Abstract
A DC model for silicon carbide (SiC) metal–oxide–semiconductor field effect transistors (MOSFETs) is proposed in this paper using a hybrid modeling method based on the artificial neural network and artificial bee colony (ABC) algorithm. A multi-layer perceptron neural network using the Levenberg–Marquardt (LM) method is applied to model SiC MOSFETs based on the data provided by the datasheet. The search strategy of artificial bees is improved based on the standard ABC, which enhances the search ability of the standard ABC. In view of the sensitivity of the LM method to the initial value, the improved ABC algorithm is adopted to help the neural network find initial weights and biases, which improves the accuracy of the modeling results. Comparing the modeling results with the I–V curves in the datasheet, the accuracy of the DC model is verified under different temperatures. In addition, the small signal parameters gm and gd that are not exposed in the training process also fit well with the datasheet, which fully demonstrates the feasibility of this hybrid modeling method.
Highlights
With the rapid development of process technologies of silicon carbide (SiC), commercial SiC devices have been widely used in the design of high-power electronics, especially SiC metal–oxide–semiconductor field effect transistors (MOSFETs)
The artificial neural network (ANN) is considered as a data-oriented modeling method,7 which has become popular in the modeling of semiconductor devices
Combining ANN with improved ABC (IABC), an accurate and valid DC model considering temperature characteristics of SiC MOSFETs is realized in this paper
Summary
With the rapid development of process technologies of silicon carbide (SiC), commercial SiC devices have been widely used in the design of high-power electronics, especially SiC metal–oxide–semiconductor field effect transistors (MOSFETs). As the popularity of SiC MOSFETs is increasing in power electronics circuit designs, an accurate and simple model of SiC MOSFETs is urgently needed. These models cannot adapt very well to the characteristics of SiC MOSFETs due to the differences in the internal physical structure between Si MOSFETs and SiC counterparts.3 Those models that deeply study the physical properties of SiC MOSFETs are generally considered to be more accurate. Based on the obtained device data, an accurate model can be quickly acquired through data-oriented modeling methods without deeply studying the physical characteristics of the devices. The artificial neural network (ANN) is considered as a data-oriented modeling method, which has become popular in the modeling of semiconductor devices.. The artificial neural network (ANN) is considered as a data-oriented modeling method, which has become popular in the modeling of semiconductor devices.8,9 At present, this modeling method is rarely considered in SiC devices, and this paper is based on this idea. Scitation.org/journal/adv comparing the modeling results and datasheet ones under different temperatures
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: 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.