Accurate and efficient remaining useful life prediction of batteries enabled by physics-informed machine learning

The safe and reliable operation of lithium-ion batteries necessitates the accurate prediction of remaining useful life(RUL).However,this task is challenging due to the diverse ageing mechanisms,various operating conditions,and limited measured signals.Although data-driven methods are perceived as a promising solution,they ignore intrinsic battery physics,leading to compromised accuracy,low efficiency,and low interpretability.In response,this study integrates domain knowledge into deep learning to enhance the RUL prediction performance.We demonstrate accurate RUL prediction using only a single charging curve.First,a generalisable physics-based model is developed to extract ageing-correlated parameters that can describe and explain battery degradation from battery charging data.The parameters inform a deep neural network(DNN)to predict RUL with high accuracy and efficiency.The trained model is validated under 3 types of batteries working under 7 conditions,considering fully charged and partially charged cases.Using data from one cycle only,the proposed method achieves a root mean squared error(RMSE)of 11.42 cycles and a mean absolute relative error(MARE)of 3.19%on average,which are over45%and 44%lower compared to the two state-of-the-art data-driven methods,respectively.Besides its accuracy,the proposed method also outperforms existing methods in terms of efficiency,input burden,and robustness.The inherent relationship between the model parameters and the battery degradation mechanism is further revealed,substantiating the intrinsic superiority of the proposed method.

The development of machine learning-based remaining useful life prediction for lithium-ion batteries

Lithium-ion batteries are the most widely used energy storage devices,for which the accurate prediction of the remaining useful life(RUL)is crucial to their reliable operation and accident prevention.This work thoroughly investigates the developmental trend of RUL prediction with machine learning(ML)algorithms based on the objective screening and statistics of related papers over the past decade to analyze the research core and find future improvement directions.The possibility of extending lithium-ion battery lifetime using RUL prediction results is also explored in this paper.The ten most used ML algorithms for RUL prediction are first identified in 380 relevant papers.Then the general flow of RUL prediction and an in-depth introduction to the four most used signal pre-processing techniques in RUL prediction are presented.The research core of common ML algorithms is given first time in a uniform format in chronological order.The algorithms are also compared from aspects of accuracy and characteristics comprehensively,and the novel and general improvement directions or opportunities including improvement in early prediction,local regeneration modeling,physical information fusion,generalized transfer learning,and hardware implementation are further outlooked.Finally,the methods of battery lifetime extension are summarized,and the feasibility of using RUL as an indicator for extending battery lifetime is outlooked.Battery lifetime can be extended by optimizing the charging profile serval times according to the accurate RUL prediction results online in the future.This paper aims to give inspiration to the future improvement of ML algorithms in battery RUL prediction and lifetime extension strategy.

Reclamation of Mercury from Used Silver Oxide Watch Batteries

This paper deals with the reclamation of mercury from the used silver oxide quartz wristwatch batteries employing leaching-cementation technique. The used batteries are first crushed to liberate the encapsulated active material from the case which is leached in nitric acid to bring all metal contents into solution. After the removal of silver in the solution as silver chloride by precipitation, the mercury which is present as Hg2+ in the solution has been reclaimed through cementation with zinc dust. Various effects like zinc sheet and dust, zinc quantity, pH of the solution, duration and temperature have been carried out to standardise the conditions for maximum mercury reclamation. At a temperature of 45℃ and at 3.9 pH, 92.3% of mercury was recovered using 74 μm size zinc dust with purity greater than 99.78% and the same is characterized by XRF and the results are discussed.

Research on thin grid materials of lead-acid batteries

A detailed investigation on Pb-Ca-Sn alloys was made in order to choose suitable grid alloys materials for thin plate lead-acid batteries. The electrochemical performances of alloys were investigated by electrochemical corrosion experiment, scanning electron microscope (SEM), and cyclic voltammetry (CV) test. The results indicate that Pb-Ca-Sn-Bi-Cu alloys can be used to make the grids used for thin grid lead-acid batteries, the content of bismuth has primary effects on the corrosion resistance of grid alloys, the composition of alloys plays an important role on batteries performance, and appropriate scale of elements can be choosed to obtain optimal electrochemical performance. The lead-acid batteries using this kind of grid show good performance by cycle life test.

Experiments Study on Charge Technology of Lead-Acid Electric Vehicle Batteries

The basic theory of the fast charge and several charge methods are introduced. In order to heighten charge efficiency of valve-regulated lead-acid battery and shorten the charge time, five charge methods are investigated with experiments done on the Digatron BNT 400-050 test bench. Battery current, terminal voltage, capacity, energy and terminal pole temperature during battery experiment were recorded, and corresponding curves were depicted. Battery capacity-time ratio, energy efficiency and energy-temperature ratio are put forward to be the appraising criteria of lead-acid battery on electric vehicle （EV）. According to the appraising criteria and the battery curves, multistage-current/negative-pulse charge method is recommended to charge lead-acid EV battery.

Simple electrode assembly engineering:Toward a multifunctional lead-acid battery

Electrochemical energy storage is a promising technology for the integration of renewable energy.Lead-acid battery is perhaps among the most successful commercialized systems ever since thanks to its excellent cost-effectiveness and safety records.Despite of 165 years of development,the low energy density as well as the coupled power and energy density scaling restrain its wider application in real life.To address this challenge,we optimized the configuration of conventional Pb-acid battery to integrate two gas diffusion electrodes.The novel device can work as a Pb-air battery using ambient air,showing a peak power density of 183 mW cm^(−2),which was comparable with other state-of-the-art metal-O_(2)batteries.It can also behave as a fuel cell,simultaneously converting H_(2)and air into electricity with a peak power density of 75 mW cm^(−2).Importantly,this device showed little performance degradation after 35 h of the longevity test.Our work shows the exciting potential of lead battery technology and demonstrates the importance of battery architecture optimization toward improved energy storage capacity.

Availability of Lithium Ion Batteries from Hybrid and Electric Cars for Second Use： How to Forecast for Germany until 2030

Due to growing numbers of sold HEV （hybrid electric vehicles）, PHEV （plug-in hybrid electric vehicles）, and BEV （battery electric vehicles）, new market opportunities to reuse or recycle old lithium ion batteries arise. Thus, a forecast of available batteries caused by accidents or from end-of-life vehicles was carried out using a mathematical model. Input data were obtained from an estimate of newly registered hybrid and electric vehicles in Germany from 2010 until 2030, from the accident rate of cars in Germany, and from the average cars’ lifetime. The results indicate that （a） the total amount of available second use batteries in 2030 will be between 130,000 units/year and 500,000 units/year, （b） the highest amount of batteries will be obtained from end-of-life vehicles not from accident vehicles, although most batteries from accident vehicles will be suitable for 2nd use, and （c） the quantity of hybrid, plug-in hybrid, and electric car batteries available for reuse will continue to rise after 2030.

Self-Discharge in Valve-Regulated Sealed Lead-Acid Batteries

Factors that cause the self-discharge in valve-regulated sealed lead-acid batteries are discussed and measures to inhibit the self-discharge are put forward.

Study of the Charge Acceptance of Small-Size Sealed Lead-Acid Batteries

ＳｔｕｄｙｏｆｔｈｅＣｈａｒｇｅＡｃｃｅｐｔａｎｃｅｏｆＳｍａｌｌ－ＳｉｚｅＳｅａｌｅｄＬｅａｄ－ＡｃｉｄＢａｔｔｅｒｉｅｓＤＯＮＧＢａｏｇｕａｎｇ；ＺＨＡＮＧＱｉｕｄａｏ；ＭＵＪｕｎｊｉａｎｇ（董保光，张秋道，穆俊江）（Ｄｅｐｔ．ｏｆＡｐｐｌｉｅｄ...

Potentiometric Measurement of State-of-Charge of Lead-Acid Batteries Using Polymeric Ferrocene and Quinones Derivatives

Measurement of state-of-charge of lead-acid batteries using potentiometric sensors would be convenient;however, most of the electrochemical couples are either soluble or are unstable in the battery electrolyte. This paper describes the results of an investigation of poly (divinylferrocene) (PDVF) and Poly(diethynylanthraquinone) (PAQ) couples in sulfuric acid with the view to developing a potentiometric sensor for lead-acid batteries. These compounds were both found to be quite stable and undergo reversible reduction/oxidation in sulfuric acid media. Their redox potential difference varied linearly with sulfuric acid concentration in the range of 1 M - 5 M (i.e. simulated lead-acid electrolyte during battery charge/discharge cycles). A sensor based on these compounds has been investigated.

Effects of Used Battery on Key Enzyme Activity during the Germination of Wheat Seeds

[Objective] This study aimed to explore the effects of used battery lixivium on wheat germination. [Method] The wheat seeds were treated with used battery lix- ivium at different concentrations to detect the change of activities of amylase, pro- tease, pyruvate dehydrogenase （PDH） and polyphenol oxidase （PPO） during the ger- mination period. [Result] The results showed that the used battery affected enzyme activity. With the increase of concentration of used battery lixivium, trends of the changes of amylase and protease activities were not different. The activities were en- hanced at low concentrations of lixivium, while were inhibited at high concentrations. The tends of changes of pyruvate dehydrogenase （PDH） and polyphenol oxidase （PPO） activities were not consistent with that of either amylase or protease, which showed continuous downward trends with the increasing concentration of used battery lixivium. [Conclusion] This study is of great practical significance for understanding the effects of used battery lixivium on the germination of wheat seeds.

A machine learning framework for remaining useful lifetime prediction of li-ion batteries using diverse neural networks

Accurate prediction of the remaining useful life(RUL)of lithium-ion batteries(LIBs)is pivotal for enhancing their operational efficiency and safety in diverse applications.Beyond operational advantages,precise RUL predictions can also expedite advancements in cell design and fast-charging methodologies,thereby reducing cycle testing durations.Despite artificial neural networks(ANNs)showing promise in this domain,determining the best-fit architecture across varied datasets and optimization approaches remains challenging.This study introduces a machine learning framework for systematically evaluating multiple ANN architectures.Using only 30%of a training dataset derived from 124 LIBs subjected to various charging regimes,an extensive evaluation is conducted across 7 ANN architectures.Each architecture is optimized in terms of hyperparameters using this framework,a process that spans 145 days on an NVIDIA GeForce RTX 4090 GPU.By optimizing each model to its best configuration,a fair and standardized basis for comparing their RUL predictions is established.The research also examines the impact of different cycling windows on predictive accuracy.Using a stratified partitioning technique underscores the significance of consistent dataset representation across subsets.Significantly,using only the features derived from individual charge–discharge cycles,our top-performing model,based on data from just 40 cycles,achieves a mean absolute percentage error of 10.7%.

A review of deep learning approach to predicting the state of health and state of charge of lithium-ion batteries

In the field of energy storage,it is very important to predict the state of charge and the state of health of lithium-ion batteries.In this paper,we review the current widely used equivalent circuit and electrochemical models for battery state predictions.The review demonstrates that machine learning and deep learning approaches can be used to construct fast and accurate data-driven models for the prediction of battery performance.The details,advantages,and limitations of these approaches are presented,compared,and summarized.Finally,future key challenges and opportunities are discussed.

A Hybrid Ensemble Deep Learning Approach for Early Prediction of Battery Remaining Useful Life

Accurate estimation of the remaining useful life(RUL)of lithium-ion batteries is critical for their large-scale deployment as energy storage devices in electric vehicles and stationary storage.A fundamental understanding of the factors affecting RUL is crucial for accelerating battery technology development.However,it is very challenging to predict RUL accurately because of complex degradation mechanisms occurring within the batteries,as well as dynamic operating conditions in practical applications.Moreover,due to insignificant capacity degradation in early stages,early prediction of battery life with early cycle data can be more difficult.In this paper,we propose a hybrid deep learning model for early prediction of battery RUL.The proposed method can effectively combine handcrafted features with domain knowledge and latent features learned by deep networks to boost the performance of RUL early prediction.We also design a non-linear correlation-based method to select effective domain knowledge-based features.Moreover,a novel snapshot ensemble learning strategy is proposed to further enhance model generalization ability without increasing any additional training cost.Our experimental results show that the proposed method not only outperforms other approaches in the primary test set having a similar distribution as the training set,but also generalizes well to the secondary test set having a clearly different distribution with the training set.The PyTorch implementation of our proposed approach is available at https://github.com/batteryrul/battery_rul_early_prediction.

Simple Rational Model for Discharge of Batteries with Aqueous Electrolytes, Based on Nernst Equation

A simple rational model is proposed for discharge of batteries with aqueous electrolytes, based on Nernst equation. Details of electrode kinetics are not taken into account. Only a few overall parameters of the battery are considered. A simple algorithm, with variable time step-length Δt, is presented, for proposed model. The model is first applied to Daniel cell, in order to clarify concepts and principles of battery operation. It is found that initial pinching, in time-history curve of voltage E-t, is due to initial under-concentration of product ion. Then, model is applied to a lead-acid battery. In absence of an ion product, and in order to construct nominator of Nernst ratio, such an ion, with coefficient tending to zero, is assumed, thus yielding unity in nominator. Time-history curves of voltage, for various values of internal resistance, are compared with corresponding published experimental curves. Temperature effect on voltage-time curve is examined. Proposed model can be extended to other types of batteries, which can be considered as having aqueous electrolytes, too.

Pb-Ca-Sn-Ba Grid Alloys for Valve-Regulated Lead Acid Batteries

The effect of barium additives on the process of anodic corrosion of lead-tin-calcium alloys in a 4.8 М sulfuric acid solution was studied. Cyclic voltammetry, impedance spectroscopy, weight loss measurements and scanning electronic microscope analysis have allowed exploring the oxidation process and characterizing the formed corrosion layer. According to our results, barium introduction into lead-tin-calcium alloys increases their hardness, reduces their electrochemical activity, and improves their corrosion stability. Reduction of the calcium content in the alloy can be compensated by adding barium. Barium dopation at lead-tin-calcium alloys decreases the resistance of the oxide layer formed on the grid surface, in a deeply discharged state, and raises its resistance during floating conditions and at a charged state of the positive electrode.

Techno-economic and environmental impact analysis of electric two-wheeler batteries in India

This paper presents a comprehensive techno-economic and environmental impact analysis of electric two-wheeler batteries in India.The technical comparison reveals that sodium-ion(Na-ion)and lithium-ion(Li-ion)batteries outperform lead-acid batteries in various parameters,with Na-ion and Li-ion batteries exhibiting higher energy densities,higher power densities,longer cycle lives,faster charge rates,better compactness,lighter weight and lower self-discharge rates.In economic comparison,Na-ion batteries were found to be~12-14%more expensive than Li-ion batteries.However,the longer lifespans and higher energy densities of Na-ion and Li-ion batteries can offset their higher costs through improved performance and long-term savings.Lead-acid batteries have the highest environmental impact,while Li-ion batteries demonstrate better environmental performance and potential for recycling.Na-ion batteries offer promising environmental advantages with their abundance,lower cost and lower toxic and hazardous material content.Efficient recycling processes can further enhance the environmental benefits of Na-ion batteries.Overall,this research examines the potential of Na-ion batteries as a cheaper alternative to Li-ion batteries,considering India’s abundant sodium resources in regions such as Rajasthan,Chhattisgarh,Jharkhand and others.

Review on Lithium-ion Battery PHM from the Perspective of Key PHM Steps

Prognostics and health management(PHM)has gotten considerable attention in the background of Industry 4.0.Battery PHM contributes to the reliable and safe operation of electric devices.Nevertheless,relevant reviews are still continuously updated over time.In this paper,we browsed extensive literature related to battery PHM from 2018to 2023 and summarized advances in battery PHM field,including battery testing and public datasets,fault diagnosis and prediction methods,health status estimation and health management methods.The last topic includes state of health estimation methods,remaining useful life prediction methods and predictive maintenance methods.Each of these categories is introduced and discussed in details.Based on this survey,we accordingly discuss challenges left to battery PHM,and provide future research opportunities.This research systematically reviews recent research about battery PHM from the perspective of key PHM steps and provide some valuable prospects for researchers and practitioners.

State of health and remaining useful life prediction for lithiumion batteries based on differential thermal voltammetry and a long and short memory neural network

As the lithium-ion battery is widely applied,the reliability of the battery has become a high-profile content in recent years.Accurate estimation and prediction of state of health(SOH)and remaining useful life(RUL)prediction are crucial for battery management systems.In this paper,the core contribution is the construction of a datadriven model with the long short-term memory(LSTM)network applicable to the time-series regression prediction problem with the integration of two methods,data-driven methods and feature signal analysis.The input features of model are extracted from differential thermal voltammetry(DTV)curves,which could characterize the battery degradation characteristics,so that the accurate prediction of battery capacity fade could be accomplished.Firstly,the DTV curve is smoothed by the Savitzky-Golay filter,and six alternate features are selected based on the connection between DTV curves and battery degradation characteristics.Then,a correlation analysis method is used to further filter the input features and three features that are highly associated with capacity fade are selected as input into the data driven model.The LSTM neural network is trained by using the root mean square propagation(RMSprop)technique and the dropout technique.Finally,the data of four batteries with different health levels are deployed for model construction,verification and comparison.The results show that the proposed method has high accuracy in SOH and RUL prediction and the capacity rebound phenomenon can be accurately estimated.This method can greatly reduce the cost and complexity,and increase the practicability,which provides the basis and guidance for battery data collection and the application of cloud technology and digital twin.

Data-driven prognostics and remaining useful life estimation for lithium-ion battery: A Review

As an important and necessary part in the intelligent battery management systems(BMS),the prognostics and remaining useful life(RUL)estimation for lithium-ion batteries attach more and more attractions.Especially,the data-driven approaches use only the monitoring data and historical data to model the performance degradation and assess the health status,that makes these methods flexible and applicable in actual lithium-ion battery applications.At first,the related concepts and definitions are introduced.And the degradation parameters identification and extraction is presented,as the health indicator and the foundation of RUL prediction for the lithium-ion batteries.Then,data-driven methods used for lithium-ion battery RUL estimation are summarized,in which several statistical and machine learning algorithms are involved.Finally,the future trend for battery prognostics and RUL estimation are forecasted.