Title :
An object oriented neuro-controller design for motor drive technologies
Author :
Rubaai, Ahmed ; Kankam, M. David ; Noga, Donald F.
Author_Institution :
Dept. of Electr. Eng., Howard Univ., Washington, DC, USA
fDate :
27 Jul-1 Aug 1997
Abstract :
This paper deals with the object-oriented model development of a neuro-controller design for permanent magnet (PM) DC motor drives. The system under study is described as a collection of interacting objects. Each object module describes the object behaviors, called methods. The characteristics of the object are included in its variables. The knowledge of the object exists within its variables, and the performance is determined by its methods. This structure maps well to the real world objects that comprise the system being modeled. A dynamic learning architecture that possesses the capabilities of simultaneous on-line identification and control is incorporated to enforce constraints on connections and control the dynamics of the motor. The control action is implemented “on-line”, in “real time” in such a way that the predicted trajectory follows a specified reference model. A design example of controlling a PM DC motor on-line shows the effectiveness of the design tool. This will therefore be very useful in aerospace applications. It is expected to provide an innovative and novel software model for the rocket engine numerical simulator executive
Keywords :
DC motor drives; feedforward neural nets; learning (artificial intelligence); machine control; multilayer perceptrons; neurocontrollers; object-oriented methods; permanent magnet motors; power engineering computing; 3-layer feedforward neural net; PM DC motor on-line control; dynamic learning architecture; hidden layers; interacting objects; motor drive technologies; motor dynamics control; object oriented neuro-controller design; permanent magnet DC motor drives; predicted trajectory; rocket engine numerical simulator; simultaneous on-line control; simultaneous on-line identification; software model; Aerodynamics; Application software; DC motors; Engines; Motor drives; Numerical simulation; Object oriented modeling; Predictive models; Rockets; Trajectory;
Conference_Titel :
Energy Conversion Engineering Conference, 1997. IECEC-97., Proceedings of the 32nd Intersociety
Conference_Location :
Honolulu, HI
Print_ISBN :
0-7803-4515-0
DOI :
10.1109/IECEC.1997.659200