M phil-computer-science-artifical-neural-networks-projects
0 likes82 views
This document presents a study on using artificial neural networks (ANNs) for speed estimation and control of a separately excited DC motor, incorporating a neural estimator and a neural controller trained via the Levenberg-Marquardt back-propagation algorithm. The neural network design includes a standard three-layer feed-forward structure with specific activation functions. Simulation results indicate the advantages of using ANNs over traditional control methods in managing DC motor systems.
1 of 1
Download to read offline
More Related Content
What's hot (11)
Ad
Viewers also liked (8)
Ad
Similar to M phil-computer-science-artifical-neural-networks-projects (20)
More from Vijay Karan (20)
Recently uploaded (20)
M phil-computer-science-artifical-neural-networks-projects
- 1. M.Phil Computer Science Artifical Neural Networks Projects Web : www.kasanpro.com Email : sales@kasanpro.com List Link : http://kasanpro.com/projects-list/m-phil-computer-science-artifical-neural-networks-projects Title :ANN - Control System DC Motor Language : Matlab Project Link : http://kasanpro.com/p/matlab/ann-control-system-dc-motor Abstract : This paper introduces the new ability of Artificial Neural Networks (ANNs) in estimating speed and controlling the separately excited DC motor. The neural control scheme consists of two parts. One is the neural estimator which is used to estimate the motor speed. The other is the neural controller which is used to generate a control signal for a converter. These two neurals are training by Levenberg-Marquardt back- propagation algorithm. ANNs are the standard three layers feed- forward neural network with sigmoid activation functions in the input and hidden layers and purelin in the output layer. Simulation result are presented to demonstrate the effectiveness of this neural and advantage of the control system DC motor with ANNs in comparison with the conventional scheme without ANNs.