Induction Motor Air Gap Analysis in Using Machine Learning
Alt Text: Induction Motor Air Gap Analysis Using Machine Learning
Title: Induction Motor Air Gap Analysis Using Machine Learning: A Spectrum-Based Approach
Caption: Advanced Fault Detection in Induction Motors
Description: Explore how machine learning techniques, such as decision tree algorithms, can effectively analyze and resolve air gap eccentricity faults in induction motors.
Keywords: Induction motor, spectrum analysis, decision tree algorithm, air gap eccentricity, machine learning
International Journal of Engineering and Techniques – Volume 11 Issue 1, Jan – Feb 2025
Mr. Shashikant Shivaji Patil1, Dr. E. Vijay Kumar2
1,2Department of Electrical Engineering, RKDF IST, SRK University, Bhopal
Email: shashi10patil@gmail.com, drvijaykumareda03@gmail.com
Abstract
This paper investigates eccentricity faults in induction motors. By utilizing decision tree and power spectrum analysis methods, the study identifies issues such as speed pulsation, vibration noise, and stator-rotor friction caused by air gap eccentricity. The proposed methodology, tested on real-time data, achieves a 90% true value and provides an economical alternative for small industries by analyzing fault spectrum components without expensive sensors…
Keywords
Induction motor, spectrum analysis, decision tree algorithm, air gap eccentricity, machine learning
How to Cite
Shashikant Shivaji Patil, E. Vijay Kumar, “Induction Motor Air Gap Analysis Using Machine Learning,” International Journal of Engineering and Techniques, Volume 11, Issue 1, Jan-Feb 2025. ISSN 2395-1303
Post Comment