Discovery Learning accelerates battery design evaluation

Fast and reliable validation of novel designs in complex physical systems such as batteries is critical to accelerating technological innovation. However, battery research and development remain bottlenecked by the prohibitively high time and energy costs required to evaluate numerous new design candidates, particularly in battery prototyping and life testing. Despite recent progress in data-driven battery lifetime prediction, existing methods require labeled data of target designs to improve accuracy and cannot make reliable predictions until after prototyping, thus falling far short of the efficiency needed to enable rapid feedback for battery design. Here, we introduce Discovery Learning (DL), a scientific machine-learning paradigm that integrates active learning, physics-guided learning, and zero-shot learning into a human-like reasoning loop, drawing inspiration from learning theories in educational psychology. DL can learn from historical battery designs and actively reduce the need for prototyping, thus enabling rapid lifetime evaluation for unobserved material-design combinations without requiring additional data labeling. To test DL, we present 123 industrial-grade large-format lithium-ion pouch cells, spanning eight material-design combinations and diverse cycling protocols. Trained solely on public datasets of small-capacity cylindrical cells, DL achieves 7.2% test error in predicting the average cycle life under unknown device variability. This results in savings of 98% in time and 95% in energy compared to industrial practices. This work highlights the potential of uncovering insights from historical designs to inform and accelerate the development of next-generation battery technologies. DL represents a key advance toward efficient data-driven modeling and helps realize the promise of machine learning for accelerating scientific discovery and engineering innovation.

Data-Driven Quantification of Battery Degradation Modes via Critical Features from Charging

Battery degradation modes influence the aging behavior of Li-ion batteries, leading to accelerated capacity loss and potential safety issues. Quantifying these aging mechanisms poses challenges for both online and offline diagnostics in charging station applications. Data-driven algorithms have emerged as effective tools for addressing state-of-health issues by learning hard-to-model electrochemical properties from data. This paper presents a data-driven method for quantifying battery degradation modes. Ninety-one statistical features are extracted from the incremental capacity curve derived from 1/3C charging data. These features are then screened based on dispersion, contribution, and correlation. Subsequently, machine learning models, including four baseline algorithms and a feedforward neural network, are used to estimate the degradation modes. Experimental validation indicates that the feedforward neural network outperforms the others, achieving a root mean square error of around 10\% across all three degradation modes (i.e., loss of lithium inventory, loss of active material on the positive electrode, and loss of active material on the negative electrode). The findings in this paper demonstrate the potential of machine learning for diagnosing battery degradation modes in charging station scenarios.