Identification and machine learning prediction of knee-point and knee-onset in capacity degradation curves of lithium-ion cells

High-performance batteries greatly benefit from accurate,early predictions of future capacity loss,to advance the management of the battery and sustain desirable application-specific performance characteristics for as long as possible.Li-ion cells exhibit a slow capacity degradation up to a knee-point,after which the degradation ac-celerates rapidly until the cell’s End-of-Life.Using capacity degradation data,we propose a robust method to identify the knee-point within capacity fade curves.In a new approach to knee research,we propose the concept‘knee-onset’,marking the beginning of the nonlinear degradation,and provide a simple and robust identifica-tion mechanism for it.We link cycle life,knee-point and knee-onset,where predicting/identifying one promptly reveals the others.On data featuring continuous high C-rate cycling(1C–8C),we show that,on average,the knee-point occurs at 95%capacity under these conditions and the knee-onset at 97.1%capacity,with knee and its onset on average 108 cycles apart.After the critical identification step,we employ machine learning(ML)techniques for early prediction of the knee-point and knee-onset.Our models predict knee-point and knee-onset quantitatively with 9.4% error using only information from the first 50 cycles of the cells’life.Our models use the knee-point predictions to classify the cells’expected cycle lives as short,medium or long with 88–90% accuracy using only information from the first 3–5 cycles.Our accuracy levels are on par with existing literature for End-of-Life prediction(requiring information from 100-cycles),nonetheless,we address the more complex problem of knee prediction.All estimations are enriched with confidence/credibility metrics.The uncertainty regarding the ML model’s estimations is quantified through prediction intervals.These yield risk-criteria insurers and manufacturers of energy storage applications can use for battery warranties.Our classification model provides a tool for cell man-ufacturers to speed up the validation of cell production techniques.

Automatic method for the estimation of li-ion degradation test sample sizesrequired to understand cell-to-cell variability

The testing of battery cells is a long and expensive process, and hence understanding how large a test set needsto be is very useful. This work proposes an automated methodology to estimate the smallest sample size ofcells required to capture the cell-to-cell variability seen in a larger population. We define cell-to-cell variationbased on the slopes of a linear regression model applied to capacity fade curves. Our methodology determinesa sample size which estimates this variability within user specified requirements on precision and confidence.The sample size is found using the distributional properties of the slopes under a normality assumption, andan implementation of the approach is available on GitHub.For the five datasets in the study, we find that a sample size of 8–10 cells (at a prespecified precision andconfidence) captures the cell-to-cell variability of the larger datasets. We show that prior testing knowledge canbe leveraged with machine learning models to operationally optimise the design of new cell-testing, leadingup to a 75% reduction in experimental costs.