Parameter Extraction for Equivalent Circuit of Common Mode Choke Based on Deep Neural Network, Random Forest Tree and Extreme Gradient Boosting Algorithm

Common mode chokes are critical components in electromagnetic interference (EMI) filters. Various parameters of passive components are required for building an EMI filter simulation model. However, the complexity of the equivalent circuit model and difficulty of parameter sets are increased due to the parasitic capacitance and inductance of the loop coil and the magnetic permeability of the ferrite core changed by the frequency. In this research, it is proposed to use deep learning, Random Forest Tree and Extreme Gradient Boosting (Xgboost) regression, three methods to extracting parameters of components in the equivalent circuit by training simulated impedance data of 5 ports of common mode chock.