Abstract: To address the shortcomings of existing estimation methods in feature extraction and time series modeling, a state-of-health estimation method lithium battery that integrates multi-scale convolutional neural networks with gated dual attention units is proposed. Firstly, health indicators reflecting the aging process are extracted from the battery charging curve. Subsequently, local fluctuations and long-term trend features in the battery degradation sequence are extracted in parallel using convolutional kernels of different sizes, and the gated dual attention unit is utilized to enhance the model's ability to model long-term dependencies and improve estimation accuracy. Finally, verification and analysis are conducted on the aging dataset. The proposed method significantly outperforms traditional support vector regression, bidirectional long short-term memory, and gated recurrent unit models, demonstrating excellent performance.