Title :
Modeling an IGBT-inverter with neural networks in control environment
Author :
Gulez, Kayhan ; Mutoh, Nobuyoshi ; Harashima, Fumio ; Ohnishi, Kouhei
Author_Institution :
Dept. of Electron. Syst. Eng., Tokyo Metropolitan Inst. of Technol., Japan
Abstract :
The IGBT is a very well-known power device used in most AC motor control applications. It is also a new power device according to most of the other power electronic developments in the last 10 years with an insulated gate input like that of the power MOSFET but with the low on-state resistance of a power bipolar transistor. Also, it is known that the IGBT functions as a bipolar transistor that is supplied base current by the drain of a MOSFET where the source of the MOSFET is shorted to the collector of the bipolar transistor. In this paper, the analytical model of the IGBT explained in the literature to match the drive circuit requirements is used with a neural network model of switching conditions of the inverter. Transient operation of the IGBT is considered to model a new type of device to prevent switching harmonics sourced by the inverter from being passed to the motor
Keywords :
AC motors; DC-AC power convertors; bipolar transistor switches; circuit simulation; control system analysis computing; electric machine analysis computing; insulated gate bipolar transistors; machine control; machine theory; neural nets; power bipolar transistors; power semiconductor switches; AC motor control applications; IGBT-inverter modelling; analytical model; control environment; drive circuit requirements; neural networks; on-state resistance; switching conditions; AC motors; Bipolar transistors; Current supplies; Insulated gate bipolar transistors; Insulation; Inverters; MOSFET circuits; Neural networks; Power MOSFET; Power electronics;
Conference_Titel :
Industrial Electronics, 2001. Proceedings. ISIE 2001. IEEE International Symposium on
Conference_Location :
Pusan
Print_ISBN :
0-7803-7090-2
DOI :
10.1109/ISIE.2001.931626
