A K-Means Approach to Temperature Estimation in Non-Linear Power Inductors

Abstract

The temperature of a power inductor operated up to saturation in a DC/DC converter is estimated based on its current profile. A dataset built by a proper model of the non-linear inductor was generated, reproducing its current profiles in different operating points. The measured current waveform is compared with the dataset values. The K-means classification is adopted to obtain clusters characterizing the operation in saturation, in which a precise estimation can be carried out. The linear and the deep saturation zones give poor information about the temperature; on the other hand, the temperature evaluation is of interest up to saturation. The K-means clustering allows for a relevant reduction in the computational effort. The proposed approach avoids direct measurement of the current by dedicated sensing; the temperature can be forecast before reaching the steady state, enhancing the converter’s reliability. Finally, experimental tests are used to assess the goodness of the proposed method.