A front-end identification scheme of mutual inductance and load resistance for inductive power transfer (IPT) systems based on random forest regression (RFR) is proposed in this paper. RFR is one of the most commonly used algorithms in the field of machine learning (ML) with the merits of excellent generalization ability and high computing speed. Compared with the traditional model-based identification methods that need to be conducted at the sub-resonant frequencies, the proposed RFR-based estimation scheme can predict mutual inductance and load resistance at the resonant frequencies simultaneously and accurately. In addition, the proposed monitoring strategy is easy to implement as only the root mean square (RMS) values of the primary side voltage and current are needed. A large number of experimental data are used to verify the performance of the proposed RFR-based method.
