A novel neural learning algorithm for multilayer perceptrons

2003 ◽  
Author(s):  
P.B. Luh ◽  
Li Zhang
Keyword(s):  
Learning Algorithm ◽  
Multilayer Perceptrons ◽  
Neural Learning

Neural learning adaptive system using simplified reactive power reference model based speed estimation in sensorless indirect vector controlled induction motor drives

2013 ◽  
Vol 62 (1) ◽  
pp. 25-41 ◽  
Author(s):  
K. Sedhuraman ◽  
S. Himavathi ◽  
A. Muthuramalingam
Keyword(s):  
Induction Motor ◽  
Reactive Power ◽  
Adaptive System ◽  
Learning Algorithm ◽  
Motor Drives ◽  
Speed Estimation ◽  
Induction Motor Drives ◽  
Model Reference ◽  
Neural Learning ◽  
Speed Estimator

Abstract This paper presents a novel speed estimator using Reactive Power based Model Reference Neural Learning Adaptive System (RP-MRNLAS) for sensorless indirect vector controlled induction motor drives. The Model Reference Adaptive System (MRAS) based speed estimator using simplified reactive power equations is one of the speed estimation method used for sensor-less indirect vector controlled induction motor drives. The conventional MRAS speed estimator uses PI controller for adaptation mechanism. The nonlinear mapping capability of Neural Network (NN) and the powerful learning algorithms have increased the applications of NN in power electronics and drives. This paper proposes the use of neural learning algorithm for adaptation in a reactive power technique based MRAS for speed estimation. The proposed scheme combines the advantages of simplified reactive power technique and the capability of neural learning algorithm to form a scheme named “Reactive Power based Model Reference Neural Learning Adaptive System” (RP-MRNLAS) for speed estimator in Sensorless Indirect Vector Controlled Induction Motor Drives. The proposed RP-MRNLAS is compared in terms of accuracy, integrator drift problems and stator resistance versions with the commonly used Rotor Flux based MRNLAS (RF-MRNLAS) for the same system and validated through Matlab/Simulink. The superiority of the RP-MRNLAS technique is demonstrated.

A FAST AND CONVERGENT STOCHASTIC MLP LEARNING ALGORITHM

2001 ◽  
Vol 11 (06) ◽  
pp. 573-583
Author(s):  
AKITO SAKURAI
Keyword(s):  
Learning Algorithm ◽  
Classification Problem ◽  
Threshold Function ◽  
Medium Size ◽  
Multilayer Perceptrons ◽  
Classification Problems ◽  
Marquardt Algorithm ◽  
Parity Function ◽  
Levenberg Marquardt ◽  
Generalization Accuracy

We propose a stochastic learning algorithm for multilayer perceptrons of linear-threshold function units, which theoretically converges with probability one and experimentally exhibits 100% convergence rate and remarkable speed on parity and classification problems with typical generalization accuracy. For learning the n bit parity function with n hidden units, the algorithm converged on all the trials we tested (n=2 to 12) after 5.8· 4.1n presentations for 0.23· 4.0n-6 seconds on a 533MHz Alpha 21164A chip on average, which is five to ten times faster than Levenberg-Marquardt algorithm with restarts. For a medium size classification problem known as Thyroid in UCI repository, the algorithm is faster in speed and comparative in generalization accuracy than the standard backpropagation and Levenberg-Marquardt algorithms.

A neural learning algorithm for blind separation of sources based on geometric properties

1998 ◽  
Vol 64 (3) ◽  
pp. 315-331 ◽  
Author(s):  
Alberto Prieto ◽  
Carlos G. Puntonet ◽  
Beatriz Prieto
Keyword(s):  
Learning Algorithm ◽  
Blind Separation ◽  
Geometric Properties ◽  
Neural Learning
Sign in / Sign up

Export Citation Format

Share Document