|
Detection and classification of induction motor faults using feed-forward backpropagation network |
|---|---|
| รหัสดีโอไอ | |
| Creator | Kreangsuk Kraikitrat |
| Title | Detection and classification of induction motor faults using feed-forward backpropagation network |
| Contributor | Sittpong Pengpraderm, and Sompornru Ruangsinchaiwanich |
| Publisher | Nakhon Pathom Rajabhat University |
| Publication Year | 2561 |
| Journal Title | Journal of Thai Interdisciplinary Research |
| Journal Vol. | 13 |
| Journal No. | 4 |
| Page no. | 18 |
| Keyword | fast Fourier transform, artificial neural network, broken rotor bar, induction motor |
| URL Website | http://rdi.npru.ac.th |
| Website title | วารสารวิจัยสหวิทยาการไทย |
| ISSN | 2465-3837 |
| Abstract | For this paper artificial neural networks technique is applied to identify broken rotor bar fault of single phaseinduction motor. Since artificial neural networks can be able to deal with non-linear problem, it is capable for applyto many applications in particular for recognizing patterns positively. Furthermore, fast Fourier transform (FFT) isemployed for converting original stator current waveform, which is time domain, to stator current signal, which isfrequency domain, that is labeled as motor current signature analysis for collecting essential data in order forsending into artificial neural networks later. Although performance of artificial neural network is related as manyfactors, three different multilayer neural network with several training algorithms are researched in this paper. Alsothree training algorithms are focused to study for exempla gradient descent algorithm, Levenberg-Marquardtalgorithm and resilient back propagation algorithm. Consequently, the Levenberg Marquardt algorithm can performvery well for every different multilayer of neural networks in term the network mean squares errors (MSE) whichhaving 5.25E-07 percent that comparing with other results of training algorithms. |
