Asian Science Citation Index is committed to provide an authoritative, trusted and significant information by the coverage of the most important and influential journals to meet the needs of the global scientific community.  
ASCI Database
308-Lasani Town,
Sargodha Road,
Faisalabad, Pakistan
Fax: +92-41-8815544
Contact Via Web
Suggest a Journal
Research Journal of Applied Sciences
Year: 2014  |  Volume: 9  |  Issue: 6  |  Page No.: 369 - 375

Application of Neural Network Trained with Meta-Heuristic Algorithms on Fault Diagnosis of Multi-Level Inverte

M. Sivakumar and R.M.S. Parvathi    

Abstract: Growing industrial need makes the choice of fast response, accurate and efficient systems. The Multilevel inverter based Induction Drives (MLID) are the best solution for the industrial drive needs which reduces the harmonics and increases the efficiency of the system. And also the need for hybrid electric vehicles increases the need of an efficient traction system with the use of multilevel inverters. As multilevel inverter has many semi-conductor switches, it is difficult to identify the fault in it. In this study, a new fault diagnosis method by using the Total Harmonic Distortion (THD) of the voltage waveform and to classify the fault, Neural Network (NN) trained with back propagation, Genetic Algorithm (GA) and also with Particle Swarm Optimization (PSO) is applied and the results are compared. Results shows that NN trained with PSO gives fast response in training algorithm when compared to BP and GA. Here, a cascaded multi-level inverter based three-phase induction motor drive is taken as the test system. MATLAB Software is used to analyse the effectiveness of the test system and results are tabulated.

Fulltext    |   Related Articles   |   Back
   
 
 
 
  Related Articles

 
 
 
 
 
 
 
 
Copyright   |   Desclaimer   |    Privacy Policy   |   Browsers   |   Accessibility