Application of Feature Fusion Using Coaxial Vibration Signal for Diagnosis of Rolling Element Bearings

Abstract

The research of rolling element bearings (REBs) fault diagnosis based on single sensor vibration signal analysis is very common. However, the information provided by an individual sensor is very limited, and the robustness of the system is poor. In this paper, a novel fault diagnosis method based on coaxial vibration signal feature fusion (CVSFF) is proposed to fully analyze the multisensor information of the system and build a more reliable diagnostic system. An ensemble empirical mode decomposition (EEMD) method is used to decompose the original vibration signal into a number of intrinsic mode functions (IMFs). Then the autocorrelation analysis is introduced to reduce the random noise remaining in IMFs. After that, the Rényi entropy is calculated as the feature of bearings. Finally, the features of coaxial vibration signal are fused by a multiple-kernel learning support vector machine (MKL-SVM) to classify bearing conditions. In order to verify the effectiveness of the CVSFF method in REB diagnosis, eight data sets from the Case Western Reserve University Bearing Data Center are selected. The fault classification results demonstrate that the proposed approach is a valuable tool for bearing faults detection, and the fused feature from coaxial sensors improves fault classification accuracy for REBs.

Fault Diagnosis of Wind Turbine Gearbox Based on Multisensor Data Fusion

“…A variety of rotating machinery states and vibration can be rapidly simulated. Moreover, the health status and failure type of the equipment can be determined by analyzing the collected data signals [22]. In the research, the vibration acceleration signal of the gearbox is collected by the rotating machinery vibration test-bed device and the sampling frequency is set as 5.12 kHz.…”

A Novel Parameter‐Adaptive VMD Method Based on Grey Wolf Optimization with Minimum Average Mutual Information for Incipient Fault Detection

“…, u k and ω k represent each mode component and center frequency, respectively. We introduce Lagrange multiplier λ and balance parameter α to transform equation (1) into an unconstrained one, which is formulated in the following equation:…”

“…Rolling bearings are one of the most crucial parts of them and their unexpected failures usually lead to great production loss and high repair cost. erefore, it is of great significance for fault detection at their incipient faulty stage to ensure the reliable and safely running of the machinery [1][2][3][4]. If a local fault occurs in a rolling bearing, some transient pulses will appear in the vibration signal.…”

A precise bare simulation approach to the minimization of some distances. Foundations

“…Some exemplary (mostly recent) studies and applications appear e.g. in Nath [270] -as well as in Arikan [15], Sundaresan [353], Bunte & Lapidoth [67], Sason & Verdu [321], Kumar et al [205] -for coding and guessing, in Bennett et al [39] in connection with unconditionally secure secret-key agreement protocols and quantum cryptography, in Mayoral [257] for cluster sampling, in Aviyente et al [21] for information extraction in certain neurophysiological signals (so-called event-related potentials), in Tao et al [355] as well as in Jiao et al [171] for early defect/fault detection of rolling element bearings, in Pham et al: [292] for blind source separation, in Liu et al [226] as well as in Rong et al [311] to electron density functional theory (DFT) for quantum chemical reactivity, in Sason [319] for data compression, in Carravilla et al [73] for the recognition of HIV-1 antibodies through STED microscopy and the corresponding design of therapeutic interventions, in Joshi et al [175] for the identification and tracking of relevant T cell receptors for adoptive immunotherapy, in Erguzel et al [121] for the investigation of Electroencephalography (EEG) signals of subjects suffering from some psychiatric disorders, in German-Sallo [133] for fault-characteristics extraction from discrete signals in manufacturing systems, in Schober et al [323] for investigations of some evolutions of the T cell antigen receptor (TCR) repertoire, in Seweryn et al [326] for the assessment of similarity and diversity of expression profiles in single cell systems, in Amezquita-Sanchez [13] for the detection of incipient damage in high-rise buildings subjected to dynamic vibrations, in Barennes et al [32] for comparing the accuracy of current T cell receptor sequencing methods employed for the understanding of adaptive immune responses, in Kumar et al [201] for the segmentation of digital images through multilevel iterative variational mode decomposition (VMD), and in Pandey [280] for the quantification of cosmic homogeneity.…”