Title :
Three-phase inverter fault diagnosis based on optimized neural networks
Author :
Bo, Fan ; Ming, Dong ; Jie, Zhao ; Qiang, Zhang
Author_Institution :
Missile Coll., Air Force Eng. Univ., Sanyuan, China
Abstract :
The problem that how to use hierarchical genetic algorithm to determine the structure and parameters of neural networks was studied. Utilized the two grade coding structure of the hierarchical genetic algorithm to solve the ancient problem that when optimize the neural networks´ structure, connection weights, threshold at the same time, the efficiency was low. Furthermore, an improved adaptive hierarchical genetic algorithm was educed, and it improved the shortage of the normal adaptive hierarchical genetic algorithm. At last, the improved adaptive genetic algorithm is used to the fault diagnosis of three-phase inverter, the simulation result shown the method was correct and applied.
Keywords :
electronic engineering computing; fault diagnosis; genetic algorithms; invertors; neural nets; power engineering computing; connection weights; grade coding structure; hierarchical genetic algorithm; neural networks structure; optimized neural networks; three phase inverter fault diagnosis; fault diagnosis; hierarchical genetic algorithm; neural networks; three-phase SPWM inverter;
Conference_Titel :
Computer Application and System Modeling (ICCASM), 2010 International Conference on
Conference_Location :
Taiyuan
Print_ISBN :
978-1-4244-7235-2
Electronic_ISBN :
978-1-4244-7237-6
DOI :
10.1109/ICCASM.2010.5622135
