Thermal safety boundary of lithium-ion battery at different state of charge

Thermal runaway(TR)is a critical issue hindering the large-scale application of lithium-ion batteries(LIBs).Understanding the thermal safety behavior of LIBs at the cell and module level under different state of charges(SOCs)has significant implications for reinforcing the thermal safety design of the lithium-ion battery module.This study first investigates the thermal safety boundary(TSB)correspondence at the cells and modules level under the guidance of a newly proposed concept,safe electric quantity boundary(SEQB).A reasonable thermal runaway propagation(TRP)judgment indicator,peak heat transfer power(PHTP),is proposed to predict whether TRP occurs.Moreover,a validated 3D model is used to quantitatively clarify the TSB at different SOCs from the perspective of PHTP,TR trigger temperature,SOC,and the full cycle life.Besides,three different TRP transfer modes are discovered.The interconversion relationship of three different TRP modes is investigated from the perspective of PHTP.This paper explores the TSB of LIBs under different SOCs at both cell and module levels for the first time,which has great significance in guiding the thermal safety design of battery systems.

Explainable Neural Network for Sensitivity Analysis of Lithium-ion Battery Smart Production

Battery production is crucial for determining the quality of electrode,which in turn affects the manufactured battery performance.As battery production is complicated with strongly coupled intermediate and control parameters,an efficient solution that can perform a reliable sensitivity analysis of the production terms of interest and forecast key battery properties in the early production phase is urgently required.This paper performs detailed sensitivity analysis of key production terms on determining the properties of manufactured battery electrode via advanced data-driven modelling.To be specific,an explainable neural network named generalized additive model with structured interaction(GAM-SI)is designed to predict two key battery properties,including electrode mass loading and porosity,while the effects of four early production terms on manufactured batteries are explained and analysed.The experimental results reveal that the proposed method is able to accurately predict battery electrode properties in the mixing and coating stages.In addition,the importance ratio ranking,global interpretation and local interpretation of both the main effects and pairwise interactions can be effectively visualized by the designed neural network.Due to the merits of interpretability,the proposed GAM-SI can help engineers gain important insights for understanding complicated production behavior,further benefitting smart battery production.

Small but mighty:Empowering sodium/potassium-ion battery performance with S-doped SnO_(2) quantum dots embedded in N,S codoped carbon fiber network

SnO_(2) has been extensively investigated as an anode material for sodium-ion batteries(SIBs)and potassium-ion batteries(PIBs)due to its high Na/K storage capacity,high abundance,and low toxicity.However,the sluggish reaction kinetics,low electronic conductivity,and large volume changes during charge and discharge hinder the practical applications of SnO_(2)-based electrodes for SIBs and PIBs.Engineering rational structures with fast charge/ion transfer and robust stability is important to overcoming these challenges.Herein,S-doped SnO_(2)(S-SnO_(2))quantum dots(QDs)(≈3 nm)encapsulated in an N,S codoped carbon fiber networks(S-SnO_(2)-CFN)are rationally fabricated using a sequential freeze-drying,calcination,and S-doping strategy.Experimental analysis and density functional theory calculations reveal that the integration of S-SnO_(2) QDs with N,S codoped carbon fiber network remarkably decreases the adsorption energies of Na/K atoms in the interlayer of SnO_(2)-CFN,and the S doping can increase the conductivity of SnO_(2),thereby enhancing the ion transfer kinetics.The synergistic interaction between S-SnO_(2) QDs and N,S codoped carbon fiber network results in a composite with fast Na+/K+storage and extraordinary long-term cyclability.Specifically,the S-SnO_(2)-CFN delivers high rate capacities of 141.0 mAh g^(−1) at 20 A g^(−1) in SIBs and 102.8 mAh g^(−1) at 10 A g^(−1) in PIBs.Impressively,it delivers ultra-stable sodium storage up to 10,000 cycles at 5 A g^(−1) and potassium storage up to 5000 cycles at 2 A g^(−1).This study provides insights into constructing metal oxide-based carbon fiber network structures for high-performance electrochemical energy storage and conversion devices.

High-performance magnesium/sodium hybrid ion battery based on sodium vanadate oxide for reversible storage of Na^(+)and Mg^(2+)

Magnesium ion batteries(MIBs)are a potential field for the energy storage of the future but are restricted by insufficient rate capability and rapid capacity degradation.Magnesium-sodium hybrid ion batteries(MSHBs)are an effective way to address these problems.Here,we report a new type of MSHBs that use layered sodium vanadate((Na,Mn)V_(8)O_(20)·5H_(2)O,Mn-NVO)cathodes coupled with an organic 3,4,9,10-perylenetetracarboxylic diimide(PTCDI)anode in Mg^(2+)/Na^(+)hybrid electrolytes.During electrochemical cycling,Mg^(2+)and Na^(+)co-participate in the cathode reactions,and the introduction of Na^(+)promotes the structural stability of the Mn-NVO cathode,as cleared by several ex-situ characterizations.Consequently,the Mn-NVO cathode presents great specific capacity(249.9 mA h g^(−1)at 300 mA g^(−1))and cycling(1500 cycles at 1500 mA g^(−1))in the Mg^(2+)/Na^(+)hybrid electrolytes.Besides,full battery displays long lifespan with 10,000 cycles at 1000 mA g^(−1).The rate performance and cycling stability of MSHBs have been improved by an economical and scalable method,and the mechanism for these improvements is discussed.

An aqueous BiI_(3)-Zn battery with dual mechanisms of Zn^(2+)(de)intercalation and I^(-)/I_(2)redox

The development of aqueous battery with dual mechanisms is now arousing more and more interest.The dual mechanisms of Zn^(2+)(de)intercalation and I^(-)/I_(2)redox bring unexpected effects.Herein,differing from previous studies using Zn I_(2)additive,this work designs an aqueous Bi I_(3)-Zn battery with selfsupplied I^(-).Ex situ tests reveal the conversion of Bi I_(3)into Bi(discharge)and Bi OI(charge)at the 1st cycle and the dissolved I^(-)in electrolyte.The active I^(-)species enhances the specific capacity and discharge medium voltage of electrode as well as improves the generation of Zn dendrite and by-product.Furthermore,the porous hard carbon is introduced to enhance the electronic/ionic conductivity and adsorb iodine species,proven by experimental and theoretical studies.Accordingly,the well-designed Bi I_(3)-Zn battery delivers a high reversible capacity of 182 m A h g^(-1)at 0.2 A g^(-1),an excellent rate capability with 88 m A h g^(-1)at 10 A g^(-1),and an impressive cyclability with 63%capacity retention over 20 K cycles at 10 A g^(-1).An excellent electrochemical performance is obtained even at a high mass loading of 6 mg cm^(-2).Moreover,a flexible quasi-solid-state Bi I_(3)-Zn battery exhibits satisfactory battery performances.This work provides a new idea for designing high-performance aqueous battery with dual mechanisms.

Enhancing I^(0)/I^(-)Conversion Efficiency by Starch Confinement in Zinc-lodine Battery

The redox couple of I^(0)/I^(-)in aqueous rechargeable iodine–zinc(I^(2)-Zn)batteries is a promising energy storage resource since it is safe and cost-effective,and provides steady output voltage.However,the cycle life and efficiency of these batteries remain unsatisfactory due to the uncontrolled shuttling of polyiodide(I_(3)^(-)and I_(5)^(-))and side reactions on the Zn anode.Starch is a very low-cost and widely sourced food used daily around the world.“Starch turns blue when it encounters iodine”is a classic chemical reaction,which results from the unique structure of the helix starch molecule–iodine complex.Inspired by this,we employ starch to confine the shuttling of polyiodide,and thus,the I^(0)/I^(-)conversion efficiency of an I^(2)-Zn battery is clearly enhanced.According to the detailed characterizations and theoretical DFT calculation results,the enhancement of I^(0)/I^(-)conversion efficiency is mainly originated from the strong bonding between the charged products of I_(3)^(-)and I_(5)^(-)and the rich hydroxyl groups in starch.This work provides inspiration for the rational design of high-performance and low-cost I^(2)-Zn in AZIBs.

Trifunctional robust electrocatalysts based on 3D Fe/N-doped carbon nanocubes encapsulating Co4N nanoparticles for efficient battery-powered water electrolyzers

Herein,we have designed a highly active and robust trifunctional electrocatalyst derived from Prussian blue analogs,where Co_(4)N nanoparticles are encapsulated by Fe embedded in N-doped carbon nanocubes to synthesize hierarchically structured Co_(4)N@Fe/N-C for rechargeable zinc-air batteries and overall water-splitting electrolyzers.As confirmed by theoretical and experimental results,the high intrinsic oxygen reduction reaction,oxygen evolution reaction,and hydrogen evolution reaction activities of Co_(4)N@Fe/N-C were attributed to the formation of the heterointerface and the modulated local electronic structure.Moreover,Co_(4)N@Fe/N-C induced improvement in these trifunctional electrocatalytic activities owing to the hierarchical hollow nanocube structure,uniform distribution of Co_(4)N,and conductive encapsulation by Fe/N-C.Thus,the rechargeable zinc-air battery with Co_(4)N@Fe/N-C delivers a high specific capacity of 789.9 mAh g^(-1) and stable voltage profiles over 500 cycles.Furthermore,the overall water electrolyzer with Co_(4)N@Fe/N-C achieved better durability and rate performance than that with the Pt/C and IrO2 catalysts,delivering a high Faradaic efficiency of 96.4%.Along with the great potential of the integrated water electrolyzer powered by a zinc-air battery for practical applications,therefore,the mechanistic understanding and active site identification provide valuable insights into the rational design of advanced multifunctional electrocatalysts for energy storage and conversion.

Lithium-Ion Battery Pack Based on Fuzzy Logic Control Research on Multi-Layer Equilibrium Circuits

In order to solve the problem of inconsistent energy in the charging and discharging cycles of lithium-ion battery packs,a new multilayer equilibrium topology is designed in this paper.The structure adopts a hierarchical structure design,which includes intra-group equilibrium,primary inter-group equilibrium and secondary inter-group equilibrium.This structure greatly increases the number of equilibrium paths for lithium-ion batteries,thus shortening the time required for equilibrium,and improving the overall efficiency.In terms of control strategy,fuzzy logic control(FLC)is chosen to control the size of the equilibrium current during the equilibrium process.We performed rigorous modeling and simulation of the proposed system by MATLAB and Simulink software.Experiments show that the multilayer equilibrium circuit structure greatly exceeds the traditional single-layer equilibrium circuit in terms of efficacy,specifically,the Li-ion battery equilibrium speed is improved by 12.71%in static equilibrium,14.48%in charge equilibrium,and 11.19%in discharge equilibrium.In addition,compared with the maximum value algorithm,the use of the FLC algorithm reduces the equalization time by about 3.27%and improves the energy transfer efficiency by about 66.49%under the stationary condition,which verifies the feasibility of the equalization scheme.

Physics-based battery SOC estimation methods:Recent advances and future perspectives

The reliable prediction of state of charge(SOC)is one of the vital functions of advanced battery management system(BMS),which has great significance towards safe operation of electric vehicles.By far,the empirical model-based and data-driven-based SOC estimation methods of lithium-ion batteries have been comprehensively discussed and reviewed in various literatures.However,few reviews involving SOC estimation focused on electrochemical mechanism,which gives physical explanations to SOC and becomes most attractive candidate for advanced BMS.For this reason,this paper comprehensively surveys on physics-based SOC algorithms applied in advanced BMS.First,the research progresses of physical SOC estimation methods for lithium-ion batteries are thoroughly discussed and corresponding evaluation criteria are carefully elaborated.Second,future perspectives of the current researches on physics-based battery SOC estimation are presented.The insights stated in this paper are expected to catalyze the development and application of the physics-based advanced BMS algorithms.

Electro-spraying/spinning: A novel battery manufacturing technology

Lithium-ion battery(LIB) industry seems to have met its bottle neck in cutting down producing costs even though much efforts have been put into building a complete industrial chain. Actually, manufacturing methods can greatly affect the cost of battery production. Up to now, lithium ion battery producers still adopt manufacturing methods with cumbersome sub-components preparing processes and costly assembling procedures, which will undoubtedly elevate the producing cost. Herein, we propose a novel approach to directly assemble battery components(cathode, anode and separator) in an integrated way using electro-spraying and electro-spinning technologies. More importantly, this novel battery manufacturing method can produce LIBs in large scale, and the products show excellent mechanical strength, flexibility, thermal stability and electrolyte wettability. Additionally, the performance of the as-prepaed Li Fe PO_(4)||graphite full cell produced by this new method is comparable or even better than that produced by conventional manufacturing approach. In brief, this work provides a new promising technology to prepare LIBs with low cost and better performance.

Heat transfer enhanced inorganic phase change material compositing carbon nanotubes for battery thermal management and thermal runaway propagation mitigation

Developing technologies that can be applied simultaneously in battery thermal management(BTM)and thermal runaway(TR)mitigation is significant to improving the safety of lithium-ion battery systems.Inorganic phase change material(PCM)with nonflammability has the potential to achieve this dual function.This study proposed an encapsulated inorganic phase change material(EPCM)with a heat transfer enhancement for battery systems,where Na_(2)HPO_(4)·12H_(2)O was used as the core PCM encapsulated by silica and the additive of carbon nanotube(CNT)was applied to enhance the thermal conductivity.The microstructure and thermal properties of the EPCM/CNT were analyzed by a series of characterization tests.Two different incorporating methods of CNT were compared and the proper CNT adding amount was also studied.After preparation,the battery thermal management performance and TR propagation mitigation effects of EPCM/CNT were further investigated on the battery modules.The experimental results of thermal management tests showed that EPCM/CNT not only slowed down the temperature rising of the module but also improved the temperature uniformity during normal operation.The peak battery temperature decreased from 76℃to 61.2℃at 2 C discharge rate and the temperature difference was controlled below 3℃.Moreover,the results of TR propagation tests demonstrated that nonflammable EPCM/CNT with good heat absorption could work as a TR barrier,which exhibited effective mitigation on TR and TR propagation.The trigger time of three cells was successfully delayed by 129,474 and 551 s,respectively and the propagation intervals were greatly extended as well.

Co/CoO heterojunction rich in oxygen vacancies introduced by O2 plasma embedded in mesoporous walls of carbon nanoboxes covered with carbon nanotubes for rechargeable zinc-air battery

Herein,Co/CoO heterojunction nanoparticles(NPs)rich in oxygen vacancies embedded in mesoporous walls of nitrogen-doped hollow carbon nanoboxes coupled with nitrogen-doped carbon nanotubes(P-Co/CoOV@NHCNB@NCNT)are well designed through zeolite-imidazole framework(ZIF-67)carbonization,chemical vapor deposition,and O_(2) plasma treatment.As a result,the threedimensional NHCNBs coupled with NCNTs and unique heterojunction with rich oxygen vacancies reduce the charge transport resistance and accelerate the catalytic reaction rate of the P-Co/CoOV@NHCNB@NCNT,and they display exceedingly good electrocatalytic performance for oxygen reduction reaction(ORR,halfwave potential[EORR,1/2=0.855 V vs.reversible hydrogen electrode])and oxygen evolution reaction(OER,overpotential(η_(OER,10)=377mV@10mA cm^(−2)),which exceeds that of the commercial Pt/C+RuO_(2) and most of the formerly reported electrocatalysts.Impressively,both the aqueous and flexible foldable all-solid-state rechargeable zinc-air batteries(ZABs)assembled with the P-Co/CoOV@NHCNB@NCNT catalyst reveal a large maximum power density and outstanding long-term cycling stability.First-principles density functional theory calculations show that the formation of heterojunctions and oxygen vacancies enhances conductivity,reduces reaction energy barriers,and accelerates reaction kinetics rates.This work opens up a new avenue for the facile construction of highly active,structurally stable,and cost-effective bifunctional catalysts for ZABs.

Light-assisted rechargeable zinc-air battery:Mechanism,progress,and prospects

Exploring effective energy storage systems is critical to alleviate energy scarcity.Rechargeable zinc-air batteries are promising energy storage devices.However,conventional rechargeable zinc-air battery systems face many challenges associated with electrolytes and electrodes,causing inferior electrochemistry performance.The light-assisted strategy represents a novel and innovative approach to conventional zinc-air battery technology that uses only electrical energy.This strategy effectively combines both light and electrical energy conversion/storage mechanisms.In addition,light-assisted rechargeable zinc-air batteries can achieve photocharging with or without applied electrical bias by partially using solar energy and the acceleration of oxygen reduction/evolution reaction kinetics.In this paper,the working mechanism and structural design of the light-assisted rechargeable zinc-air batteries are introduced based on the theory of photoelectrochemistry and its characteristics.Then,the latest advances in electrolyte and photocathode design strategies are discussed in detail.The performance enhancement of aqueous light-assisted rechargeable zinc-air batteries using photoelectric materials is explained.Finally,a summary and outlook on the further modification of properties of light-assisted rechargeable zinc-air batteries,especially the photovoltaic electrode catalyst design strategies,are illustrated.This review provides insights and guidance for the design of high-performance light-assisted rechargeable Zn-air batteries for next-generation energy storage devices.

Fluorine-Modulated MXene-Derived Catalysts for Multiphase Sulfur Conversion in Lithium-Sulfur Battery

Fluorine owing to its inherently high electronegativity exhibits charge delocalization and ion dissociation capabilities;as a result,there has been an influx of research studies focused on the utilization of fluorides to optimize solid electrolyte interfaces and provide dynamic protection of electrodes to regulate the reaction and function performance of batteries.Nonetheless,the shuttle effect and the sluggish redox reaction kinetics emphasize the potential bottlenecks of lithium-sulfur batteries.Whether fluorine modulation regulate the reaction process of Li-S chemistry?Here,the TiOF/Ti_(3)C_(2)MXene nanoribbons with a tailored F distribution were constructed via an NH4F fluorinated method.Relying on in situ characterizations and electrochemical analysis,the F activates the catalysis function of Ti metal atoms in the consecutive redox reaction.The positive charge of Ti metal sites is increased due to the formation of O-Ti-F bonds based on the Lewis acid-base mechanism,which contributes to the adsorption of polysulfides,provides more nucleation sites and promotes the cleavage of S-S bonds.This facilitates the deposition of Li_(2)S at lower overpotentials.Additionally,fluorine has the capacity to capture electrons originating from Li_(2)S dissolution due to charge compensation mechanisms.The fluorine modulation strategy holds the promise of guiding the construction of fluorine-based catalysts and facilitating the seamless integration of multiple consecutive heterogeneous catalytic processes.

Effect of preload forces on multidimensional signal dynamic behaviours for battery early safety warning

Providing early safety warning for batteries in real-world applications is challenging.In this study,comprehensive thermal abuse experiments are conducted to clarify the multidimensional signal evolution of battery failure under various preload forces.The time-sequence relationship among expansion force,voltage,and temperature during thermal abuse under five categorised stages is revealed.Three characteristic peaks are identified for the expansion force,which correspond to venting,internal short-circuiting,and thermal runaway.In particular,an abnormal expansion force signal can be detected at temperatures as low as 42.4°C,followed by battery thermal runaway in approximately 6.5 min.Moreover,reducing the preload force can improve the effectiveness of the early-warning method via the expansion force.Specifically,reducing the preload force from 6000 to 1000 N prolongs the warning time(i.e.,227 to 398 s)before thermal runaway is triggered.Based on the results,a notable expansion force early-warning method is proposed that can successfully enable early safety warning approximately 375 s ahead of battery thermal runaway and effectively prevent failure propagation with module validation.This study provides a practical reference for the development of timely and accurate early-warning strategies as well as guidance for the design of safer battery systems.

Ultra‑Stable Sodium‑Ion Battery Enabled by All‑Solid‑State Ferroelectric‑Engineered Composite Electrolytes

Symmetric Na-ion cells using the NASICON-structured electrodes could simplify the manufacturing process,reduce the cost,facilitate the recycling post-process,and thus attractive in the field of large-scale stationary energy storage.However,the long-term cycling performance of such batteries is usually poor.This investigation reveals the unavoidable side reactions between the NASICON-type Na_(3)V_(2)(PO_(4))_(3)(NVP)anode and the commercial liquid electrolyte,leading to serious capacity fading in the symmetric NVP//NVP cells.To resolve this issue,an all-solid-state composite electrolyte is used to replace the liquid electrolyte so that to overcome the side reaction and achieve high anode/electrolyte interfacial stability.The ferroelectric engineering could further improve the interfacial ion conduction,effectively reducing the electrode/electrolyte interfacial resistances.The NVP//NVP cell using the ferroelectric-engineered composite electrolyte can achieve a capacity retention of 86.4%after 650 cycles.Furthermore,the electrolyte can also be used to match the Prussianblue cathode NaxFeyFe(CN)_(6−z)·nH_(2)O(NFFCN).Outstanding long-term cycling stability has been obtained in the all-solid-state NVP//NFFCN cell over 9000 cycles at a current density of 500 mA g^(-1),with a fading rate as low as 0.005%per cycle.

Constructing Al@C-Sn pellet anode without passivation layer for lithium-ion battery

Al is considered as a promising lithium-ion battery(LIBs)anode materials owing to its high theoretical capacity and appropri-ate lithation/de-lithation potential.Unfortunately,its inevitable volume expansion causes the electrode structure instability,leading to poor cyclic stability.What’s worse,the natural Al2O3 layer on commercial Al pellets is always existed as a robust insulating barrier for elec-trons,which brings the voltage dip and results in low reversible capacity.Herein,this work synthesized core-shell Al@C-Sn pellets for LIBs by a plus-minus strategy.In this proposal,the natural Al2O3 passivation layer is eliminated when annealing the pre-introduced SnCl2,meanwhile,polydopamine-derived carbon is introduced as dual functional shell to liberate the fresh Al core from re-oxidization and alle-viate the volume swellings.Benefiting from the addition of C-Sn shell and the elimination of the Al2O3 passivation layer,the as-prepared Al@C-Sn pellet electrode exhibits little voltage dip and delivers a reversible capacity of 1018.7 mAh·g^(-1) at 0.1 A·g^(-1) and 295.0 mAh·g^(-1) at 2.0 A·g^(-1)(after 1000 cycles),respectively.Moreover,its diffusion-controlled capacity is muchly improved compared to those of its counterparts,confirming the well-designed nanostructure contributes to the rapid Li-ion diffusion and further enhances the lithium storage activity.

Machine learning in metal-ion battery research: Advancing material prediction, characterization, and status evaluation

Metal-ion batteries(MIBs),including alkali metal-ion(Li^(+),Na^(+),and K^(3)),multi-valent metal-ion(Zn^(2+),Mg^(2+),and Al^(3+)),metal-air,and metal-sulfur batteries,play an indispensable role in electrochemical energy storage.However,the performance of MIBs is significantly influenced by numerous variables,resulting in multi-dimensional and long-term challenges in the field of battery research and performance enhancement.Machine learning(ML),with its capability to solve intricate tasks and perform robust data processing,is now catalyzing a revolutionary transformation in the development of MIB materials and devices.In this review,we summarize the utilization of ML algorithms that have expedited research on MIBs over the past five years.We present an extensive overview of existing algorithms,elucidating their details,advantages,and limitations in various applications,which encompass electrode screening,material property prediction,electrolyte formulation design,electrode material characterization,manufacturing parameter optimization,and real-time battery status monitoring.Finally,we propose potential solutions and future directions for the application of ML in advancing MIB development.

Microstructure design of advanced magnesium-air battery anodes

Metal-air battery is an environmental friendly energy storage system with unique open structure.Magnesium(Mg)and its alloys have been extensively attempted as anodes for air batteries due to high theoretical energy density,low cost,and recyclability.However,the study on Mg-air battery(MAB)is still at the laboratory level currently,mainly owing to the low anodic efficiency caused by the poor corrosion resistance.In order to reduce corrosion losses and achieve optimal utilization efficiency of Mg anode,the design strategies are reviewed from microstructure perspectives.Firstly,the corrosion behaviors have been discussed,especially the negative difference effect derived by hydrogen evolution.Special attention is given to the effect of anode micro-structures on the MAB,which includes grain size,grain orientation,second phases,crystal structure,twins,and dislocations.For further improvement,the discharge performance,long period stacking ordered phase and its enhancing effect are considered.Meanwhile,given the current debates over Mg dendrites,the potential risk,the impact on discharge,and the elimination strategies are discussed.Microstructure control and single crystal would be promising ways for MAB anode.

Battery pack capacity estimation for electric vehicles based on enhanced machine learning and field data

Accurate capacity estimation is of great importance for the reliable state monitoring,timely maintenance,and second-life utilization of lithium-ion batteries.Despite numerous works on battery capacity estimation using laboratory datasets,most of them are applied to battery cells and lack satisfactory fidelity when extended to real-world electric vehicle(EV)battery packs.The challenges intensify for large-sized EV battery packs,where unpredictable operating profiles and low-quality data acquisition hinder precise capacity estimation.To fill the gap,this study introduces a novel data-driven battery pack capacity estimation method grounded in field data.The proposed approach begins by determining labeled capacity through an innovative combination of the inverse ampere-hour integral,open circuit voltage-based,and resistance-based correction methods.Then,multiple health features are extracted from incremental capacity curves,voltage curves,equivalent circuit model parameters,and operating temperature to thoroughly characterize battery aging behavior.A feature selection procedure is performed to determine the optimal feature set based on the Pearson correlation coefficient.Moreover,a convolutional neural network and bidirectional gated recurrent unit,enhanced by an attention mechanism,are employed to estimate the battery pack capacity in real-world EV applications.Finally,the proposed method is validated with a field dataset from two EVs,covering approximately 35,000 kilometers.The results demonstrate that the proposed method exhibits better estimation performance with an error of less than 1.1%compared to existing methods.This work shows great potential for accurate large-sized EV battery pack capacity estimation based on field data,which provides significant insights into reliable labeled capacity calculation,effective features extraction,and machine learning-enabled health diagnosis.