Position Prediction for Dynamic Wireless Power Transfer Based on BP Neural Network

-This paper presents a position prediction technology for electric vehicle (EV) based on back propagation (BP) neural network. It aims to solve the problem of predicting the positions of transmitting and receiving coils in dynamic wireless power transfer (DWPT) systems. Simulated measurements and training learning are conducted on the voltage, current, coupling coefficient on the transmitting side, and the load resistance on the receiving side. The BP neural network is then employed to fit the nonlinear relationship, achieving efficient and accurate prediction of the coupling coefficient between the two coils. This allows for calculating the EV's position. Simulation models and BP neural network models are established. Extensive data training and testing are conducted to demonstrate the effectiveness and accuracy of this method. Through the analysis of the error distribution diagram, the overall accuracy of the BP neural network has been confirmed by us. It effectively predicts the coupling coefficients
$K$
1 and
$K$
2.