State of health prediction of lithium-ion batteries for driving conditions based on full parameter domain sparrow search algorithm and dual-module bidirectional gated recurrent unit

TL;DR

The study tackles Li-ion battery SOH prediction under driving conditions by fusing a dual-module BiGRU with full-parameter-domain optimization via Sparrow Search Algorithm. Indirect health indicators are extracted from Incremental Capacity curves using ICA and SVD-denoising, then selected through Spearman correlation to feed the BiGRU time-series model. The key contributions include (1) HI extraction from IC curves, (2) full-domain SSA hyperparameter optimization for a robust dual-BiGRU predictor, and (3) validation on both Oxford driving-condition datasets and real EV charging data, showing improved accuracy, robustness, and generalization. The findings suggest the approach provides accurate, early SOH predictions suitable for EV battery management in real-world conditions, with practical potential for deployment in prognostics and maintenance scheduling.

Abstract

Aiming at the state of health (SOH) prediction of lithium-ion batteries (LiBs) for electric vehicles (EVs), this paper proposes a fusion model of a dual-module bidirectional gated recurrent unit (BiGRU) and sparrow search algorithm (SSA) with full parameter domain optimization. With the help of Spearman correlation analysis and ablation experiments, the indirect health indicator (HI) that can characterize the battery degradation is extracted first based on the incremental capacity (IC) curves of the Oxford battery dataset, which simulates the driving conditions. On this basis, the filtered one-dimensional HI is inputted into the dual-module BiGRU for learning the pre- and post-textual information of the input sequence and extracting the sequence features. In order to combine the different hyperparameters in the dual-module BiGRU, SSA is used to optimize the hyperparameters in the full parameter domain. The proposed SSA-BiGRU model combines the advantages and structures of SSA and BiGRU to achieve the highly accurate SOH prediction of LiBs. Studies based on the Oxford battery dataset have shown that the SSA-BiGRU model has higher accuracy, better robustness and generalization ability. Moreover, the proposed SSA-BiGRU model is tested on a real road-driven EV charging dataset and accurate SOH prediction are obtained.

Figures (21)

• Figure 1: Schematic diagram of feature extraction based on IC curve.
• Figure 2: Capacity degradation curve of Oxford battery dataset.
• Figure 3: SOH curves of Oxford battery dataset.
• Figure 4: Partial charge IC curve of battery Cell2.
• Figure 5: Thermogram of SVD-HI vs. SOH Spearman correlation for battery Cell2.