Vessel Recognition in Induction Heating Appliances—A Deep-Learning Approach

The selection of a vessel by an induction-hob user has significant impact on the performance appliance. Due to induction heating physical phenomena, there exist many factors that modify equivalent impedance hobs and, consequently, operational conditions inverter. In particular, type vessel, which is sole decision user, strongly affects these parameters. Besides, ferromagnetic properties different materials vessels are made with, vary differently with excitation level, and given most domestic based ac-bus voltage arrangement, level continuously varies. algorithm proposed in this work takes advantage fact identify load recognize pot. This accomplished through phase-sensitive detector was already literature application deep learning. Different convolutional neural networks tested augmented experimental-based dataset implemented experimental prototype system-on-chip. implementation presented as effective accurate method characterize discriminate between pots could enable further functionalities new generations hobs.