Semi-supervised estimation of capacity degradation for lithium ion batteries with electrochemical impedance spectroscopy

Machine learning-based methods have emerged as a promising solution to accurate battery capacity estimation for battery management systems.However,they are generally developed in a supervised manner which requires a considerable number of input features and corresponding capacities,leading to prohibitive costs and efforts for data collection.In response to this issue,this study proposes a convolutional neural network(CNN)based method to perform end-to-end capacity estimation by taking only raw impedance spectra as input.More importantly,an input reconstruction module is devised to effectively exploit impedance spectra without corresponding capacities in the training process,thereby significantly alleviating the cost of collecting training data.Two large battery degradation datasets encompassing over 4700 impedance spectra are developed to validate the proposed method.The results show that accurate capacity estimation can be achieved when substantial training samples with measured capacities are given.However,the estimation performance of supervised machine learning algorithms sharply deteriorates when fewer samples with measured capacities are available.In this case,the proposed method outperforms supervised benchmarks and can reduce the root mean square error by up to 50.66%.A further validation under different current rates and states of charge confirms the effectiveness of the proposed method.Our method provides a flexible approach to take advantage of unlabelled samples for developing data-driven models and is promising to be generalised to other battery management tasks.

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.

Interpretable hybrid machine learning demystifies the degradation of practical lithium-sulfur batteries

The ever-increasing future demands of electrification and grid storage have spurred continued research to develop rechargeable battery chemistries for reliable energy storage[1].Beyond current lithium-ion batteries,lithium–sulfur battery represents a promising system due to its high energy density(2600 Wh kg^(-1))and low material cost[2].

Charge compensation and capacity fading in LiCoO2 at high voltage investigated by soft x-ray absorption spectroscopy

In order to obtain an in-depth insight into the mechanism of charge compensation and capacity fading in LiCoO2, the evolution of electronic structure of LiCoO2 at different cutoff voltages and after different cycles are studied by soft x-ray absorption spectroscopy in total electron（TEY） and fluorescence（TFY） detection modes, which provide surface and bulk information, respectively. The spectra of Co L2,3-edge indicate that Co contributes to charge compensation below 4.4 V.Combining with the spectra of O K-edge, it manifests that only O contributes to electron compensation above 4.4 V with the formation of local O 2 p holes both on the surface and in the bulk, where the surficial O evolves more remarkably. The evolution of the O 2 p holes gives an explanation to the origin of O2^-or even O2. A comparison between the TEY and TFY of O K-edge spectra of LiCoO2 cycled in a range from 3 V to 4.6 V indicates both the structural change in the bulk and aggregation of lithium salts on the electrode surface are responsible for the capacity fading. However, the latter is found to play a more important role after many cycles.

Structures and Electrochemical Performances of As-spun RE-Mg-Ni-Mn-based Alloys Applied to Ni-MH Battery

The La-Mg-Ni-Mn-based AB_2-type La_（1-x）Ce_xMgNi_（3.5）Mn_（0.5）（x = 0, 0.1, 0.2, 0.3, and 0.4） alloys were fabricated by melt spinning technology. The effects of Ce content on the structures and electrochemical hydrogen storage performances of the alloys were studied systematically. The XRD and SEM analyses proved that the experimental alloys consist of a major phase LaMgNi_4 and a secondary phase LaNi_5. The variation of Ce content causes an obvious change in the phase abundance of the alloys without changing the phase composition. Namely, with the increase of Ce content, the LaMgNi_4 phase augments and the LaNi_5 phase declines. The lattice constants and cell volumes of the alloys clearly shrink with increasing Ce content. Moreover, the Ce substitution for La results in the grains of the alloys clearly refined. The electrochemical tests showed that the substitution of Ce for La obviously improves the cycle stability of the as-spun alloys. The analyses on the capacity degradation mechanism demonstrate that the improvement can be attributed to the ameliorated anti-corrosion and antioxidation ability originating from substituting partial La with Ce. The as-spun alloys exhibit excellent activation capability, reaching the maximum discharge capacities just at the first cycling without any activation treatment. The substitution of Ce for La evidently improves the discharge potential characteristics of the as-spun alloys. The discharge capacity of the alloys first increases and then decreases with growing Ce content. Furthermore, a similar trend also exists in the electrochemical kinetics of the alloys, including the high rate discharge ability（HRD）, hydrogen diffusion coefficient（D）, limiting current density（IL） and charge transfer rate.

Recent progress in synthesis and surface modification of nickel-rich layered oxide cathode materials for lithium-ion batteries

Nickel-rich layered oxides have been identified as the most promising commercial cathode materials for lithium-ion batteries(LIBs)for their high theoretical specific capacity.However,the poor cycling stability of nickel-rich cathode materials is one of the major barriers for the large-scale usage of LIBs.The existing obstructions that suppress the capacity degradation of nickel-rich cathode materials are as a result of phase transition,mechanical instability,intergranular cracks,side reaction,oxygen loss,and thermal instability during cycling.Core–shell structures,oxidating precursors,electrolyte additives,doping/coating and synthesizing single crystals have been identified as effective methods to improve cycling stability of nickel-rich cathode materials.Herein,recent progress of surface modification,e.g.coating and doping,in nickel-rich cathode materials are summarized based on Periodic table to provide a clear understanding.Electrochemical performances and mechanisms of modified structure are discussed in detail.It is hoped that an overview of synthesis and surface modification can be presented and a perspective of nickel-rich materials in LIBs can be given.

Electrochemical Performance and EIS Analysis of Commercial Lithium-Ion Battery

Degradation behavior is the main technical problem in the field of commercial application of lithiumion batteries. According to the characteristics of voltage, discharge capacity and inner resistance during the charge/discharge process of commercial lithium-ion batteries of mobile telephone, degradation analysis and related mechanisms are put forward and discussed in the paper. The impedance spectra of prismatic commercial lithium-ion batteries are measured at various state of charge after different charge/discharge cycles. The incastared impedance spectra are discussed with a proposed equivalent circuit. Results indicated that the structure change of electrode materials or swell and shrink of crystal lattice, decompose of electrolyte, dissolution of active materials and solid electrolyte interphase film formation are the main reasons leading to the capacity degradation.

Prediction of future capacity and internal resistance of Li-ion cells from one cycle of input data

There is a large demand for models able to predict the future capacity retention and internal resistance(IR)of Lithium-ion battery cells with as little testing as possible.We provide a data-centric model accurately predicting a cell’s entire capacity and IR trajectory from one single cycle of input data.This represents a significant reduction in the amount of input data needed over previous works.Our approach characterises the capacity and IR curve through a small number of key points,which,once predicted and interpolated,describe the full curve.With this approach the remaining useful life is predicted with an 8.6%mean absolute percentage error when the input-cycle is within the first 100 cycles.

Changes of crystal structure and hydrogen storage performances for multiphase La0.7Mg0.3Ni3 alloy upon gas–solid cycling

In order to examine the effects of structure stability on the degradation behaviors of multiphase La0.7Mg0.3Ni3 alloy,changes of the crystal structure and hydrogen storage properties after gas-solid cycling were investigated in detail.The structural analysis identifies that（La,Mg）Ni3（PuNi3-type） phase transforms to amorphous,i.e.,hydrogen-induced amorphization（HIA） occurs whereas LaNi5（CaCu5-type）,（La,Mg）2Ni7（Ce2Ni7-type）,and（La,Mg）5Ni19（Pr5Co19-type） phases still keep crystalline upon hydriding/dehydriding cycling.Partial amorphization remarkably affects both the gas-solid and electrochemical storage performances.The plateau of PCT curves becomes narrow and steep with cycling.Moreover,the maximum electrochemical capacity decreases notably after gas-solid hydrogenation repeats.The electrochemical capacity reduction could be ascribed to both drop of the maximum storage capacity and the slope of plateau induced by partial amorphization.For direct electrochemical cycling,it is suggested that the capacity decay is mainly attributed to HIA in the initial stage.