Identification and control of brushless DC motors using on-line trained artificial neural networks

2003 ◽  
Author(s):  
V. Tipsuwanporn ◽  
W. Piyarat ◽  
C. Tarasantisuk
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Brushless Dc Motors ◽  
Brushless Dc ◽  
Dc Motors ◽  
On Line ◽  
Artificial Neural ◽  
And Control

Adaptive Neurocontrol and Minimization of Energy Consumption of a Heat Exchanger Test Facility

2000 ◽  
Author(s):  
Gerardo Díaz ◽  
Mihir Sen ◽  
Rodney L. McClain
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Energy Consumption ◽  
Heat Exchanger ◽  
Heat Exchangers ◽  
Test Facility ◽  
The Neural Network ◽  
On Line ◽  
Artificial Neural ◽  
And Control

Abstract It has been shown that artificial neural networks (ANNs) can be used to simulate and control thermal systems such as heat exchangers. It is known that the characteristics of thermal components such as heat exchangers vary with respect to time mainly due to fouling effects. There is a need of a model that can adapt to the new characteristics of the thermal system. In this work adaptive artificial neural networks are used to control the outlet air temperature of a heat exchanger test facility. The neurocontrollers are adapted on-line on the basis of different criteria. The parameters of the ANNs are modified considering target error and stability conditions of the closed loop system analyzed as a nonlinear iterative map. We also implement a minimization of a performance index that quantifies the energy consumption. It is shown numerically and experimentally that the neural network is able to control the thermal facility, and is also able to adapt to different disturbances applied to the system, while minimizing the amount of energy used.

The Research on Suppression Strategies for Electromagnetic Torque Ripples of Brushless DC Motors

2014 ◽  
Vol 910 ◽  
pp. 327-331
Author(s):  
Lian Jun Hu ◽  
Xiao Hui Zeng ◽  
Hong Song ◽  
Xiao Long Huang ◽  
Ming Liu
Keyword(s):  
Control Algorithms ◽  
Electromagnetic Torque ◽  
Tracking Errors ◽  
Brushless Dc Motors ◽  
Brushless Dc ◽  
Dc Motors ◽  
On Line ◽  
Suppression Method ◽  
Torque Ripples ◽  
And Control

Despite of its remarkable active performances, brushless DC motors, which are widely used in mechanical engineering, have an obvious disadvantage in its high electromagnetic torque ripples. In the paper, a ripple suppression method based on predictive controls of stator currents is proposed according to analysis of causes electromagnetic torque ripples generate in commutation periods of brushless DC motors. First of all, a relative accurate prediction is acquired through DC motor on-line parameter corrections based on generalized predictive control algorithms. Then rolling optimizations make tracking errors and control qualities optimized for best control effects. And finally, minimum electromagnetic torque ripples are achieved. The simulation results show that torque ripples can be suppressed effectively with improved reliabilities by using the method proposed.

Artificial Neural Networks vs. Fuzzy Logic: Simple Tools to Predict and Control Complex Processes—Application to Plasma Spray Processes

2008 ◽  
Vol 17 (3) ◽  
pp. 365-376 ◽  
Author(s):  
Abdoul-Fatah Kanta ◽  
Ghislain Montavon ◽  
Michel Vardelle ◽  
Marie-Pierre Planche ◽  
Christopher C. Berndt ◽  
...  
Keyword(s):  
Neural Networks ◽  
Fuzzy Logic ◽  
Artificial Neural Networks ◽  
Plasma Spray ◽  
Complex Processes ◽  
Artificial Neural ◽  
And Control ◽  
Control Complex

Einsatz von künstlichen neuronalen Netzwerken an Scannersystemen*/Application of artificial neural networks on scanner systems

2017 ◽  
Vol 107 (07-08) ◽  
pp. 536-540
Author(s):  
S. J. Pieczona ◽  
F. Muratore ◽  
M. F. Prof. Zäh
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Artificial Neural ◽  
And Control ◽  
Dynamic Enhancement

Zur Dynamiksteigerung von Scannersystemen werden verschiedene Arten von Modellierungs- und Regelungsmethoden in der Forschung genutzt. Jedoch sind Nichtlinearitäten, welche das Systemverhalten nachweisbar beeinflussen, in aller Regel nicht Teil der Untersuchung. Mit der Anwendung künstlicher neuronaler Netzwerke (KNN) wird das gesamte dynamische Systemverhalten sowohl für ein geregeltes als auch für ein ungeregeltes Scannersystem abgebildet. So wird geklärt, ob sich diese Art der Modellbildung für eine zukünftige Dynamiksteigerung eignet.   To enhance the dynamics of a scanner system, different methods of modelling and control are utilized. Nonlinearities, which have a certain impact on the system’s behavior, are generally ignored, though. By applying artificial neural networks, the overall dynamics of a controlled and an uncontrolled scanner could be represented. Thus, it will be clarified whether this kind of modelling is appropriate for a future dynamic enhancement.

On-Line Estimation of Transit Time Using Artificial Neural Networks

1998 ◽  
Vol 130 (1) ◽  
pp. 113-127 ◽  
Author(s):  
T. Tambouratzis ◽  
M. Antonopoulos-Domis ◽  
M. Marseguerra ◽  
E. Padovani
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Transit Time ◽  
On Line ◽  
Artificial Neural
Sign in / Sign up

Export Citation Format

Share Document