As electric vehicles return growing numbers of retired lithium-ion batteries, reusing them in second-life storage is attractive, yet how a cell was operated, above all the state-of-charge window it was cycled within, strongly shapes how it has aged. The usage history of a retired cell is usually undocumented, and existing battery-management methods treat the operating conditions as a known input rather than as a quantity to be recovered. In contrast to data-driven methods that forecast a present or future battery state, this work reconstructs that past operating condition and shows that the window, a five-class label, can be recovered from a single charge–discharge cycle using only eight leakage-free features derived from charge and energy efficiency and three cell-surface temperatures. The capacity and voltage quantities that would trivially reveal the window are excluded by design. A regularised logistic-regression classifier is selected from a pool of candidate models and validated one cell at a time on twenty commercial prismatic cells. It identifies the window with a per-cycle balanced accuracy of 0.797 and classifies seventeen of the twenty cells correctly, a result well above chance and confirmed by a permutation test. Because the windows are ordered by depth of discharge, the few mistakes remain mild on that scale, with a quadratically weighted κ of 0.82 and a depth-of-discharge mean absolute error near one percentage point, and they fall only between the two windows that are physically almost identical. The most informative signals are the drop in energy efficiency and the rise in surface temperature that accompany deeper cycling. These findings show that an unknown usage history can be read back from a single low-cost measurement, offering a practical tool for screening and grading cells in second-life battery management.

The state-of-charge (SoC) window used during cycling influences battery behaviour and is relevant to the assessment of cells considered for second-life use. This study investigates whether the SoC window in which a cell was cycled can be identified from the electro-thermal response of a single reference cycle that is identical for every cell, without cycling data recorded within that window. Twenty commercial 102 Ah prismatic lithium iron phosphate (LFP) cells were cycled in five fixed SoC windows with periodic reference cycles. Sixty-five features describing capacity, efficiencies, rest voltages, the voltage curve and surface temperatures were derived from each reference cycle. Under leave-one-cell-out cross-validation, a regularised logistic-regression classifier achieved a per-cycle balanced accuracy of 0.75, and aggregating each cell’s reference cycles correctly classified 19 of 20 cells. With feature-group, model and hyper-parameter selection nested within each fold, the per-cycle balanced accuracy was 0.61 and 16 cells were correctly classified. Misclassifications were concentrated between closely related windows, with a quadratically weighted $\kappa$ of 0.88 and a depth-of-discharge mean absolute error of 2.0 percentage points. Rest voltages after the full discharge provided the strongest discrimination. The results establish single-cycle window identification for the tested cells and conditions, providing a basis for second-life assessment.