Beyond Expert‐Level Performance Prediction for Rechargeable Batteries by Unsupervised Machine Learning

Abstract

Predicting the performance of rechargeable batteries in real time is of great importance to battery research and industrial production, and hence has been a long pursuit. Previously, sophisticated apparatus is required to measure indicator properties of performance, while machine learning approaches based on feature engineering procedures require a priori expertise that is challenged by the complicated environment of real‐world applications. Here, for a more effective real‐time prediction of battery life and failure, a novel end‐to‐end unsupervised machine learning approach is shown; this approach is free from feature engineering and uses only the raw images of the charge–discharge voltage profiles. This model enables unsupervised real‐time automatic extraction of latent physical factors that control the performance of Na‐ion batteries to classify good or bad cycling performance by using only the voltage profile of the first cycle. This model can also monitor the safety of Li‐metal battery systems by giving warnings when the battery is approaching a failure. With the beyond expert‐level prediction ability, the abovementioned framework can be a promising prototype to further develop and enable high accuracy predictions of battery performance for real‐world applications in the future.

Li Penetration in Ceramic Solid Electrolytes: Operando Microscopy Analysis of Morphology, Propagation, and Reversibility

“…Voltage trace analysis has been demonstrated as a potential means for on-board diagnostics using machine-learning techniques, and thus linking of voltage signatures with underlying phenomena is of great interest. 46 The preferential plating into and stripping from the dendritic structures suggests that there is a difference between the two interfaces. This behavior was also observed in liquid electrolytes, where it was attributed to a thinner solid electrolyte interface (SEI) on the freshly plated Li inside the dendritic structures.…”

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

“…For example, CNNs have recently been used for battery health prediction and crack detection in labelled data. [18][19][20][21][22] While CV approaches show great promise as an alternative route to analyze image data, their application to segmentation of 3D tomographic data remains limited. Two notable examples used semantic segmentation for an accurate multi-phase electrode segmentation and object recognition and, semantic segmentation of flawed particles.…”

Artificial Intelligence Applied to Battery Research: Hype or Reality?

“…(a) Autoencoder anomaly detector for failure prediction: schematics of an autoencoder NN and (b) cycles before the last 30 and within the last 30 show distinct features indicated by the reconstruction error of the autoencoder . (a, b) Figure reproduced with permission from ref . Copyright 2019 Wiley.…”

“…In a recent study, Chen et al 391 used a novel end-to-end unsupervised ML approach for a more effective real-time prediction of battery life and failure. This model enabled unsupervised real-time automatic extraction of latent physical factors that control the performance of Na-ion batteries, classifying them as having good or bad cycling performance, using only the voltage profile of the first cycle.…”