Fig. 5: Visualization results of the LASSO algorithm for different feature combinations. | Communications Engineering

Fig. 5: Visualization results of the LASSO algorithm for different feature combinations.

From: Data-driven available capacity estimation of lithium-ion batteries based on fragmented charge capacity

Fig. 5: Visualization results of the LASSO algorithm for different feature combinations.

The available capacity estimation performance is plotted for 8 feature combinations, and the results for the remaining 28 combinations are referenced in Supplementary Figs. 6–9. The 8 feature combinations include (segments 3, 9) (a), (segments 2, 9) (b), (segments 7, 9) (c), (segments 5, 9) (d), (segments 9, 11) (e), (segments 1, 9) (f), (segments 8, 9) (g), and (segment 9) (h). The gradients correspond to varying point-aggregation densities. RMSE denotes root-mean-square error and MAPE denotes mean absolute percentage error.

Back to article page