Accurate and reliable state of health (SOH) estimation is essential to ensure the stable and safe operation of lithium-ion batteries. The SOH estimation for batteries with different formulations remains challenging. To solve this problem, this paper proposed a novel transfer learning (TL) framework with attention mechanisms and random forest (RF) regression for battery health estimation. First, only partial charging voltage and current are used in this method, significantly enhancing adaptability to real-world working conditions. Furthermore, multiple attention mechanisms are integrated with the convolution neural network (CNN) to improve feature acuity and expedite convergence. Pre-training tests conducted on three different datasets affirm that the multi attention mechanisms lead to a substantial reduction in estimation errors by 80.9%, 41.3% and 25.6% for LCO, LFP and NCA respectively. Moreover, to ensure precise SOH estimation for batteries with diverse formulations while mitigating the risk of overfitting on limited data, a novel transfer learning (TL) strategy is employed. This involves the freezing of CNN parameters and the transformation of dense layers using RF regression. The optimization of three critical hyper-parameters in the RF process is accomplished through the Tree-structure Parzen Estimator (TPE) method instead of inefficient brute-force search. In the TL process, despite the training data for fine-tuning only occupies 20%, the root mean square error (RMSE) of SOH estimation is impressively low, standing at only 0.46% and 1.61% for LFP and NCA, respectively.

Complex operating conditions of lithium-ion batteries in practical applications bring challenges to accurate diagnosis of battery aging. This article proposes a practical method to estimate both battery capacity and electrode aging through an open-circuit voltage (OCV) reconstruction process. First, the recursive least square algorithm is implemented in a real battery management system (BMS) to identify OCV in real-time. Then, an electrode OCV model is employed to reconstruct the OCV curve based on the raw identified data from BMS. Thus, the parameters of the electrode OCV model are obtained, with which the battery capacity and electrode aging can be determined. During OCV reconstruction, a two-step estimation method with weighted objective functions is utilized to address the impact of fragmented and poorly identified OCV in BMS. Meanwhile, the Peukert coefficient is employed to improve the adaptability to different temperatures. The proposed method is validated with four aged batteries at different temperatures of 5 $^\circ \rm C$ , 25 $^\circ \rm C$ , and 45 $^\circ \rm C$ , respectively. Experimental results indicate that the proposed method can achieve accurate estimations of battery capacity and electrode aging state at various temperatures.