This paper proposes a novel fusion architecture that combines Liquid Neural Networks (LNN) with multi-head attention mechanisms for accurate State of Health (SOH) estimation of lithium-ion battery packs. The method employs learnable liquid time constants (LTC) that enable dynamic adjustment of memory characteristics based on input temporal patterns, while the multi-head attention mechanism identifies critical time steps that contribute most to SOH prediction. Additionally, we introduce an innovative coverage-averaging mapping strategy that transforms overlapping window predictions into smooth, cycle-level SOH estimates, eliminating the boundary discontinuities commonly observed in traditional sliding window approaches. Experimental evaluation on real battery data demonstrates competitive performance with an RMSE of 0.0072 and R² of 0.9248. The results show that the proposed method successfully captures the complex temporal dynamics of battery degradation processes while maintaining computational efficiency suitable for real-time deployment in battery management systems.

State of Health (SOH),Liquid Neural Networks (LNN),Multi-head attention