Title :
Design and implementation of neural networks for digital current regulation of inverter drives
Author :
Buhl, Michael R. ; Lorenz, Robert D.
Author_Institution :
Dept. of Electr. & Comput. Eng., Wisconsin Univ., Madison, WI, USA
fDate :
Sept. 28 1991-Oct. 4 1991
Abstract :
A discussion is presented of the design of one, two, and three layer neural networks for digital current regulation of the inverter drives. The learning requirements of various designs are evaluated by developing two different learning techniques for such inverter current regulators. The models and learning techniques have been investigated by simulation. These simulation results along with design considerations are used to determine the network best suited for this application. The implementation of neural networks is described, and experimental results are given.<>
Keywords :
control system synthesis; digital control; electric current control; invertors; learning systems; neural nets; control system synthesis; current regulators; design; digital control; electric current control; inverter drives; learning techniques; models; neural networks; Computer networks; Concurrent computing; Current control; Drives; Inverters; Neural networks; Regulators; Switches; Switching frequency; Voltage;
Conference_Titel :
Industry Applications Society Annual Meeting, 1991., Conference Record of the 1991 IEEE
Conference_Location :
Dearborn, MI, USA
Print_ISBN :
0-7803-0453-5
DOI :
10.1109/IAS.1991.178189
