Abstract
The selection of a vessel by an induction-hob user has a significant impact on the performance of the appliance. Due to the induction heating physical phenomena, there exist many factors that modify the equivalent impedance of induction hobs and, consequently, the operational conditions of the inverter. In particular, the type of vessel, which is a sole decision of the user, strongly affects these parameters. Besides, the ferromagnetic properties of the different materials the vessels are made with, vary differently with the excitation level, and given that most of the domestic induction hobs are based on an ac-bus voltage arrangement, the excitation level continuously varies. The algorithm proposed in this work takes advantage of this fact to identify the equivalent impedance of the load and recognize the pot. This is accomplished through a phase-sensitive detector that was already proposed in the literature and the application of deep learning. Different convolutional neural networks are tested on an augmented experimental-based dataset and the proposed algorithm is implemented in an experimental prototype with a system-on-chip. The proposed implementation is presented as an effective and accurate method to characterize and discriminate between different pots that could enable further functionalities in new generations of induction hobs.
Highlights
Induction heating is a contact-less heating method that has been widely used in many applications [1]–[3]
In the domestic induction heating (DIH) case, its main advantage compared to the resistive cooktops is that while in the last ones the hottest component is the resistor, in the former, the hottest element is the bottom part of the pot
The identification method is based on a phase-sensitive detector (PSD), which generates the sinusoidal signals that are synchronized with the inverter signals
Summary
Induction heating is a contact-less heating method that has been widely used in many applications [1]–[3]. Villa et al.: Vessel Recognition in Induction Heating Appliances—A Deep-Learning Approach the electromagnetic compatibility (EMC) with the grid This filter is mainly designed to comply with the standards that limit the emissions of radio-frequency disturbances in the frequency range from 9 kHz to 30 MHz. One of the drawbacks and challenges of DIH is that the equivalent load varies with many parameters such as the switching frequency, the excitation level, the characteristics of the pot (material, size, temperature), the misalignment and distance between the inductor and the pot, etc. In [19] the authors calculate the power factor and the absolute value of the impedance, |Z|, for the first four harmonics of the switching frequency and apply a neural network to estimate the size of the vessel placed above the inductor In this case, the algorithm is implemented in a simpler induction hob with a single inductor and a single-switch inverter.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
