Degradation mechanism analysis of LiNi0.5Co0.2Mn0.3O2 single crystal cathode materials through machine learning

Abstract

LiNi0.5Co0.2Mn0.3O2 (NCM523) has become one of the most popular cathode materials for current lithium-ion batteries due to its high-energy density and cost performance. However, the rapid capacity fading of NCM severely hinders its development and applications. Here, the single crystal NCM523 materials under different degradation states are characterized using scanning transmission electron microscopy (STEM). Then we developed a neural network model with a two-sequential attention block to recognize the crystal structure and locate defects in STEM images. The number of point defects in NCM523 is observed to experience a trend of increasing first and then decreasing in the degradation process. The space between the transition metal columns shrinks obviously, inducing dramatic capacity decay. This analysis sheds light on the defect evolution and chemical transformation correlated with layered material degradation. It also provides interesting hints for researchers to regenerate the electrochemical capacity and design better battery materials with longer life.

Requirement on the Capacity of Energy Storage to Meet the 2 °C Goal

“…We considered that 10% of the demand for energy storage by wind, PV, and bioenergy would be satisfied by using batteries, while the remaining energy will be stored using hydro pump, compressed air energy storage systems, and others [46]. The consumption of minerals was estimated in the manufacture of lithium-ion batteries (LiNi 0.5 Co 0.2 Mn 0.3 O 2 ), which is widely used in current markets [47]. The production of one Gigawatt hours (GWh) of ternary lithium batteries was estimated to consume 107.65 tons of lithium (Li), 455.76 tons of nickel (Ni), 183.08 tons of cobalt (Co), and 256.01 tons of manganese (Mn) [48,49].…”

“…We next considered that lithium-ion batteries would contribute to 10% of total capacity of energy storage, while hydro pumps, compressed air energy storage systems, and other technologies could be adopted to fulfill the remaining demand for energy storage [46]. We assumed that NCM523 (LiNi 0.5 Co 0.2 Mn 0.3 O 2 ) would be used to store energy for wind and PV power, which has a high energy density [47]. As the consumption of batteries largely depends on the cycle life, we performed three sensitivity experiments by adopting a cycle life of 1000 cycles [50], 2000 cycles [51], and 3000 cycles [52] for NCM523, respectively.…”

Challenges and opportunities using Ni-rich layered oxide cathodes in Li-ion rechargeable batteries: the case of nickel cobalt manganese oxides

“…The widespread use of NCM cathode materials in the current scenario is evident from Table 4 as well as the work reported by research groups working in this direction. [113][114][115][116] The electrochemical performance of the NCM cathode can be optimized by altering the chemical compositions 117 as observed from compositions such as LiNi 1/3 Co 1/3 Mn 1/3 O 2 (NCM333), 118 120 LiNi 0.5 Co 0.3 Mn 0.2 O 2 (NCM532), 121 LiNi 0.6-Co 0.2 Mn 0.2 O 2 (NCM622), 122,123 and LiNi 0.8 Co 0.1 Mn 0.1 O 2 (NCM811). 124,125 As a result, several investigations are 43,44 LMO LiMnO 2 Lithium ion nickel oxide battery 45 LNO LiNiO 2 Lithium iron phosphate battery 46,47 LFP LiFePO 4 Lithium nickel manganese battery 48 LNMO LiNi 0.5 Mn 1.5 O 4 Lithium nickel cobalt aluminium oxide 49 NCA LiNiCoAlO 2 Lithium nickel cobalt manganese oxide 50 NCM LiNiCoMnO 2 Lithium-titanate battery 51 LTO Li 4 Ti 5 O 12 Lithium-sulphur battery 52 Li-S Li as anode and Li 2 S as cathode Lithium-air battery 53 Li-air Lithium-ion polymer battery 54,55 LIP Polymer as electrolyte Thin film lithium-ion battery/microbattery [56][57][58] Based on the nature of electrolyte and thickness of electrodes Lithium ceramic battery/solid state battery 59 Based on nature of electrolyte 126,127 In effect, NCM cathodes with excess Ni contents in the range of 0.8 to 0.99 are being designed by researchers in order to increase the cumulative capacity.…”

MatGPT: A Vane of Materials Informatics from Past, Present, to Future

“…[155] In addition to electrolyte engineering, AI has also played a key role in electrode material design. [144,[156][157][158] For example, Choy et al applied six ML regression models to study the correlations of the structural, elemental feature of 168 distinct doped nickelcobalt-manganese (NCM) systems. They found that GBDT was the best prediction power for both initial discharge capacity and 50th cycle discharge capacity (EC), with the root-mean-square errors calculated to be 16.66 and 18.59 mAh g −1 , respectively.…”

“…In addition to electrolyte engineering, AI has also played a key role in electrode material design. [ 144,156–158 ] For example, Choy et al. applied six ML regression models to study the correlations of the structural, elemental feature of 168 distinct doped nickel–cobalt–manganese (NCM) systems.…”