A Method for the Investigation of Bearing Vibration Based on Spectrogram Image Comparison

International Conference on Recent Advancements and Effectual Researches in Engineering Science and Technology

Arun, P.^1 ; Madhukumar, S.^1 ; Careena, P.^2

Department of Electronics and Communication Engineering, St. Joseph's College of Engineering and Technology, Palai

686 579, India^1

Department of Electronics and Communication Engineering, Amal Jyothi College of Engineering, Kerala

686518, India^2

关键词: Bearing vibrations;    Frequency domains;    Image comparison;    Normal vibrations;    Pattern similarity;    Peak Signal to Noise Ratio (PSNR);    Time frequency domain;    Vibration signal;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/396/1/012044/pdf
DOI  :  10.1088/1757-899X/396/1/012044

来源: IOP

【 摘 要 】

The possibility of analyzing the condition of bearing systems from the vibrations generated during their operation, by means of signal processing methods, has been of extensive research, over last few years. As, vibration signal is highly non-stationary, time as well as frequency domain features cannot designate its behavior well. Though, Spectrogram is a time-frequency domain feature extraction method, its analysis is tedious and maybe, subjective. In the proposed method, the spectrogram images of the normal vibration data is compared with that of the contextual vibration, using Peak Signal-To-Noise Ratio (PSNR). It has postulated that, the pattern similarity between the contextual spectrogram and baseline is little when the bearing is faulty. The PSNR between the spectrogram image of normal bearing vibration data and the baseline is different from those between the baseline and vibration data corresponding to Inner Race Failure (IRF), Roller Element Defect (RED) and Outer Race Failure (ORF).The PSNR analogous to the vibrations picked up from normal and faulty bearings vary with a P value of 4.58445 × 10-20. The method can discriminate faulty bearings with, 96.77% sensitivity and 100% specificity.