A Self-attention Knowledge Domain Adaptation Network for Commercial Lithium-ion Batteries State-of-health Estimation under Shallow Cycles

TL;DR

This paper introduces an unsupervised deep transfer learning approach using self-attention and domain adaptation techniques to accurately estimate the state-of-health of lithium-ion batteries under shallow-cycle conditions, where labeled data is scarce.

Contribution

It presents a novel method combining self-attention distillation and multi-kernel MMD for domain adaptation in battery SOH estimation without requiring full-cycle data.

Findings

Achieves RMS error within 2% for SOH estimation.

Outperforms existing transfer learning methods across various conditions.

Effective for batteries from different manufacturers and operating environments.

Abstract

Accurate state-of-health (SOH) estimation is critical to guarantee the safety, efficiency and reliability of battery-powered applications. Most SOH estimation methods focus on the 0-100\% full state-of-charge (SOC) range that has similar distributions. However, the batteries in real-world applications usually work in the partial SOC range under shallow-cycle conditions and follow different degradation profiles with no labeled data available, thus making SOH estimation challenging. To estimate shallow-cycle battery SOH, a novel unsupervised deep transfer learning method is proposed to bridge different domains using self-attention distillation module and multi-kernel maximum mean discrepancy technique. The proposed method automatically extracts domain-variant features from charge curves to transfer knowledge from the large-scale labeled full cycles to the unlabeled shallow cycles. The CALCE and SNL battery datasets are employed to verify the effectiveness of the proposed method to estimate the battery SOH for different SOC ranges, temperatures, and discharge rates. The proposed method achieves a root-mean-square error within 2\% and outperforms other transfer learning methods for different SOC ranges. When applied to batteries with different operating conditions and from different manufacturers, the proposed method still exhibits superior SOH estimation performance. The proposed method is the first attempt at accurately estimating battery SOH under shallow-cycle conditions without needing a full-cycle characteristic test.