Piecewise-linear modelling with automated feature selection for Li-ion battery end-of-life prognosis

The complex nature of lithium-ion battery degradation has led to many machine learning-based approaches for health forecasting being proposed in the literature. However, learning using sophisticated models can be computationally expensive, and although linear are faster they also inflexible. Piecewise-linear offer a compromise—a fast flexible alternative that is not as expensive techniques such neural networks or Gaussian process regression. Here, piecewise-linear approach forecasting, including an automated feature selection step, compared regression model found perform equally well terms median error on training dataset, indeed somewhat better at 95th percentile error. demonstrates benefit limiting correlation between inputs. Further trials was robust changing input size availability data. • Data-driven capacity fade Automated breakpoint selection. Median RMS result 1.1% predictions 1.6% end life. Fast, interpretable memory efficient more ML approaches.