Rolling Element Bearing Fault Recognition Approach Based on Fuzzy Clustering Bispectrum Estimation

Abstract

Abstract. A rolling element bearing fault recognition approach is proposed in this paper. This method combines the basic Higherorder spectrum (HOS) theory and fuzzy clustering method in data mining area. In the first step, all the bispectrum estimation results of the training samples and test samples are turned into binary feature images. Secondly, the binary feature images of the training samples are used to construct object templates including kernel images and domain images. Every fault category has one object templates. At last, by calculating the distances between test samples' binary feature images and the different object templates, the object classification and pattern recognition can be effectively accomplished. Bearing is the most important and much easier to be damaged component in rotating machinery. Furthermore, there exist large amounts of noise jamming and nonlinear coupling components in bearing vibration signals. The Higher Order Cumulants (HOC), which can quantitatively describe the nonlinear characteristic signals with close relationship between the mechanical faults, is introduced in this paper to de-noise the raw bearing vibration signals and obtain the bispectrum estimation pictures. In the experimental part, the rolling bearing fault diagnosis experiment results proved that the classification was completely correct.

Research on SVM-Based Bearing Fault Diagnosis Modeling and Multiple Swarm Genetic Algorithm Parameter Identification Method

“…The method solves the problem that the current fault classification framework generally focuses on the pattern of single-domain feature classifier, which easily leads to insufficient feature extraction and low recognition accuracy. Liu et al [21] introduced the higher-order cumulants (HOC) that can quantitatively describe the nonlinear feature signals with close relationships between mechanical faults, achieve noise reduction of the original bearing vibration signals to obtain a bispectral estimation image, and proposed a rolling bearing fault identification method that combines the basic higher-order spectrum (HOS) theory and the fuzzy clustering method in the field of data mining. Wan et al [22] proposed a method based on group decomposition (SWD), morphological envelope dispersion entropy (MEDE) and random forest (RF) based on the ideas of signal denoising, feature extraction and pattern classification to achieve effective detection and intelligent identification of weak faults in rolling bearings.…”

Observer-biased bearing condition monitoring: From fault detection to multi-fault classification

“…FCM has been extensively studied in bearing fault diagnosis as an exploratory tool (Jia et al, 2005;Guan et al, 2006;Wadhwani et al, 2006;Cui et al, 2008;Sui et al, 2010;Fu et al, 2011;Ye et al, 2011;Zhang et al, 2011;Cao et al, 2012;Liu and Han, 2012;Xu et al, 2012;Xinbin et al, 2012;Wang et al, 2012b,a, Zanoli andAstolfi, 2012;Liu and Han, 2013;Vijay et al, 2013;Ou and Yu, 2014;Wang et al, 2014;Meng et al, 2014;Liu et al, 2014;Zheng et al, 2015).…”

Correlation Coefficient of Simplified Neutrosophic Sets for Bearing Fault Diagnosis

“…The next key issue is to recognize fault types of bearings according to the extracted fault features from vibration signals. To solve this problem, various approaches such as expert systems [9,10], neural networks [3,11,12], and fuzzy approaches [13][14][15] have been developed for fault diagnosis over the past few years. Fuzzy theory has attracted increasing attention in bearing fault diagnosis, and many researches show that fuzzy theory is an effective tool to diagnose bearing faults.…”