State of Charge and Temperature Joint Estimation Based on Ultrasonic Reflection Waves for Lithium-Ion Battery Applications

Accurate estimation of the state charge (SOC) and temperature batteries is essential to ensure safety energy storage systems. However, it very difficult obtain multiple states battery with fewer sensors. In this paper, a joint method for lithium iron phosphate battery’s SOC based on ultrasonic reflection waves proposed. A piezoelectric transducer affixed surface ultrasonic–electric transduction. Ultrasonic signals are excited at transducer, transmitted through battery, back by reaching underside battery. Feature indicator extraction intervals determined sliding–window matching correlation analysis. Virtual samples used expand data after feature extraction. Finally, backpropagation (BP) neural network model applied multistate in wide range. According experimental results, root mean square error (RMSE) lithium-ion results 7.42% 0.40 °C, respectively. The nondestructive easy apply management Combined detection gas production inside can improve system.