Compound-Fault Diagnosis of Bearing Based on Order Tracking Wavelet Packet and Rough Sets

Abstract

The diagnosis of compound-fault is always a difficult point, and there is not an effective method in equipment diagnosis field, then a new method of compound-fault diagnosis was presented. The vibration signals at start-up in the gearbox are non-stationary signals, and traditional ways of diagnosis have low precision. Order tracking and wavelet packet and rough sets theory are introduced in the compound-fault diagnosis of bearing. First, the vibration signals at start-up were resampled using computer order tracking arithmetic and equal angle distributed vibration signals were obtained, and wavelet packet has been used for equal angle distributed vibration signals decomposition and reconstruction. Then, energy distribution of every frequency band can be calculated according to normalization process. A new feature vector can be obtained, then clear and concise decision rules can be obtained by rough sets theory. Finally, the result of compound-fault example proves that the proposed method has high validity and more amplitude appliance foreground.

Clustering Application for Condition-Based Maintenance in Time-Varying Processes: A Review Using Latent Dirichlet Allocation

“…Similar analyses, using the same algorithm but with different parameters, specifically the energy ratios of the intrinsic mode functions of the bearings, have also been carried out in other research projects [55]. The same parameter is found, with the same diagnostic objectives, in other contributions to bearing analysis [56]. In the theme of slowly evolving faults, a contribution on temperature controllers shows the application of the AUto-adaptive and Dynamical Clustering technique to estimate the probability of occurrence of a fault.…”

“…The same contributions and [56,59] show a fruitful application of the decomposition of monitored signals into intrinsic mode functions, to use some extracted information as a discriminative feature within the analysis. Another important technique in this topic is the empirical mode decomposition, for the decomposition of monitored signals [54][55][56]59,60]. The temperature theme, highlighted among the keywords, relates to the topic of temperature controller monitoring [51,57].…”

“…The analysis on the techniques highlights the fuzzy c-means technique, mainly applied for the bearings monitoring [54,55], and different contexts [58]. The same contributions and [56,59] show a fruitful application of the decomposition of monitored signals into intrinsic mode functions, to use some extracted information as a discriminative feature within the analysis. Another important technique in this topic is the empirical mode decomposition, for the decomposition of monitored signals [54][55][56]59,60].…”