Title:  Applications Of Machine Learning Strategy For Wireless Power Transfer And Identification

Committee: 

Dr. Tentzeris, Advisor   

Dr. Peterson, Chair

Dr. Durgin

Abstract:

The objective of the proposed research is to propose and demonstrate machine learning (ML) applications into the wireless power transfer and identification technology. Specifically, this work describes the implementation of a ML strategy based on 1) the Neural Network for real-time range-adaptive automatic impedance matching of WPT applications, which can perform the effective prediction of the optimal parameters of the tunable matching network and classification range-adaptive transmitter coils to achieve an effective automatic impedance matching over a wide range of relative distances and 2) the Support Vector Machine (SVM) classification strategy for read/interrogation enhancement in chipless RFID applications, which can perform effective transponder readings for a wide variety of ranges ranges and contexts.