Wavelet Packets Transform processing and Genetic Neuro-Fuzzy classification to detect faulty bearings

Abstract

A great investment is made in maintenance of machinery in any industry. A big percentage of this is spent both in workers and in materials in order to prevent potential issues with said devices. In order to avoid unnecessary expenses, this article presents an intelligent method to detect incipient faults. Particularly, this study focuses on bearings due to the fact that they are the mechanical elements that are most likely to break down. In this article, the proposed method is tested with data collected from a quasi-real industrial machine, which allows for the measurement of the behaviour of faulty bearings with incipient defects. In a second phase, the vibrations obtained from healthy and defective pieces are processed with a multiresolution analysis with the purpose of extracting the most interesting characteristics. Particularly, a Wavelet Packets Transform processing is carried out. Finally, these parameters are used as Genetic Neuro-Fuzzy inputs; this way, once it has been trained, it will indicate whether the analyzed mechanical element is faulty or not.

Data Preprocessing for Vibration Analysis: Application in Indirect Monitoring of ‘Ship Centrifuge Lube Oil Separation Systems’

“…As an example, the increase in relative energy, between the first and the second conditions of the packet corresponding to the motor speed for MOSS 4 on the X axis, was calculated using symlet 9, which was the one selected by applying the methodology, obtaining an energy increase of 225.42% compared with an increase of 216.95% obtained with Daubechies 6, which has been used in many studies based on experience [24,26,32]. As can be seen, using the optimal mother wavelet allows obtainment of the maximum increment in energy in the shortest possible time, which was the objective of the proposed methodology, since in this way, it is easier and more reliable to establish a threshold to determine the operating hours and condition of the machine, which will be analyzed in future work.…”

“…Therefore, currently, methodologies are being proposed for the selection of the optimal mother wavelet for each case and condition [25]. Although the WPT has been used in several studies to detect different defects in different mechanical components and rotating machines [24,26], no study has yet focused on finding the optimal mother wavelet to extract patterns that change according to the number of operating hours in a faster, more reliable, and efficient way, in purifiers of marine lube oils. For this reason, in this work, a methodology to select the best mother wavelet and the patterns to monitor the state of centrifugal oil lubricant separators systems, was carried out.…”

An Analysis of the WPT Function for Pattern Optimization to Detect Defects in Bearings

“…To avoid this, an analysis using the wavelet packet transform (WPT) is proposed in this work to know the energy of a range of frequency that includes the fault frequency. The energy of this packet should increase when a bearing has a defect and has been proved to be a good pattern to detect changes in the dynamical behavior of the system [19][20][21]. To sum up, tools that work in the frequency domain have a great disadvantage compared to other tools that work in the time and frequency domain.…”

“…Many works choose the best mother wavelet based on the experience of achieving good results with it. For example, similar works [19][20][21] used the Daubechies 6 mother wavelet for this reason. Other works focus on comparing several mother wavelets and choosing the one that offers the best results.…”

Application of Axis Orbit Image Optimization in Fault Diagnosis for Rotor System

“…In the field of rotating machinery, its fault identification is usually divided into four steps: signal purification, image processing, feature extraction, and automatic identification. There are several methods for signal purification, among which the more common and representative methods include wavelet transform/wavelet packet transform [2][3][4], harmonic wavelet decomposition, empirical mode decomposition (EMD) [5], and ensemble empirical mode decomposition (EEMD) [6,7]. Wavelet transform will inevitably cause loss of details when processing signals, and it will also cause problems such as frequency aliasing and threshold selection.…”