No abstract

No abstract

This paper proposes an optimal power distribution method for multi-objective wireless power transfer (WPT) systems, aiming to improve the transmission flexibility and satisfy various power demands. Previous studies have barely explored the impact of wide-range and unpredictable variations of load parameters on the performance of multi-channel power transmissions. In this paper, by taking the impact of equivalent impedance, motion, power demand variation and response speed of charging object into consideration, an optimal power distribution scheme with fast response, high stability and high accuracy is proposed to satisfy various power demands from multiple objectives including portable electronics, moving electric vehicles (EVs), batteries and super capacitors, without using any communication networks. The effectiveness of the proposed control scheme is demonstrated by simulation results based on different charging cases and experimental results based on a 10 W prototype.

No abstract

We propose a general method for growing neural network with shared parameter by matching trained network to new input. By leveraging Hoeffding's inequality, we provide a theoretical base for improving performance by adding subnetwork to existing network. With the theoretical base of adding new subnetwork, we implement a matching method to apply trained subnetwork of existing network to new input. Our method has shown the ability to improve performance with higher parameter efficiency. It can also be applied to trans-task case and realize transfer learning by changing the combination of subnetworks without training on new task.