Classification of motor faults based on transmission coefficient and reflection coefficient of omni-directional antenna using DCNN. (15th July 2022)

• Record Type: Journal Article
• Authors: Dutta, Sagar; Basu, Banani; Talukdar, Fazal Ahmed
• Is Part Of: Expert systems with applications. Volume 198(2022)
• Publication Date: 2022-07-15
• Subjects: Antenna -- Convolutional neural network -- Induction motor -- Classification -- Spectrogram -- Vibration; Expert systems (Computer science) -- Periodicals; Systèmes experts (Informatique) -- Périodiques; Electronic journals; 006.33
• DOI: 10.1016/j.eswa.2022.116832
• Languages: English
• ISSNs: 0957-4174

Abstract

Abstract: The most commonly used electrical rotary machines in the field are induction machines. In this paper, we propose an antenna based approach for the classification of motor faults in induction motors using the reflection coefficient S 11 and the transmission coefficient S 21 of the antenna. The spectrograms of S 11 and S 21 is seen to possess unique signatures for various fault conditions that are used for the classification. To learn the required characteristics and classification boundaries, deep convolution neural network (DCNN) is applied to the spectrogram of the S-parameter. DCNN has been found to reach classification accuracy 93% using S 11, 98.1% using S 21 and 100% using both S 11 and S 21 . The effect of antenna operating frequency, its location and duration of signal on the classification accuracy is also presented and discussed. Highlights: Induction motor fault classification using S-parameter of antenna. Vibration signal pattern recognition using deep convolutional neural network. Non invasive method of monitoring motor fault. Classification accuracy decreases as the antenna moves away from source of vibration.