<p>Accurate and reliable estimation of the State of Health (SOH) of lithium-ion batteries is a fundamental requirement for the safe operation of Battery Management Systems in electric vehicles. Existing methods are broadly limited by the underutilization of complementary multi-modal information, overly simplistic fusion strategies that neglect cross-modal interactions, and the absence of explicit modeling between macroscopic temporal degradation signals and microscopic electrochemical impedance parameters. To address these limitations, this paper proposes DS-Transformer (Dual-Stream Transformer), an end-to-end dual-stream Transformer network. The model processes heterogeneous inputs through two parallel encoding paths: Stream 1 employs a multi-scale one-dimensional convolutional neural network to extract local degradation features from voltage, current, and temperature time-series signals recorded during discharge; Stream 2 uses a multi-layer perceptron to semantically encode the internal resistance (<InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(R_e\)</EquationSource> </InlineEquation>) and charge transfer resistance (<InlineEquation ID="IEq2"> <EquationSource Format="TEX">\(R_{ct}\)</EquationSource> </InlineEquation>). Unlike prior multi-modal methods that rely on simple feature concatenation, the two streams are dynamically aligned and explicitly fused through the proposed Cross-Stream Cross-Attention (CSCA) module, which uses temporal embeddings as Query and impedance embeddings as Key/Value to achieve semantic-level interaction modeling between degradation patterns and electrochemical states. A Transformer Encoder then captures global sequence dependencies, ultimately yielding SOH regression predictions. Systematic validation is conducted on the publicly available NASA AMES lithium-ion battery aging dataset (34 batteries, 7,565 experiments, covering five temperature conditions from 4<InlineEquation ID="IEq3"> <EquationSource Format="TEX">\(^\circ\)</EquationSource> </InlineEquation>C to 44<InlineEquation ID="IEq4"> <EquationSource Format="TEX">\(^\circ\)</EquationSource> </InlineEquation>C). DS-Transformer achieves MAE = 1.24%, RMSE = 1.67%, and <InlineEquation ID="IEq5"> <EquationSource Format="TEX">\(R^2\)</EquationSource> </InlineEquation> = 0.9782, improving over the best baseline by 28.3%, 27.1%, and 1.90%, respectively. Ablation studies quantitatively demonstrate that the CSCA module is the most critical contributor (MAE increases by 37.9% upon removal, outperforming simple concatenation by 27.5%), while the dual-stream architecture and Transformer encoder are each independently indispensable. Multi-temperature robustness experiments further validate the stable generalization capability of the proposed model. This work establishes, for the first time, an explicit cross-modal interaction framework between discharge temporal signals and electrochemical impedance parameters for battery SOH estimation, offering significant theoretical insights and practical engineering value.</p>

DS-transformer: a dual-stream transformer for lithium-ion battery state-of-health estimation via cross-attention fusion of discharge curves and impedance features

期刊论文
出版模式：

开放获取
发表日期：

2026年5月11日

查看全文

Xue Shi,
Jing Zeng,
Jiajia Zhang

摘要

Accurate and reliable estimation of the State of Health (SOH) of lithium-ion batteries is a fundamental requirement for the safe operation of Battery Management Systems in electric vehicles. Existing methods are broadly limited by the underutilization of complementary multi-modal information, overly simplistic fusion strategies that neglect cross-modal interactions, and the absence of explicit modeling between macroscopic temporal degradation signals and microscopic electrochemical impedance parameters. To address these limitations, this paper proposes DS-Transformer (Dual-Stream Transformer), an end-to-end dual-stream Transformer network. The model processes heterogeneous inputs through two parallel encoding paths: Stream 1 employs a multi-scale one-dimensional convolutional neural network to extract local degradation features from voltage, current, and temperature time-series signals recorded during discharge; Stream 2 uses a multi-layer perceptron to semantically encode the internal resistance ( \(R_e\) ) and charge transfer resistance ( \(R_{ct}\) ). Unlike prior multi-modal methods that rely on simple feature concatenation, the two streams are dynamically aligned and explicitly fused through the proposed Cross-Stream Cross-Attention (CSCA) module, which uses temporal embeddings as Query and impedance embeddings as Key/Value to achieve semantic-level interaction modeling between degradation patterns and electrochemical states. A Transformer Encoder then captures global sequence dependencies, ultimately yielding SOH regression predictions. Systematic validation is conducted on the publicly available NASA AMES lithium-ion battery aging dataset (34 batteries, 7,565 experiments, covering five temperature conditions from 4 \(^\circ\) C to 44 \(^\circ\) C). DS-Transformer achieves MAE = 1.24%, RMSE = 1.67%, and \(R^2\) = 0.9782, improving over the best baseline by 28.3%, 27.1%, and 1.90%, respectively. Ablation studies quantitatively demonstrate that the CSCA module is the most critical contributor (MAE increases by 37.9% upon removal, outperforming simple concatenation by 27.5%), while the dual-stream architecture and Transformer encoder are each independently indispensable. Multi-temperature robustness experiments further validate the stable generalization capability of the proposed model. This work establishes, for the first time, an explicit cross-modal interaction framework between discharge temporal signals and electrochemical impedance parameters for battery SOH estimation, offering significant theoretical insights and practical engineering value.