With the increasingly serious problem of environmental pollution, new energy vehicles have become a hot spot in today’s research. The lithium-ion battery has become the mainstream power battery of new energy vehicles as it has the advantages of long service life, high-rated voltage, low self-discharge rate, etc. The battery management system is the key part that ensures the efficient and safe operation of the vehicle as well as the long life of the power battery. The accurate estimation of the power battery state directly affects the whole vehicle’s performance. As a result, this paper established a lithium-ion battery charge state estimation model based on BP, PSO-BP and LSTM neural networks, which tried to combine the PSO algorithm with the LSTM algorithm. The particle swarm algorithm was utilized to obtain the optimal parameters of the model in the process of repetitive iteration so as to establish the PSO-LSTM prediction model. The superiority of the LSTM neural network model in SOC estimation was demonstrated by comparing the estimation accuracies of BP, PSO-BP and LSTM neural networks. The comparative analysis under constant flow conditions in the laboratory showed that the PSO-LSTM neural network predicts SOC more accurately than BP, PSO-BP and LSTM neural networks. The comparative analysis under DST and US06 operating conditions showed that the PSO-LSTM neural network has a greater prediction accuracy for SOC than the LSTM neural network.

A battery thermal management system (BTMS) with functions of heat dissipation and heating by using only one liquid and one structure was studied, and a design for a new type of thermal management device structure was proposed. To find the influence factors of the BTMS on heat dissipation and heating characteristics, we selected and simulated three parameters: inlet size, liquid flow rate, and temperature. The convective heat transfer coefficient h and the Nusselt number Nu were used to analyze the influence of inlet size and liquid velocity on heat transfer intensity. The results show that: (1) In the temperature environment of 298 K with different discharge rates, a pipe diameter of 10 mm is the best size of the BTMS; (2) The increase in flow rate can increase the convective heat transfer coefficient h and the Nusselt number Nu. When the flow rate is 0.02 m/s, the growth rate of h and Nu is the largest; (3) The higher the fluid temperature, the faster the temperature of the battery pack increases in cold environments, but the uneven surface temperature of the battery is also more obvious.

Lithium-ion batteries which are used in electric vehicles cannot be charged to their maximum capacity at the end of the charging period, a situation which is caused by inconsistency between the battery cells. This paper takes the 18650 ternary lithium battery as the research object and proposes an alternate equalization control system in the charging process. This system takes SOC consistency to be the equalization variable. Through controlling the relay, this system realizes the alternate recombination between different batteries in order to form a series battery group for charging, which achieves the goal of SOC equalization of the entire battery group. The simulation result of charge equalization, based on Matlab/Simulink, shows that at the end of the charging simulation, the SOC inconsistency of the battery group reduced from 10% to 1%. Finally, an experimental platform was built in order to verify the experiment. During the charge balance experiment, the maximum SOC inconsistency between the batteries reduced from 1.542% to 1.035%. The SOC inconsistency at the end of charging reduced from 1.214% to 0.8%, which represents an improvement of the equalization effect of the control system. The experimental results are consistent with the simulation results, which proves the effectiveness of the system’s ability to control the battery SOC balance during the charging process.