has received considerable attention. Ensemble learning(EL) typically leverages the strengths of multiple base models to achieve more robust and accurate outputs. However, the lack of a clear review of current research hinders the further development of ensemble methods in SOH estimation. Therefore, this paper comprehensively reviews multi-model ensemble learning methods for battery SOH estimation. First, existing ensemble methods are systematically categorized into 6 classes based on their combination strategies. Different realizations and underlying connections are meticulously analyzed for each category of EL methods, highlighting distinctions, innovations, and typical applications. Subsequently, these ensemble methods are comprehensively compared in terms of base models, combination strategies, and publication trends. Evaluations across 6 dimensions underscore the outstanding performance of stacking-based ensemble methods. Following this, these ensemble methods are further inspected from the perspectives of weighted ensemble and diversity, aiming to inspire potential approaches for enhancing ensemble performance. Moreover, addressing challenges such as base model selection, measuring model robustness and uncertainty, and interpretability of ensemble models in practical applications is emphasized. Finally, future research prospects are outlined, specifically noting that deep learning ensemble is poised to advance ensemble methods for battery SOH estimation. The convergence of advanced machine learning with ensemble learning is anticipated to yield valuable avenues for research. Accelerated research in ensemble learning holds promising prospects for achieving more accurate and reliable battery SOH estimation under real-world conditions.展开更多
Accurate estimation of lithium battery state-of-health(SOH)is essential for ensuring safe operation and efficient utilization.To address the challenges of complex degradation factors and unreliable feature extraction,...Accurate estimation of lithium battery state-of-health(SOH)is essential for ensuring safe operation and efficient utilization.To address the challenges of complex degradation factors and unreliable feature extraction,we develop a novel SOH prediction model integrating physical information constraints and multimodal feature fusion.Our approach employs a multi-channel encoder to process heterogeneous data modalities,including health indicators,raw charge/discharge sequences,and incremental capacity data,and uses multi-channel encoders to achieve structured input.A physics-informed loss function,derived from an empirical capacity decay equation,is incorporated to enforce interpretability,while a cross-layer attention mechanism dynamically weights features to handle missing modalities and random noise.Experimental validation on multiple battery types demonstrates that our model reduces mean absolute error(MAE)by at least 51.09%compared to unimodal baselines,maintains robustness under adverse conditions such as partial data loss,and achieves an average MAE of 0.0201 in real-world battery pack applications.This model significantly enhances the accuracy and universality of prediction,enabling accurate prediction of battery SOH under actual engineering conditions.展开更多
The state of charge （SOC） and state of health （SOH） are two of the most important parameters of Li-ion batteries in industrial production and in practical applications. The real-time estimation for these two param...The state of charge （SOC） and state of health （SOH） are two of the most important parameters of Li-ion batteries in industrial production and in practical applications. The real-time estimation for these two parameters is crucial to realize a safe and reliable battery application. However, this is a great problem for LiFePO4 batteries due to the large constant potential plateau in the charge/discharge process. Here we propose a combined SOC and SOH co-estimation method based on the experimental test under the simulating electric vehicle working condition. A first-order resistance-capacitance equivalent circuit is used to model the battery cell, and three parameter values, ohmic resistance （Rs）, parallel resistance （Rp） and parallel capacity （Cp）, are identified from a real-time experimental test. Finally we find that Rp and Cp could be utilized to make a judgement on the SOIl. More importantly, the linear relationship between Cp and the SOC is established to make the estimation of the SOC for the first time.展开更多
State-of-health(SOH) is one of the main factors for lithium-ion batteries that indicate their life information. Thus it is essential to estimate SOH accurately during the operation of lithium-ion batteries. In this pa...State-of-health(SOH) is one of the main factors for lithium-ion batteries that indicate their life information. Thus it is essential to estimate SOH accurately during the operation of lithium-ion batteries. In this paper, an SOH map is proposed to illustrate the SOH of lithium-ion batteries by an internal combustion engine(ICE) map approach. Both direct current internal resistance(DCR) and open circuit voltage(OCV) are key parameters of lithium-ion batteries, which are obtained through metering and computing. Due to serious affection by environmental temperature, temperature translation is proposed to translate DCR/OCV of different temperature into a nominal value at 25 ℃. Compared with ICE map, SOH map is illustrated by the nominal DCR and OCV, which can be looked up to get a nominal SOH. In the SOH map, a pair of the DCR and the OCV can only map out a unique SOH, which is beneficial for application in engineering practice in most cases.展开更多
The state-of-charge(SOC)and state-of-health(SOH)of lithium-ion batteries affect their operating performance and safety.The coupled SOC and SOH are difficult to estimate adaptively in multi-temperatures and aging.This ...The state-of-charge(SOC)and state-of-health(SOH)of lithium-ion batteries affect their operating performance and safety.The coupled SOC and SOH are difficult to estimate adaptively in multi-temperatures and aging.This paper proposes a novel transformer-embedded lithium-ion battery model for joint estimation of state-ofcharge and state-of-health.The battery model is formulated across temperatures and aging,which provides accurate feedback for unscented Kalman filter-based SOC estimation and aging information.The open-circuit voltages(OCVs)are corrected globally by the temporal convolutional network with accurate OCVs in time-sliding windows.Arrhenius equation is combined with estimated SOH for temperature-aging migration.A novel transformer model is introduced,which integrates multiscale attention with the transformer's encoder to incorporate SOC-voltage differential derived from battery model.This model simultaneously extracts local aging information from various sequences and aging channels using a self-attention and depth-separate convolution.By leveraging multi-head attention,the model establishes information dependency relationships across different aging levels,enabling rapid and precise SOH estimation.Specifically,the root mean square error for SOC and SOH under conditions of 15℃dynamic stress test and 25℃constant current cycling was less than 0.9%and 0.8%,respectively.Notably,the proposed method exhibits excellent adaptability to varying temperature and aging conditions,accurately estimating SOC and SOH.展开更多
Lithium-ion batteries(LIBs)are crucial for the large-scale utilization of clean energy.However,because of the com-plexity and real-time nature of internal reactions,the mechanism of capacity decline in LIBs is still u...Lithium-ion batteries(LIBs)are crucial for the large-scale utilization of clean energy.However,because of the com-plexity and real-time nature of internal reactions,the mechanism of capacity decline in LIBs is still unclear.This has become a bottleneck restricting their promotion and application.Electrochemical impedance spectroscopy(EIS)contains rich electrochemical connotations and significant application prospects,and has attracted widespread atten-tion and research on efficient energy storage systems.Compared to traditional voltage and current data,the state-of-health(SOH)estimation model based on EIS has higher accuracy.This paper categorizes EIS measurement methods based on different principles,introduces the relationship between LIBs aging mechanism and SOH,and compares the advantages of different SOH estimation methods.After a detailed analysis of the latest technologies,a review is given.The insights of this review can deepen the understanding of the relationship between EIS and the aging effect mechanism of LIBs,and promote the development of new energy storage devices and evaluation methods.展开更多
Estimation of state-of-charge and state-of-health for batteries is one of the most important feature for modern battery management system(BMS).Robust or adaptive methods are the most investigated because a more intell...Estimation of state-of-charge and state-of-health for batteries is one of the most important feature for modern battery management system(BMS).Robust or adaptive methods are the most investigated because a more intelligent BMS could lead to sensible cost reduction of the entire battery system.We propose a new robust method,called ERMES(extendible range multi-model estimator),for determining an estimated state-of-charge(SoC),an estimated state-of-health(SoH)and a prediction of uncertainty of the estimates(state-of-uncertainty—SoU),thanks to which it is possible to monitor the validity of the estimates and adjust it,extending the robustness against a wider range of uncertainty,if necessary.Specifically,a finite number of models in state-space form are considered starting from a modified Thevenin battery model.Each model is characterized by a hypothesis of SoH value.An iterated extended Kalman filter(EKF)is then applied to each model in parallel,estimating for each one the SoC state variable.Residual errors are then considered to fuse both the estimated SoC and SoH from the bank of EKF,yielding the overall SoC and SoH estimates,respectively.In addition,a figure of uncertainty of such estimates is also provided.展开更多
Energy storage batteries operating under high levels of renewable energy integration face signifi-cant power fluctuations and frequent charge-discharge cycles,leading to substantial errors and uncertainties in state-o...Energy storage batteries operating under high levels of renewable energy integration face signifi-cant power fluctuations and frequent charge-discharge cycles,leading to substantial errors and uncertainties in state-of-charge(SOC)estimation at short time scales.To address this challenge,this paper proposes a novel SOC estimation method by integrating adaptive forgetting factor recursive least squares(AFF-RLS)with a data-driven hybrid architecture based on bidirectional long short-term memory(BiLSTM)and Transformer model.A second-order equivalent RC circuit model is con-structed,and AFF-RLS is employed for real-time identi-fication of model parameters,which are subsequently used as input features for the BiLSTM-Transformer model.The learning rate is dynamically adjusted based on error variation,and network parameters are optimized using the Adam algorithm.The method is validated using experimental data obtained from lead-carbon batteries,with its reliability and robustness verified through widely accepted performance metrics,including mean absolute error,mean absolute percentage error,root mean square error,and the coefficient of determination.Comparative experiments against convolutional neural network,Transformer,and LSTM-based models indicate that the proposed SOC estimation method consistently achieves lower estimation errors within 1.5%across varying state-of-health,demonstrating superior accuracy and robustness.展开更多
Electrolysis is expected to play an essential role in future energy systems that rely on renewable energy sources,especially in achieving climate neutrality in sectors that are challenging to electrify directly.The ec...Electrolysis is expected to play an essential role in future energy systems that rely on renewable energy sources,especially in achieving climate neutrality in sectors that are challenging to electrify directly.The economic success of this technology is largely dependent on effective predictive maintenance,which requires a clear understanding of the systems’current and future state-of-health to ensure adequate replacement planning with decreasing efficiency and prevent undesired aging-related failures.Given the incomplete physical understanding and mathematical description of degradation processes,while more and more data is becoming available,data-driven machine learning models are increasingly moving into focus.These models can learn underlying relationships from data without necessitating prior knowledge.Therefore,this study concentrates on predicting the degradation trend of a proton exchange membrane water electrolysis cell using a data-driven machine learning approach.To this end,a comprehensive data-driven modeling matrix is proposed and evaluated through selected practically relevant modeling concepts,which are characterized by different combinations of available training data and desired model outputs.Experimentally,this is facilitated by a targeted accelerated stress test consisting of operating and characterization phases.The applied machine learning pipeline,covering the hierarchical sequence of necessary data preprocessing and modeling steps,is presented in detail to ensure the traceability and reproducibility of the methodology from data collection to model testing and evaluation.As a major finding,it was demonstrated that the degradation trend prediction for the entire polarization curve can be realized using only typical operating data.This represents an initial step toward predicting the complete cell characteristic without interrupting ongoing operation for corresponding measurements.展开更多
Lithium-ion batteries(LiB)are widely used in electric vehicles(EVs)and battery energy storage systems,and accurate state estimation relying on the relationship between battery Open-Circuit-Voltage(OCV)and State-of-Cha...Lithium-ion batteries(LiB)are widely used in electric vehicles(EVs)and battery energy storage systems,and accurate state estimation relying on the relationship between battery Open-Circuit-Voltage(OCV)and State-of-Charge(SOC)is the basis for their safe and efficient applications.To avoid the time-consuming lab test needed for obtaining OCV-SOC curves,this study proposes a data-driven universal method by using operation data collected onboard about the variation of OCV with ampere-hour(Ah).To guarantee high reliability,a series of constraints have been implemented.To verify the effectiveness of this method,the constructed OCV-SOC curves are used to estimate battery SOC and State-of-Health(SOH),which are compared with data from both lab tests and EV manufacturers.Results show that a higher accuracy can be achieved in the estimation of both SOC and SOH,for which the maximum deviations are less than 3.0%and 2.9%respectively.展开更多
The health management of batteries is a key enabler for the adoption of Electric Vertical Take-off and Landingvehicles (eVTOLs). Currently, few studies consider the health management of eVTOL batteries. One distinctch...The health management of batteries is a key enabler for the adoption of Electric Vertical Take-off and Landingvehicles (eVTOLs). Currently, few studies consider the health management of eVTOL batteries. One distinctcharacteristic of batteries for eVTOLs is that the discharge rates are significantly larger during take-off andlanding, compared with the battery discharge rates needed for automotives. Such discharge protocols areexpected to impact the long-run health of batteries. This paper proposes a data-driven machine learningframework to estimate the state-of-health and remaining-useful-lifetime of eVTOL batteries under varying flightconditions and taking into account the entire flight profile of the eVTOLs. Three main features are consideredfor the assessment of the health of the batteries: charge, discharge and temperature. The importance of thesefeatures is also quantified. Considering battery charging before flight, a selection of missions for state-ofhealth and remaining-useful-lifetime prediction is performed. The results show that indeed, discharge-relatedfeatures have the highest importance when predicting battery state-of-health and remaining-useful-lifetime.Using several machine learning algorithms, it is shown that the battery state-of-health and remaining-useful-lifeare well estimated using Random Forest regression and Extreme Gradient Boosting, respectively.展开更多
基金supported by the National Natural Science Foundation of China(No.52207228)the Beijing Natural Science Foundation,China(No.3224070)the National Natural Science Foundation of China(No.52077208).
文摘The growing use of lithium-ion batteries in electric transportation and grid-scale storage systems has intensified the need for accurate and highly generalizable state-of-health(SOH)estimation.Conventional approaches often suffer from reduced accuracy under dynamically uncertain state-of-charge(SOC)operating ranges and heterogeneous aging stresses.This study presents a unified SOH estimation framework that integrates physics-informed modeling,subspace identification,and Transformer-based learning.A reduced-order model is derived from simplified electrochemical dynamics,providing an interpretable and computationally efficient representation of battery behavior.Subspace identification across a wide SOC and SOH range yields degradation-sensitive features,which the Transformer uses to capture long-range aging dynamics via multi-head self-attention.Experiments on LiFePO4 cells under joint-cell training show consistently accurate SOH estimation,with a maximum error of 1.39%,demonstrating the framework’s effectiveness in decoupling SOC and SOH effects.In cross-cell validation,where training and validation are performed on different cells,the model maintains a maximum error of 2.06%,confirming strong generalization to unseen aging trajectories.Comparative experiments on LiFePO_(4)and public LiCoO_(2)datasets confirm the framework’s cross-chemistry applicability.By extracting low-dimensional,physically interpretable features via subspace identification,the framework significantly reduces training cost while maintaining high SOH estimation accuracy,outperforming conventional data-driven models lacking physical guidance.
基金National Natural Science Foundation of China (52075420)Fundamental Research Funds for the Central Universities (xzy022023049)National Key Research and Development Program of China (2023YFB3408600)。
文摘The burgeoning market for lithium-ion batteries has stimulated a growing need for more reliable battery performance monitoring. Accurate state-of-health(SOH) estimation is critical for ensuring battery operational performance. Despite numerous data-driven methods reported in existing research for battery SOH estimation, these methods often exhibit inconsistent performance across different application scenarios. To address this issue and overcome the performance limitations of individual data-driven models,integrating multiple models for SOH estimation has received considerable attention. Ensemble learning(EL) typically leverages the strengths of multiple base models to achieve more robust and accurate outputs. However, the lack of a clear review of current research hinders the further development of ensemble methods in SOH estimation. Therefore, this paper comprehensively reviews multi-model ensemble learning methods for battery SOH estimation. First, existing ensemble methods are systematically categorized into 6 classes based on their combination strategies. Different realizations and underlying connections are meticulously analyzed for each category of EL methods, highlighting distinctions, innovations, and typical applications. Subsequently, these ensemble methods are comprehensively compared in terms of base models, combination strategies, and publication trends. Evaluations across 6 dimensions underscore the outstanding performance of stacking-based ensemble methods. Following this, these ensemble methods are further inspected from the perspectives of weighted ensemble and diversity, aiming to inspire potential approaches for enhancing ensemble performance. Moreover, addressing challenges such as base model selection, measuring model robustness and uncertainty, and interpretability of ensemble models in practical applications is emphasized. Finally, future research prospects are outlined, specifically noting that deep learning ensemble is poised to advance ensemble methods for battery SOH estimation. The convergence of advanced machine learning with ensemble learning is anticipated to yield valuable avenues for research. Accelerated research in ensemble learning holds promising prospects for achieving more accurate and reliable battery SOH estimation under real-world conditions.
基金Project(2023YFB2303704-07)supported by the National Natural Science Foundation of China。
文摘Accurate estimation of lithium battery state-of-health(SOH)is essential for ensuring safe operation and efficient utilization.To address the challenges of complex degradation factors and unreliable feature extraction,we develop a novel SOH prediction model integrating physical information constraints and multimodal feature fusion.Our approach employs a multi-channel encoder to process heterogeneous data modalities,including health indicators,raw charge/discharge sequences,and incremental capacity data,and uses multi-channel encoders to achieve structured input.A physics-informed loss function,derived from an empirical capacity decay equation,is incorporated to enforce interpretability,while a cross-layer attention mechanism dynamically weights features to handle missing modalities and random noise.Experimental validation on multiple battery types demonstrates that our model reduces mean absolute error(MAE)by at least 51.09%compared to unimodal baselines,maintains robustness under adverse conditions such as partial data loss,and achieves an average MAE of 0.0201 in real-world battery pack applications.This model significantly enhances the accuracy and universality of prediction,enabling accurate prediction of battery SOH under actual engineering conditions.
基金Supported by the Guangdong Innovation Team Project under Grant No 2013N080the Peacock Plan of Shenzhen Science and Technology Research under Grant No KYPT20141016105435850
文摘The state of charge （SOC） and state of health （SOH） are two of the most important parameters of Li-ion batteries in industrial production and in practical applications. The real-time estimation for these two parameters is crucial to realize a safe and reliable battery application. However, this is a great problem for LiFePO4 batteries due to the large constant potential plateau in the charge/discharge process. Here we propose a combined SOC and SOH co-estimation method based on the experimental test under the simulating electric vehicle working condition. A first-order resistance-capacitance equivalent circuit is used to model the battery cell, and three parameter values, ohmic resistance （Rs）, parallel resistance （Rp） and parallel capacity （Cp）, are identified from a real-time experimental test. Finally we find that Rp and Cp could be utilized to make a judgement on the SOIl. More importantly, the linear relationship between Cp and the SOC is established to make the estimation of the SOC for the first time.
基金Sponsored by the National Key Research and Development Program of China(Grant No.2017YFB0103104)the Science and Technology Special Project of Anhui Province(Grant No.18030901063)。
文摘State-of-health(SOH) is one of the main factors for lithium-ion batteries that indicate their life information. Thus it is essential to estimate SOH accurately during the operation of lithium-ion batteries. In this paper, an SOH map is proposed to illustrate the SOH of lithium-ion batteries by an internal combustion engine(ICE) map approach. Both direct current internal resistance(DCR) and open circuit voltage(OCV) are key parameters of lithium-ion batteries, which are obtained through metering and computing. Due to serious affection by environmental temperature, temperature translation is proposed to translate DCR/OCV of different temperature into a nominal value at 25 ℃. Compared with ICE map, SOH map is illustrated by the nominal DCR and OCV, which can be looked up to get a nominal SOH. In the SOH map, a pair of the DCR and the OCV can only map out a unique SOH, which is beneficial for application in engineering practice in most cases.
基金financially supported by the Science and Technology Major Project of Fujian Province of China(No.2022HZ028018)the National Natural Science Foundation of China(No.51907030)。
文摘The state-of-charge(SOC)and state-of-health(SOH)of lithium-ion batteries affect their operating performance and safety.The coupled SOC and SOH are difficult to estimate adaptively in multi-temperatures and aging.This paper proposes a novel transformer-embedded lithium-ion battery model for joint estimation of state-ofcharge and state-of-health.The battery model is formulated across temperatures and aging,which provides accurate feedback for unscented Kalman filter-based SOC estimation and aging information.The open-circuit voltages(OCVs)are corrected globally by the temporal convolutional network with accurate OCVs in time-sliding windows.Arrhenius equation is combined with estimated SOH for temperature-aging migration.A novel transformer model is introduced,which integrates multiscale attention with the transformer's encoder to incorporate SOC-voltage differential derived from battery model.This model simultaneously extracts local aging information from various sequences and aging channels using a self-attention and depth-separate convolution.By leveraging multi-head attention,the model establishes information dependency relationships across different aging levels,enabling rapid and precise SOH estimation.Specifically,the root mean square error for SOC and SOH under conditions of 15℃dynamic stress test and 25℃constant current cycling was less than 0.9%and 0.8%,respectively.Notably,the proposed method exhibits excellent adaptability to varying temperature and aging conditions,accurately estimating SOC and SOH.
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Lithium-ion batteries(LIBs)are crucial for the large-scale utilization of clean energy.However,because of the com-plexity and real-time nature of internal reactions,the mechanism of capacity decline in LIBs is still unclear.This has become a bottleneck restricting their promotion and application.Electrochemical impedance spectroscopy(EIS)contains rich electrochemical connotations and significant application prospects,and has attracted widespread atten-tion and research on efficient energy storage systems.Compared to traditional voltage and current data,the state-of-health(SOH)estimation model based on EIS has higher accuracy.This paper categorizes EIS measurement methods based on different principles,introduces the relationship between LIBs aging mechanism and SOH,and compares the advantages of different SOH estimation methods.After a detailed analysis of the latest technologies,a review is given.The insights of this review can deepen the understanding of the relationship between EIS and the aging effect mechanism of LIBs,and promote the development of new energy storage devices and evaluation methods.
文摘Estimation of state-of-charge and state-of-health for batteries is one of the most important feature for modern battery management system(BMS).Robust or adaptive methods are the most investigated because a more intelligent BMS could lead to sensible cost reduction of the entire battery system.We propose a new robust method,called ERMES(extendible range multi-model estimator),for determining an estimated state-of-charge(SoC),an estimated state-of-health(SoH)and a prediction of uncertainty of the estimates(state-of-uncertainty—SoU),thanks to which it is possible to monitor the validity of the estimates and adjust it,extending the robustness against a wider range of uncertainty,if necessary.Specifically,a finite number of models in state-space form are considered starting from a modified Thevenin battery model.Each model is characterized by a hypothesis of SoH value.An iterated extended Kalman filter(EKF)is then applied to each model in parallel,estimating for each one the SoC state variable.Residual errors are then considered to fuse both the estimated SoC and SoH from the bank of EKF,yielding the overall SoC and SoH estimates,respectively.In addition,a figure of uncertainty of such estimates is also provided.
基金supported by the National Natural Science Foundation of China(No.52037003)the Major Science and Technology Projects in Yunnan Province(No.202402AG050006)Yunnan Fundamental Research Projects(No.202401BE070001-014).
文摘Energy storage batteries operating under high levels of renewable energy integration face signifi-cant power fluctuations and frequent charge-discharge cycles,leading to substantial errors and uncertainties in state-of-charge(SOC)estimation at short time scales.To address this challenge,this paper proposes a novel SOC estimation method by integrating adaptive forgetting factor recursive least squares(AFF-RLS)with a data-driven hybrid architecture based on bidirectional long short-term memory(BiLSTM)and Transformer model.A second-order equivalent RC circuit model is con-structed,and AFF-RLS is employed for real-time identi-fication of model parameters,which are subsequently used as input features for the BiLSTM-Transformer model.The learning rate is dynamically adjusted based on error variation,and network parameters are optimized using the Adam algorithm.The method is validated using experimental data obtained from lead-carbon batteries,with its reliability and robustness verified through widely accepted performance metrics,including mean absolute error,mean absolute percentage error,root mean square error,and the coefficient of determination.Comparative experiments against convolutional neural network,Transformer,and LSTM-based models indicate that the proposed SOC estimation method consistently achieves lower estimation errors within 1.5%across varying state-of-health,demonstrating superior accuracy and robustness.
基金financial support by the Federal Ministry of Education and Research of Germany in the frame-work of SEGIWA(grant no.03HY121G)HyThroughGen(grant no.3HY108C)as part of the hydrogen flagship project H2Giga.
文摘Electrolysis is expected to play an essential role in future energy systems that rely on renewable energy sources,especially in achieving climate neutrality in sectors that are challenging to electrify directly.The economic success of this technology is largely dependent on effective predictive maintenance,which requires a clear understanding of the systems’current and future state-of-health to ensure adequate replacement planning with decreasing efficiency and prevent undesired aging-related failures.Given the incomplete physical understanding and mathematical description of degradation processes,while more and more data is becoming available,data-driven machine learning models are increasingly moving into focus.These models can learn underlying relationships from data without necessitating prior knowledge.Therefore,this study concentrates on predicting the degradation trend of a proton exchange membrane water electrolysis cell using a data-driven machine learning approach.To this end,a comprehensive data-driven modeling matrix is proposed and evaluated through selected practically relevant modeling concepts,which are characterized by different combinations of available training data and desired model outputs.Experimentally,this is facilitated by a targeted accelerated stress test consisting of operating and characterization phases.The applied machine learning pipeline,covering the hierarchical sequence of necessary data preprocessing and modeling steps,is presented in detail to ensure the traceability and reproducibility of the methodology from data collection to model testing and evaluation.As a major finding,it was demonstrated that the degradation trend prediction for the entire polarization curve can be realized using only typical operating data.This represents an initial step toward predicting the complete cell characteristic without interrupting ongoing operation for corresponding measurements.
文摘Lithium-ion batteries(LiB)are widely used in electric vehicles(EVs)and battery energy storage systems,and accurate state estimation relying on the relationship between battery Open-Circuit-Voltage(OCV)and State-of-Charge(SOC)is the basis for their safe and efficient applications.To avoid the time-consuming lab test needed for obtaining OCV-SOC curves,this study proposes a data-driven universal method by using operation data collected onboard about the variation of OCV with ampere-hour(Ah).To guarantee high reliability,a series of constraints have been implemented.To verify the effectiveness of this method,the constructed OCV-SOC curves are used to estimate battery SOC and State-of-Health(SOH),which are compared with data from both lab tests and EV manufacturers.Results show that a higher accuracy can be achieved in the estimation of both SOC and SOH,for which the maximum deviations are less than 3.0%and 2.9%respectively.
文摘The health management of batteries is a key enabler for the adoption of Electric Vertical Take-off and Landingvehicles (eVTOLs). Currently, few studies consider the health management of eVTOL batteries. One distinctcharacteristic of batteries for eVTOLs is that the discharge rates are significantly larger during take-off andlanding, compared with the battery discharge rates needed for automotives. Such discharge protocols areexpected to impact the long-run health of batteries. This paper proposes a data-driven machine learningframework to estimate the state-of-health and remaining-useful-lifetime of eVTOL batteries under varying flightconditions and taking into account the entire flight profile of the eVTOLs. Three main features are consideredfor the assessment of the health of the batteries: charge, discharge and temperature. The importance of thesefeatures is also quantified. Considering battery charging before flight, a selection of missions for state-ofhealth and remaining-useful-lifetime prediction is performed. The results show that indeed, discharge-relatedfeatures have the highest importance when predicting battery state-of-health and remaining-useful-lifetime.Using several machine learning algorithms, it is shown that the battery state-of-health and remaining-useful-lifeare well estimated using Random Forest regression and Extreme Gradient Boosting, respectively.
