• Amit. M. Umbrajkaar
• A.Krishnamurthy

In all kind of rotating machinery application misalignment is the major concern with machinery health monitoring. Usually, misalignment effects are seen at coupling, bearing and at support. In major of previous attempt, the misalignment is predicted by analyzing vibration signals in frequency domain using Fast Fourier Transform (FFT). The analysis of signal using FFT is possible up to single level of decomposition as it loses time domain information. Therefore, to analyze vibration signals at different level of decomposition in both time and frequency domain Discrete Wavelet Transform (DWT) is proposed in this paper. Different mother wavelets are available in DWT which shows different result of analysis for same signals. Selection of mother wavelet is based on characteristics like vanishing moments, symmetry etc. But different mother wavelet may have same characteristics. In such case, shape of mother wavelet matching with shape of original signal is selected for analysis. In this work, under healthy and misalignment conditions vibration signals are collected to extract features using suitable mother wavelet. It is observed that selected mother wavelet, level of decomposition and extracted features are most useful for prediction of misalignment.

"Model Based Misalignment Prediction by Wavelet Approach", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 4, page no.763-771, April-2019, Available :http://www.jetir.org/papers/JETIRBB06148.pdf

"Model Based Misalignment Prediction by Wavelet Approach", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 4, page no. pp763-771, April-2019, Available at : http://www.jetir.org/papers/JETIRBB06148.pdf