| Full text | |
| Author(s): |
Cunha Palacios, Rodrigo Henrique
;
da Silva, Ivan Nunes
;
Goedtel, Alessandro
;
Godoy, Wagner Fontes
;
Lopes, Tiago Drummond
Total Authors: 5
|
| Document type: | Journal article |
| Source: | IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS; v. 13, n. 4, p. 1681-1691, AUG 2017. |
| Web of Science Citations: | 6 |
| Abstract | |
Three-phase induction motors are the primary means of transformation of electrical energy into mechanical energy in industry, since they are robust and present low cost. However, despite being robust, these machines are subject to electrical or mechanical faults. Thus, identifying a defect in a running motor may decrease the risk of possible damage. This paper proposes an alternative approach to identify defects in the stator of these motors, by analyzing current signals in the time domain. In addition, it presents the determination of the consequent fault severity by means of two proposals: 1) a multiagent system with a classifier behavior; and 2) a neural estimator. The faults observed are related to short circuits between turns in the stator coil of 1% to 10%. Experimental results are observed with motors of different powers, under various adverse situations of electrical feed and a wide range of load conditions on the machine shaft. (AU) | |
| FAPESP's process: | 11/17610-0 - Monitoring and control of dynamic systems subject to faults |
| Grantee: | Roberto Kawakami Harrop Galvão |
| Support Opportunities: | Research Projects - Thematic Grants |