Loading...
Please wait, while we are loading the content...
Similar Documents
Detection and Diagnosis of Broken Rotor Bars in Induction Motors Using the Fuzzy Min-Max Neural Network
| Content Provider | Semantic Scholar |
|---|---|
| Author | Min-Max |
| Copyright Year | 2019 |
| Abstract | In this paper, a fault detection and diagnosis system for induction motors using motor current signature analysis and the Fuzzy Min-Max (FMM) neural network is described. The finite element method is first employed to generate experimental data for predicting the changes in stator current signatures of an induction motor due to broken rotor bars. Then, a series real laboratory experiments is for broken rotor bars detection and diagnosis. The induction motor with broken rotor bars is operated under different load conditions. In all the experiments, the FMM network is used to learn and distinguish between normal and faulty states of the induction motor based on the input features extracted from the power spectral density. The experimental results positively demonstrate that the FMM network is useful for fault detection and diagnosis of broken rotor bars in induction motors. DOI: 10.4018/jncr.2012010104 International Journal of Natural Computing Research, 3(1), 44-55, January-March 2012 45 Copyright © 2012, IGI Global. Copying or distributing in print or electronic forms without written permission of IGI Global is prohibited. motor failure in the drive system. One way to use MCSA is to sample the harmonics components in the stator-current spectrum using the Fast Fourier Transform (FFT) (Benbouzid & Kliman, 2003). Current monitoring can then be implemented by using current transformers on small to large motors. Indeed, a lot of research work has been conducted to detect machine faults using MCSA (Thomson et al., 1999). Methods for detecting mechanical faults in induction motors using MCSA generally ignore the load effects (Benbouzid et al., 1999; Thomson & Fenger, 2001), or assume that the load is known (Kim et al., 2003). Comparing different types of soft computing techniques, neural networks have been shown to be useful for undertaking fault detection and diagnosis tasks (Ho & Lau, 1995; Tallam et al., 2003). Some of the popular neural network models include the Radial Basis Function (RBF) networks (Ghate & Dudul, 2010a) and the Multi-Layer Perceptron (MLP) networks (Ghate & Dudul, 2010b). One of the main advantages of these networks is the flexibility to learn from data samples, whereby the learning procedure does not require an exact mathematical model of the problem under scrutiny. However, the conventional RBF and MLP networks operate in an offline batch learning mode, and re-training is necessary is more data samples are available after the training phase. As such, in this study, the supervised Fuzzy MinMax (FMM) (Simpson, 1992) neural network is selected mainly because of its capabilities of online, one-pass learning without the need for re-training. In other words, FMM has the capability of learning new data samples and adapting to new classes incrementally while refining the existing classes quickly and autonomously (Simpson, 1992). The organization of this paper is as follows. In Section 2, the theory and related work of fault detection and diagnosis of broken rotor bars are given. The proposed method using the supervised FMM network is detailed in Section 3. This is followed by an experimental study, results, and discussion in Section 4. Finally, concluding remarks are presented in Section 5. 2. BROKEN ROTOR BARS In this section, the theory of broken rotor bars is first given. This is followed by a review of related work pertaining to fault detection and diagnosis of broken rotor bars. |
| File Format | PDF HTM / HTML |
| Alternate Webpage(s) | https://www.igi-global.com/viewtitlesample.aspx?id=72871&ptid=59209&t=detection+and+diagnosis+of+broken+rotor+bars+in+induction+motors+using+the+fuzzy+min-max+neural+network |
| Language | English |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Article |
