Title:	Neuro-fuzzy approaches to estimating thermal overstress behavior of IGBTs
Authors:	Jamshidi, Mohammad Talla, Jakub Peroutka, Zdeněk Roshani, Saeed
Citation:	JAMSHIDI, M. TALLA, J. PEROUTKA, Z. ROSHANI, S. Neuro-fuzzy approaches to estimating thermal overstress behavior of IGBTs. In 2021 IEEE 19th International Power Electronics and Motion Control Conference (PEMC) : /proceedings/. Piscaway: IEEE, 2021. s. 843-850. ISBN: 978-1-72815-660-6
Issue Date:	2021
Publisher:	IEEE
Document type:	konferenční příspěvek ConferenceObject
URI:	2-s2.0-85107490862 http://hdl.handle.net/11025/46661
ISBN:	978-1-72815-660-6
Keywords in different language:	IGBT;fuzzy systems;machine learning;system identification;thermal model;ANFIS
Abstract in different language:	The Thermal overstress behavior of power semiconductor components is a determining factor to evaluate the reliability and performance of power electronic devices. Many theoretical and empirical methods have been presented to address the thermal effects of power electronics components on the quality of power systems. However, analyzing temperature brings to us a large number of uncertainties and nonlinearities affecting the accuracy of modeling. This paper proposes three neuro-fuzzy based techniques to estimate the temperature of Insulated Gate Bipolar Transistors (IGBTs). These techniques include grid partitioning clustering, Fuzzy C-Means (FCM) clustering, and subtractive clustering. An experimental dataset containing over 1.5 million data points is used to develop and train the proposed neuro-fuzzy approaches. This dataset is obtained during a comprehensive investigation on IGBTs and thermal effects by scientists at Ames Research Center of NASA. Preliminary results have demonstrated that the applied approaches are superior to estimating the thermal overstress behavior of IGBTs.
Rights:	Plný text je přístupný v rámci univerzity přihlášeným uživatelům. © IEEE
Appears in Collections:	Konferenční příspěvky / Conference papers (RICE) Konferenční příspěvky / Conference Papers (KEV) OBD

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.