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.

A hierarchical enhanced data-driven battery pack capacity estimation framework for real-world operating conditions with fewer labeled data

Battery pack capacity estimation under real-world operating conditions is important for battery performance optimization and health management,contributing to the reliability and longevity of batterypowered systems.However,complex operating conditions,coupling cell-to-cell inconsistency,and limited labeled data pose great challenges to accurate and robust battery pack capacity estimation.To address these issues,this paper proposes a hierarchical data-driven framework aimed at enhancing the training of machine learning models with fewer labeled data.Unlike traditional data-driven methods that lack interpretability,the hierarchical data-driven framework unveils the“mechanism”of the black box inside the data-driven framework by splitting the final estimation target into cell-level and pack-level intermediate targets.A generalized feature matrix is devised without requiring all cell voltages,significantly reducing the computational cost and memory resources.The generated intermediate target labels and the corresponding features are hierarchically employed to enhance the training of two machine learning models,effectively alleviating the difficulty of learning the relationship from all features due to fewer labeled data and addressing the dilemma of requiring extensive labeled data for accurate estimation.Using only 10%of degradation data,the proposed framework outperforms the state-of-the-art battery pack capacity estimation methods,achieving mean absolute percentage errors of 0.608%,0.601%,and 1.128%for three battery packs whose degradation load profiles represent real-world operating conditions.Its high accuracy,adaptability,and robustness indicate the potential in different application scenarios,which is promising for reducing laborious and expensive aging experiments at the pack level and facilitating the development of battery technology.

Electric-controlled pressure relief valve for enhanced safety in liquid-cooled lithium-ion battery packs

The liquid-cooled battery energy sto rage system(LCBESS) has gained significant attention due to its superior thermal management capacity.However,liquid-cooled battery pack(LCBP) usually has a high sealing level above IP65,which can trap flammable and explosive gases from battery thermal runaway and cause explosions.This poses serious safety risks and challenges for LCBESS.In this study,we tested overcharged battery inside a commercial LCBP and found that the conventionally mechanical pressure relief valve(PRV) on the LCBP had a delayed response and low-pressure relief efficiency.A realistic 20-foot model of an energy storage cabin was constructed using the Flacs finite element simulation software.Comparative studies were conducted to evaluate the pressure relief efficiency and the influence on neighboring battery packs in case of internal explosions,considering different sizes and installation positions of the PRV.Here,a newly developed electric-controlled PRV integrated with battery fault detection is introduced,capable of starting within 50 ms of the battery safety valve opening.Furthermore,the PRV was integrated with the battery management system and changed the battery charging and discharging strategy after the PRV was opened.Experimental tests confirmed the efficacy of this method in preventing explosions.This paper addresses the safety concerns associated with LCBPs and proposes an effective solution for explosion relief.

Lifetime and Aging Degradation Prognostics for Lithium-ion Battery Packs Based on a Cell to Pack Method

Aging diagnosis of batteries is essential to ensure that the energy storage systems operate within a safe region.This paper proposes a novel cell to pack health and lifetime prognostics method based on the combination of transferred deep learning and Gaussian process regression.General health indicators are extracted from the partial discharge process.The sequential degradation model of the health indicator is developed based on a deep learning framework and is migrated for the battery pack degradation prediction.The future degraded capacities of both battery pack and each battery cell are probabilistically predicted to provide a comprehensive lifetime prognostic.Besides,only a few separate battery cells in the source domain and early data of battery packs in the target domain are needed for model construction.Experimental results show that the lifetime prediction errors are less than 25 cycles for the battery pack,even with only 50 cycles for model fine-tuning,which can save about 90%time for the aging experiment.Thus,it largely reduces the time and labor for battery pack investigation.The predicted capacity trends of the battery cells connected in the battery pack accurately reflect the actual degradation of each battery cell,which can reveal the weakest cell for maintenance in advance.

Analysis on the capacity degradation mechanism of a series lithium-ion power battery pack based on inconsistency of capacity

The lithium-ion battery has been widely used as an energy source. Charge rate, discharge rate, and operating tem- perature are very important factors for the capacity degradations of power batteries and battery packs. Firstly, in this paper we make use of an accelerated life test and a statistical analysis method to establish the capacity accelerated degradation model under three constant stress parameters according to the degradation data, which are charge rate, discharge rate, and operating temperature, and then we propose a capacity degradation model according to the current residual capacity of a Li-ion cell under dynamic stress parameters. Secondly, we analyze the charge and discharge process of a series power battery pack and interpret the correlation between the capacity degradations of the battery pack and its charge/discharge rate. According to this cycling condition, we establish a capacity degradation model of a series power battery pack under inconsistent capacity of cells, and analyze the degradation mechanism with capacity variance and operating temperature difference. The comparative analysis of test results shows that the inconsistent operating temperatures of cells in the series power battery pack are the main cause of its degradation; when the difference between inconsistent temperatures is narrowed by 5 ℃, the cycle life can be improved by more than 50%. Therefore, it effectively improves the cycle life of the series battery pack to reasonably assemble the batteries according to their capacities and to narrow the differences in operating temperature among cells.

Thermal Management of Air-Cooling Lithium-Ion Battery Pack

Lithium-ion battery packs are made by many batteries, and the difficulty in heat transfer can cause many safety issues. It is important to evaluate thermal performance of a battery pack in designing process. Here, a multiscale method combining a pseudo-two-dimensional model of individual battery and three-dimensional computational fluid dynamics is employed to describe heat generation and transfer in a battery pack. The effect of battery arrangement on the thermal performance of battery packs is investigated. We discuss the air-cooling effect of the pack with four battery arrangements which include one square arrangement, one stagger arrangement and two trapezoid arrangements. In addition, the air-cooling strategy is studied by observing temperature distribution of the battery pack. It is found that the square arrangement is the structure with the best air-cooling effect, and the cooling effect is best when the cold air inlet is at the top of the battery pack. We hope that this work can provide theoretical guidance for thermal management of lithium-ion battery packs.

Modeling and Optimization of Heat Dissipation Structure of EV Battery Pack

In order to solve the problems of high temperature and inconsistency in the operation of electric vehicle（ EV） battery pack,computational fluid dynamics（ CFD） simulation method is used to simulate and optimize the heat dissipation of battery pack. The heat generation rate at different discharge magnifications is identified by establishing the heat generation model of the battery. In the forced air cooling mode,the Fluent software is used to compare the effects of different inlet and outlet directions,inlet angles,outlet angles,outlet sizes and inlet air speeds on heat dissipation. The simulation results show that the heat dissipation effect of the structure with the inlet and outlet on the same side is better than that on the different sides; the appropriate inlet angle and outlet width can improve the uniformity of temperature field; the increase of the inlet speed can improve the heat dissipation effect significantly. Compared with the steady temperature field of the initial structure,the average temperature after structure optimization is reduced by 4. 8℃ and the temperature difference is reduced by 15. 8℃,so that the battery can work under reasonable temperature and temperature difference.

Comparative study of the thermal insulation performance of steel and aluminum battery packs in high-and low-temperature environments

As the only power source of pure electric vehicles,the performance of battery packs is easily affected by the temperature,and too high or too low temperature will make the performance of battery packs decline.In this study,the thermal analysis finite element modeling of a cast aluminum battery pack and steel battery pack of a pure electric vehicle is established to compare the thermal insulation performance of two kinds of battery packs under high-and low-temperature conditions.The simulation results show that the thermal insulation performance of the two kinds of battery packs meets the design requirements under high-and low-temperature conditions.The external environment of the cell and battery pack mainly transmits heat through heat conduction.Aiming at the problem that the uniform temperature performance of the steel battery pack is lower than that of the cast aluminum battery pack,several optimization solutions are put forward for the insulation design of the steel battery pack,and the optimal solution is obtained by comparing the simulation results.

Internal short circuit detection method for battery pack based on circuit topology

Internal short circuit(ISCr) is one of the major obstacles to the improvement of the battery safety. The ISCr may lead to the battery thermal runaway and is hard to be detected in the early stage. In this work, a new ISCr detection method based on the symmetrical loop circuit topology(SLCT) is introduced. The SLCT ensures that every battery has the same priority in the circuit and every battery will contribute the same amount of short-circuit current to the ISCr once the ISCr happens. The ISCr battery could be identified by the combination of the ratio of the short-circuit currents and the sign of the short-circuit currents. The recursive least square method is adopted for the real-time application and the optimized ammeters allocation is derived from the mathematic deduction. The battery pack based on the individual DP(dual polarization) battery model is established to verify the ISCr detection method. The 1–1000 Ω s ISCr(the early stage ISCr) can be effectively detected within 1–125 s. The SLCT provides the possibility of new battery pack designs and new battery management methods. The proposed ISCr detection method shows excellent effectiveness and efficiency on the identification of the ISCr battery in the early stage.

Joint Estimation of Inconsistency and State of Health for Series Battery Packs

Battery packs are applied in various areas(e.g.,electric vehicles,energy storage,space,mining,etc.),which requires the state of health(SOH)to be accurately estimated.Inconsistency,also known as cell variation,is considered a significant evaluation index that greatly affects the degradation of battery pack.This paper proposes a novel joint inconsistency and SOH estimation method under cycling,which fills the gap of joint estimation based on the fast-charging process for electric vehicles.First,fifteen features are extracted from current change points during the partial charging process.Then,a joint estimation system is designed,where fusion weights are obtained by the analytic hierarchy process and multi-scale sample entropy to evaluate inconsistency.A wrapper is used to select the optimal feature subset,and Gaussian process regression is implemented to estimate the SOH.Finally,the estimation performance is assessed by the test data.The results show that the inconsistency evaluation can reflect the aging conditions,and the inconsistency does affect the aging process.The wrapper selection method improves the accuracy of SOH estimation by about 75.8%compared to the traditional filter method when only 10%of data is used for model training.The maximum absolute error and root mean square error are 2.58%and 0.93%,respectively.

Battery package design optimization for small electric aircraft

The increasing gross weight of electric Unmanned Aerial Vehicle(UAV) poses a challenge in practical applications. The range and endurance of the electric UAV are limited by the fixed mass of the battery package. In this work, a design optimization method for the battery package topology of small electric UAV is proposed to enhance the performance. To improve the accuracy of the method, the dynamic battery model and simplified electric component models are presented.These models are utilized by the trajectory optimization method, which takes the dynamic characteristic into consideration to calculate the aircraft performance. The direct optimal control method is used for solving the trajectory optimization problem, and this method is tested on a small blended-wing-body electric aircraft. The test result shows that the range and energy-consumption are mainly influenced by the parallel topology of the battery package, while the flight time in climb phase is more sensitive to the series topology. It is deduced that the range-and energy-optimal design points can be considered concurrently in design optimization. The work proves the feasibility of integrating the trajectory optimization and battery package design.

A data-fusion-model method for state of health estimation of Li-ion battery packs based on partial charging curve

The estimation of State of Health(SOH)for battery packs used in Electric Vehicles(EVs)is a complex task with significant importance,accompanied by several challenges.This study introduces a data-fusion model approach to estimate the SOH of battery packs.The approach utilizes dual Gaussian Process Regressions(GPRs)to construct a data-driven and non-parametric aging model based on charging-based Aging Features(AFs).To enhance the accuracy of the aging model,a noise model is established to replace the random noise.Subsequently,the statespace representation of the aging model is incorporated.Additionally,the Particle Filter(PF)is introduced to track the unknown state in the aging model,thereby developing the data-fusion-model for SOH estimation.The performance of the proposed method is validated through aging experiments conducted on battery packs.The simulation results demonstrate that the data-fusion model approach achieves accurate SOH estimation,with maximum errors less than 1.5%.Compared to conventional techniques such as GPR and Support Vector Regression(SVR),the proposed method exhibits higher estimation accuracy and robustness.

Numerical Simulation of Thermal Management of Lithium Battery Based on Air Cooled Heat Dissipation

In recent years,due to the rapid increase in the number of vehicles in the world,the traditional vehicles using gasoline or diesel as energy have led to serious air pollution and energy depletion.It is urgent to develop practical clean energy vehicles.The performance of electric vehicle depends on the power battery pack.The working temperature of the battery pack has a great impact on the performance of the battery,so it is necessary to carry out thermal management on the battery pack.Taking a lithium-ion battery as the research object,the temperature field of the battery pack in the charge and discharge state is simulated and analyzed by using CFD simulation software in the way of air cooled heat dissipation,so as to understand the influencing factors of uneven temperature field.At the same time,the development trend of battery temperature can be well predicted through simulation,so as to provide theoretical basis for the design of battery pack.

Development and Verification of the Equilibrium Strategy for Batteries in Electric Vehicles

The inconsistency of the cells in a battery pack can affect its lifespan,safety and reliability in the electric vehicles. The balanced system is an effective technique to reduce its inconsistency and improve the operating performance. A hybrid equilibrium strategy based on decision combing battery state-of-charge（ SOC） and voltage has been proposed. The battery SOC is estimated through an improved least squares method. An equalization hardware in loop（ HIL） platform has been constructed. Based on this HIL platform,equilibrium strategy has been verified under the constant-current-constant-voltage（ CCCV） and dynamicstresstest（ DST） conditions. Experimental results indicate that the proposed hybrid equalization strategy can achieve good balance effect and avoid the overcharge and over-discharge of the battery pack at the same time.

A branch current estimation and correction method for a parallel connected battery system based on dual BP neural networks

In the actual use of a parallel battery pack in electric vehicles(EVs),current distribution in each branch will be different due to inconsistence characteristics of each battery cell.If the branch current is approximately calculated by the total current of the battery pack divided by the number of the parallel branches,there will be a large error between the calculated branch current and the real branch current.Adding current sensors to measure each branch current is not practical because of the high cost.Accurate estimation of branch currents can give a safety warning in time when the parallel batteries of EVs are seriously inconsistent.This paper puts forward a method to estimate and correct branch currents based on dual back propagation(BP)neural networks.In the proposed method,one BP neural network is used to estimate branch currents,the other BP neural network is used to reduce the estimation error cause by current pulse excitations.Furthermore,this paper makes discussions on the selection of the best inputs for the dual BP neural networks and the adaptability of the method for different battery capacity and resistence differences.The effectiveness of the proposed method is verified by multiple dynamic conditions of two cells connected in parallel.

Design a Hybrid Energy-Supply for the Electrically Driven Heavy-Duty Hexapod Vehicle

Increasing the power density and overload capability of the energy-supply units(ESUs)is always one of the most challenging tasks in developing and deploying legged vehicles,especially for heavy-duty legged vehicles,in which significant power fluctuations in energy supply exist with peak power several times surpassing the average value.Applying ESUs with high power density and high overload can compactly ensure fluctuating power source supply on demand.It can avoid the ultra-high configuration issue,which usually exists in the conventional lithium-ion battery-based or engine-generator-based ESUs.Moreover,it dramatically reduces weight and significantly increases the loading and endurance capabilities of the legged vehicles.In this paper,we present a hybrid energy-supply unit for a heavy-duty legged vehicle combining the discharge characteristics of lithium-ion batteries and peak energy release/absorption characteristics of supercapacitors to adapt the ESU to high overload power fluctuations.The parameters of the lithium-ion battery pack and supercapacitor pack inside the ESU are optimally matched using the genetic algorithm based on the energy consumption model of the heavy-duty legged vehicle.The experiment results exhibit that the legged vehicle with a weight of 4.2 tons can walk at the speed of 5 km/h in a tripod gait under a reduction of 35.39%in weight of the ESU compared to the conventional lithium-ion battery-based solution.

Fluorinated graphite nanosheets for ultrahigh-capacity lithium primary batteries

For better performances of Ni-based catalysts at low temperatures,Ni/SiC catalyst doped with a little amount of additive La was successfully prepared.The catalytic CO methanation activity tests showed that 3%La-Ni/SiC catalyst was excellent at a low reaction temperature(95.9%CO conversion and 85.1%CH4 selectivity at250℃)with a superior stability compared with Ni/SiC(3.4%CO conversion and 0%CH4 selectivity at 250℃).This can be attributed to that the addition of La can markedly improve the dispersibility of active metal Ni and reduce the particle sizes of Ni nanoparticles or clusters,and can also regulate the interaction between active components and supports.Moreover,the high thermal conductivity and thermal stability could avoid the generation of hot spots in the catalyst bed.These results will promote the development of highly active Ni-based catalysts for the low-temperature methanation reaction.