With the increasing demand for the driving range of new energy vehicles, the energy of power battery is increasing. As a temperature‐sensitive component, the life, safety, and charge–discharge performance of lithium‐ion power battery will be affected by the working temperature, which makes the battery thermal management system particularly important. Concerning the fact that the thermal contact resistance between the power battery and the heat transfer components has become the bottleneck of battery thermal management system, this study firstly establishes a traditional sandwich structure of phase change material–based thermal management system and then try to reduce the thermal contact resistance of the system by increasing the thermal conductivity of the cooling part and filling the interface with high thermal conductivity material. The thermal contact resistance and the heat flux between the power battery and the thermal management module are experimentally tested and calculated. Based on the external and internal temperature of battery, the effect of contact resistance on the performance of a thermal management system is discussed. The results show that when increasing the thermal conductivity of the cooling part, the battery external and internal temperatures under 3C, 4C, and 5C discharge are reduced by 8.3%, 8.1%, 7.6% and 5.2%, 9.3%, 6.3%, respectively, as compared to the traditional sandwich structure of phase change material–based thermal management system. And the temperatures are further reduced by 6.5%, 7.7%, 6.3% and 7.8%, 6.1%, 7.3% when the interface between the battery and the thermal management module are filled with graphene with high thermal conductivity. Furthermore, the power battery can work within the optimum operating temperature range for a long period and can ensure battery safety by reducing the thermal contact resistance.
Accurate estimation of battery health is an effective means of improving the safety and reliability of electrical equipment. However, developing data-driven models to estimate battery state of health (SOH) is challenging when the amount of data is restricted. In this regard, this study proposes a method for estimating the SOH of lithium batteries based on sample data generation and a temporal convolutional neural network. First, we analyzed the charge/discharge curves of the batteries, from which we extracted features that were highly correlated with the SOH decay. Then, we used a Variational Auto-Encoder (VAE) to learn the features and distributions of the sample data to generate highly similar data and enrich the number of samples. Finally, a temporal convolutional neural network (TCN) was built to mine the nonlinear relationship between features and SOH by combining the source and extended domain data to realize SOH estimation. The experimental results show that the proposed method in this study has less than 2% error in SOH estimation, which improves the accuracy by 64.9% based on its baseline model. The feasibility of using data-driven models for battery health management in data-constrained application scenarios is demonstrated.