A new approach to health condition identification of rolling bearing using hierarchical dispersion entropy and improved Laplacian score

Abstract

Since bearing fault signal under complex running status is usually manifested as the characteristics of nonlinear and non-stationary, which implies it is difficult to extract accurate affluent features and achieve effective fault identification via conventional signal processing tools. In this article, a hybrid intelligent fault identification scheme, the combination of hierarchical dispersion entropy and improved Laplacian score, is proposed to address this problem, which is mainly composed of three procedures. First, the particle swarm optimization–based optimized hierarchical dispersion entropy is adopted to excavate multilevel fault symptoms from low-frequency and high-frequency components, which can both solve the shortcoming of missing of high-frequency feature information existing in the recently presented multiscale dispersion entropy and artificial parameter selection issue of hierarchical dispersion entropy. Second, an improved feature selection strategy based on improved Laplacian score is proposed to select the sensitive features to establish a low-dimensional feature data set by incorporating the weight coefficient into Laplacian score. Finally, the established low-dimensional feature data set is fed to a Softmax classifier to automatically identify different health conditions of rolling bearing. The efficacy of the proposed method is validated by two experimental cases. Results show that our approach is highly effective in recognizing different fault categories and severities of rolling bearing. Meanwhile, our approach exhibits higher accuracy and better identification performance than some similar entropy-based hybrid approaches and other identification methods reported in this article.

Memory-Event-Triggered $H_{\infty }$ Load Frequency Control of Multi-Area Power Systems With Cyber-Attacks and Communication Delays

“…In addition, it is worthy noting that most of these ETMs use the instantaneous measured output and last triggered data to construct the triggering rules. Practically, the measured output could have stochastic fluctuations incurred by exogenous noises and disturbances [17], [18]. Under such situation, the existing ETMs are sensitive to the fluctuations, which may trigger many unnecessary data to overoccupy limited network bandwidth.…”

Intelligent Fault Diagnosis of Wind Turbine Gearbox based on Refined Generalized Multi-scale State Joint Entropy and RSFS Feature Selection

“…Moreover, FS shows the opposite characteristics. It focuses on the global separation performance of samples, and does not consider the similarity of adjacent samples [31]. Therefore, the features selected by FS and LS cannot effectively represent the separability of multi class samples.…”

Simulation data driven weakly supervised adversarial domain adaptation approach for intelligent cross-machine fault diagnosis

“…Rotating machine is widely used equipment in the industrial field, which usually operates in a harsh environment such as extreme temperature, unsuitable humidity, and poor lubrication. [1][2][3][4][5][6][7][8][9] A component defect of the rotating machine can lead to a complete shutdown of the production process. The implementation of effective condition monitoring and fault diagnosis techniques can prevent the unexpected machine shutdown and ensure a reliable operation of mechanical equipment.…”

“…The implementation of effective condition monitoring and fault diagnosis techniques can prevent the unexpected machine shutdown and ensure a reliable operation of mechanical equipment. 3,4 In the recent years, various intelligent fault diagnosis techniques have been investigated and applied to detect the healthy condition of mechanical equipment. These existing intelligent fault diagnosis techniques can be summarized into two groups, that is, the shallow architecture network-based methods and the deep learningbased methods.…”

“…A hybrid intelligent fault identification scheme by combining hierarchical dispersion entropy and improved Laplacian score is proposed to recognize various fault modes and severities for rolling bearing. 3 Chen et al 4 attempted to estimate the bearing healthy condition using multi-kernel relevance vector machine and multi-domain features. Cerrada et al 5 proposed a statistical feature selection based on genetic algorithm to filter out the useless features among various stages.…”