| Full text | |
| Author(s): |
Total Authors: 2
|
| Affiliation: | [1] Nove de Julho Univ, Informat & Knowledge Management Grad Program, BR-01504000 Sao Paulo - Brazil
[2] Nove de Julho Univ, Ind Engn Post Graduat Program, BR-01504000 Sao Paulo - Brazil
Total Affiliations: 2
|
| Document type: | Journal article |
| Source: | IEEE SENSORS JOURNAL; v. 18, n. 11, p. 4602-4613, JUN 1 2018. |
| Web of Science Citations: | 6 |
| Abstract | |
This paper proposes the use of a Hall effect sensor installed between two stator slots of a squirrel cage induction motor, spectral analysis of the air gap disturbances and machine learning approaches for diagnosing fully broken rotor bars in motors running at very low slip. This paper overcomes a typical drawback of broken bars diagnosis by using the traditional analysis of the motor current signature, usually when machines operate under low or no-load conditions. A fast Fourier transform has been performed in Hall sensor data to identify some harmonic features, and also, some statistical data have been extracted to get time-domain properties. These values were used as inputs for a multilayer perceptron (MLP) neural network classifier, a k-nearest neighbor classifier, and a support vector machine classification technique. In addition, principal component analysis has been applied to reduce data dimension among some original values, i.e., for both time and frequency features, and contribute to rotor failure detection. A cross-validation method has been used for classifier performance evaluation on each case. The efficiency of this approach was evaluated from a 7.5-kW squirrel cage induction machine running at very low slip conditions, and MLP classifier has achieved better results than the other intelligent methods. (AU) | |
| FAPESP's process: | 16/02525-1 - Diagnosis of broken bars in squirrel cage induction motors using intelligent techniques |
| Grantee: | Cleber Gustavo Dias |
| Support Opportunities: | Regular Research Grants |