Modeling of switching conditions of a multilevel inverter structure with neural networks in control environment

K. Gulez, N. Mutoh, F. Harashima, K. Ohnishi, H. Pastaci

Research output: Chapter in Book/Report/Conference proceedingConference contribution


In recent years, control systems, especially including IGBT-inverter and motor applications have assumed an increasingly important in the development and advancement of modern civilization and technology. The IGBT is a very well-known power device used in the most AC motor control applications. In this paper, the analytical model of the IGBT explained in the literature to match the drive circuit requirements is used with the neural network model of switching conditions for a multilevel inverter structure mathematical model considered with the passing capacitor ones of the device at the same time. This approximation method as a first step for a multilevel inverter model is a type of consideration to prevent switching harmonics and match EMI emissions, in some extent, of motor control systems. Thus, these kinds of applications supported by artificial neural networks (ANN) enable the development of really effective AC drive control with ever lower power dissipation system or hardware and ever more accurate control structures.

Original languageEnglish
Title of host publicationProceedings of the Power Conversion Conference-Osaka 2002, PCC-Osaka 2002
PublisherInstitute of Electrical and Electronics Engineers Inc.
Number of pages6
ISBN (Print)0780371569, 9780780371569
Publication statusPublished - 2002
EventPower Conversion Conference-Osaka 2002, PCC-Osaka 2002 - Osaka, Japan
Duration: 2002 Apr 22002 Apr 5


OtherPower Conversion Conference-Osaka 2002, PCC-Osaka 2002


  • artificial neural networks
  • motor control systems
  • multilevel inverter
  • passing capacitors
  • power electronic system
  • switching conditions

ASJC Scopus subject areas

  • Energy Engineering and Power Technology
  • Electrical and Electronic Engineering


Dive into the research topics of 'Modeling of switching conditions of a multilevel inverter structure with neural networks in control environment'. Together they form a unique fingerprint.

Cite this