A self-attention knowledge domain adaptation network for commercial lithium-ion batteries state-of-health estimation under shallow cycles

Abstract

Accurate state-of-health (SOH) estimation is crucial for the safety, efficiency, and reliability of battery-powered systems. Conventional SOH estimation methods are designed for the full state-of-charge (SOC) range of 0%–100%, assuming uniform distributions. Yet, batteries in real-world applications often operate under partial SOC ranges and experience shallow-cycle conditions, which result in distinct and unlabeled degradation profiles that make SOH estimation more complex. To tackle this issue, we propose a novel method—self-attention knowledge domain adaptation network (SKDAN)—which utilizes a self-attention distillation module combined with a multi-kernel maximum mean discrepancy framework to effectively navigate between these disparate domains. This strategy successfully extracts domain-specific features from charging curves, facilitating the transfer of knowledge from well-labeled full cycles to unlabeled shallow cycles. The effectiveness of the SKDAN method is validated through extensive testing on the CALCE and SNL battery datasets, demonstrating its robust capability to estimate SOH accurately across different SOC ranges, temperatures, and discharge rates. With a root-mean-square error (RMSE) of less than 2%, the SKDAN method outperforms existing transfer learning techniques for various SOC ranges. Additionally, it exhibits exceptional SOH estimation performance when applied to batteries from different manufacturers and operating under varied conditions. This study represents the first instance of accurately estimating battery SOH under shallow-cycle conditions without relying on full-cycle characteristic tests.