This research presents a new solution strategy for recognising defects in a multiphase induction motor using the least mean square filter (LMS) and a new hybrid neural network with mind evolution computation algorithm. The use of an artificial neural network (ANN) has shown to be a useful tool for solving difficulties in a variety of fields. Teaching an artificial neural network (ANN) is one of the most complex processes in system learning, and it has lately attracted a huge number of researchers. The proposed hybrid fault diagnostic technique includes an efficient feature extractor based on LMS and a fault classifier based on a hybrid neural network. Testing 600 samples modelled on the failure model determines the performance and efficiency of the offered hybrid neural network classifier. The average correct classification with and without the mind evolution computation technique is roughly 98 percent and 96.17 percent, respectively, for various defect signals. The findings of the simulation research show that the proposed hybrid neural network is effective for fault detection in multiphase induction motors.
A. Balamurugan,
Department of Electrical and Electronics Engineering, Ariyalur Engineering College, Ariyalur, Tamil Nadu, India.
R. Ramya,
Department of Electronics and Communication Engineering, Kings Engineering College, Chennai, Tamil Nadu, India.
S. Saravanan,
Principal, Ranipet Institute of Technology, Walaja, Vellore, Tamil Nadu, India.
Please see the link here: https://stm.bookpi.org/TIER-V3/article/view/7065
No comments:
Post a Comment