Computer‐Vision‐Based Approach to Classify and Quantify Flaws in Li‐Ion Electrodes

Abstract

X‐ray computed tomography (X‐ray CT) is a non‐destructive characterization technique that in recent years has been adopted to study the microstructure of battery electrodes. However, the often manual and laborious data analysis process hinders the extraction of useful metrics that can ultimately inform the mechanisms behind cycle life degradation. This work presents a novel approach that combines two convolutional neural networks to first locate and segment each particle in a nano‐CT LiNiMnCoO2 (NMC) electrode dataset, and successively classifies each particle according to the presence of flaws or cracks within its internal structure. Metrics extracted from the computer vision segmentation are validated with respect to traditional threshold‐based segmentation, confirming that flawed particles are correctly identified as single entities. Successively, slices from each particle are analyzed by a pre‐trained classifier to detect the presence of flaws or cracks. The models are used to quantify microstructural evolution in uncycled and cycled NMC811 electrodes, as well as the number of flawed particles in a NMC622 electrode. As a proof‐of‐concept, a 3‐phase segmentation is also presented, whereby each individual flaw is segmented as a separate pixel label. It is anticipated that this analysis pipeline will be widely used in the field of battery research and beyond.

Computational Model for Predicting Particle Fracture During Electrode Calendering

“…[11] Additionally, a variety of algorithms based on machine learning have been developed to support the segmentation of each material phase (AM, carbon-binder, and pores) in the grayscale image dataset. [22,23] Computational models are popular in this digital age and offer a plethora of interesting capabilities to gain insights into the electrode microstructure. To link with industrial production, digital models for different steps of the LIB manufacturing process have been developed.…”

“…It also enables the tracking of the electrode size, shape, and network morphology changes like AM cracking and irreversible deformation due to mechanical factors during and after the manufacturing process [11] . Additionally, a variety of algorithms based on machine learning have been developed to support the segmentation of each material phase (AM, carbon‐binder, and pores) in the grayscale image dataset [22,23] …”

5D Analysis of Capacity Degradation in Battery Electrodes Enabled by Operando CT‐XANES

“…In this regard, synchrotron X-ray computed tomography (CT) is a powerful tool that enables non-destructive 3D observation of the electrode microstructure, as well as its evolution during cycling at multiple length scales. [66][67][68][69][70][71][72][73][74] However, while CT techniques can precisely discern microstructural changes in electrodes that potentially result in capacity degradation, they lack the capability for directly observing the capacity fade itself. Such limitations of the CT technique can be overcome by integration with spectroscopic chemical characterization techniques, such as X-ray absorption spectroscopy.…”

SEI-Coated Carbon Particles: Electrochemomechanical Fracture Mechanisms

“…7,8 Mechanical fracture-induced degradation in rechargeable battery technology is a well-established phenomenon, and is believed to be partly responsible for the long-term capacity fading of active materials because it isolates electrochemically active anode and cathode particles from the surrounding electrolyte and decreases the total charge capacity that can be reversibly exchanged with the counter electrode layer. [9][10][11][12][13][14][15][16] Many flaws form during the processing (synthesis) of the particles, 9,13 while others are induced during manufacturing of the porous electrode. 9,17 These processing-induced (initial) distribution of flaws seed the initial charge and end of life, while the daily cycling promotes the growth, coalescence, and linkage of energetically favored flaws.…”

“…[9][10][11][12][13][14][15][16] Many flaws form during the processing (synthesis) of the particles, 9,13 while others are induced during manufacturing of the porous electrode. 9,17 These processing-induced (initial) distribution of flaws seed the initial charge and end of life, while the daily cycling promotes the growth, coalescence, and linkage of energetically favored flaws. [9][10][11]13,16 Different types of mechanically-induced flaws have been reported in the literature, e.g., see Fig.…”