State of health is a critical state which evaluates the degradation level of batteries. However, it cannot be measured directly but requires estimation. While accurate state of health estimation has progressed markedly, the time- and resource-consuming degradation experiments to generate target battery labels hinder the development of state of health estimation methods. In this article, we design a deep-learning framework to enable the estimation of battery state of health in the absence of target battery labels. This framework integrates a swarm of deep neural networks equipped with domain adaptation to produce accurate estimation. We employ 65 commercial batteries from 5 different manufacturers to generate 71,588 samples for cross-validation. The validation results indicate that the proposed framework can ensure absolute errors of less than 3% for 89.4% of samples (less than 5% for 98.9% of samples), with a maximum absolute error of less than 8.87% in the absence of target labels. This work emphasizes the power of deep learning in precluding degradation experiments and highlights the promise of rapid development of battery management algorithms for new-generation batteries using only previous experimental data.

Battery models are the cornerstone to battery state of charge (SOC) estimation and battery management systems in electric vehicles. This paper proposes a novel fractional order model for a battery which considers both Butler-Volmer equation and fractional calculus of constant phase element. The structure characteristics of the proposed model are then analyzed, and a novel identification method which combines least squares and nonlinear optimization algorithm is proposed. The method is proven to be efficient and accurate. Based on the proposed model, a fractional order unscented Kalman filter is developed to estimate SOC while singular value decomposition is applied to tackle the nonlinearity of Butler-Volmer equation and fractional calculus of constant phase element. The systematic comparison between the proposed model and traditional fractional order model is carried out on two NMC lithium ion batteries at different temperatures, ageing levels and electric vehicle current profiles. The comparison results show that the proposed model has higher estimation accuracy in battery terminal voltage and SOC than the other two models over wide range of temperature and ageing level under electric vehicle operation conditions. Furthermore, the hardware-in-the-loop test validates that the proposed SOC estimation method is suitable for SOC estimation in electric vehicles.

State of health estimation of lithium ion battery is a key but challengeable technique for the application of electric vehicles. Due to the ambiguous ageing mechanisms and sensitivity to the applied conditions of lithium-ion batteries, the recognition of ageing mechanisms and SOH monitoring of the battery might be difficult. A novel SOH estimation and ageing mechanism identification method is presented in this paper. First, considering the dispersion effect, a fractional order model is constructed and the parameter identification approach is proposed, and a comparison between integer order model and fractional order model has been done from the prospect of predicting accuracy. Then, based on the identified open circuit voltage, battery ageing mechanism can be analyzed by the means of incremental capacity analysis method. Moreover, the normalized Incremental capacity peak is used to estimate the remaining capacity. Finally, the robustness of the SOH estimation method is validated by batteries aged at different conditions based on the idea of cross validation and the estimation error of the remaining capacity can be reduced within 3.1%.