In view of the limitations of existing rotating machine fault diagnosis methods in single-scale signal analysis, a fault diagnosis method based on multi-scale permutation entropy (MPE) and multi-channel fusion convolutional neural networks (MCFCNN) is proposed. First, MPE quantitatively analyzes the vibration signals of rotating machine at different scales, and obtains permutation entropy (PE) to construct feature vector sets. Then, considering the structure and spatial information between different sensor measurement points, MCFCNN constructs multiple channels in the input layer according to the number of sensors, and each channel corresponds to the MPE feature sets of different monitored points. MCFCNN uses convolutional kernels to learn the features of each channel in an unsupervised way, and fuses the features of each channel into a new feature map. At last, multi-layer perceptron is applied to fuse multi-channel features and identify faults. Through the health monitoring experiment of planetary gearbox and rolling bearing, and compared with single channel convolutional neural networks (CNN) and existing CNN based fusion methods, the proposed method based on MPE and MCFCNN model can diagnose faults with high accuracy, stability, and speed.
In the fault diagnosis of gearbox, the extraction of the characteristic currently, usually suppose that vibration signal fault signal is a key problem. The practical testing vibration is acquired on constant duty and unchanged circumstance, and signal of gearbox is no stable or Gauss distributing. In different have the characteristic of stability and Gauss distributing. In fault states, the vibration signal has different Gauss property and fact, in engineering, much mechanical equipment usually runs symmetry property, usually including stronger noise and low '' .SNR. Faint fault information is often totally flooded in the noise, n siftion anar duty. So th practi eca nical, so it is very difficult to extract the signal characteristic. Because viatio sign mostly blns to non-stead si signal's Higher-order cumulant is not sensitive to the adding especially even more like this while breaking down, but just Gauss noise and symmetry non-Gauss noise, if applied in the stability under meeting certain special condition fault diagnosis of the gearbox, it can separate signal and noiseIn the fault diagnosis of gearbox, the extraction of the fault effectively, improve the SNR and intensify fault information.signal is a key problem. The practical testing vibration signal Based on the contrast and analysis of the vibration signal of some of gearbox is no stable or Gauss distributing. In different fault second gearbox under different states, this paper has extracted states, the vibration signal has different Gauss property and the power spectrum and Higher-order cumulant spectrum symmetry property, usually including stronger noise and low (bispectrum) of the gear vibration signals, has set up the SNR. Faint fault information is often totally flooded in the characteristic vector of bispectrum used in fault diagnosis. The noise, so it is very difficult to extract the signal characteristic.analysis result shows that, compared with power spectrum, the Two-order cumulant spectrum (the power spectrum) is the characteristic extracting from the Higher-order Cumulant commonly analysis method of gear fault signal. The frequency spectrum is more sensitive to the fault characteristic, and easy to spectrum difference of vibration signal under the normal and realize the digital characteristic extracting in the intelligent fault state can distinguish the working state of gearbox, thus diagnosis, can identify the fault of gearbox effectively, the fault can be diagnosed. Theoretically, the power spectrum Keywords: gearbox, vibration signal, Higher-order cumulant of the signal is sensitive to the colored noise; it can't offer the spectrum. effective means to separate the primitive signal and noise. Xu Jinwu, etc. take use of the method of matrix fantastic spectrum 1. INTRODUCTION characteristic of reconstruct attractive particle orbit and wavelet transform to reduce the noise, so the fault As a kind of shifting and power transferring common characteristic of vibration signal is intensified [2,3]. While this equipment, because of its compact stru...
Blind source separation (BBS) technology was applied to vibration signal processing of gearbox for separating different fault vibration sources and enhancing fault information. An improved BSS algorithm based on particle swarm optimization (PSO) was proposed. It can change the traditional fault-enhancing thought based on de-noising. And it can also solve the practical difficult problem of fault location and low fault diagnosis rate in early stage. It was applied to the vibration signal of gearbox under three working states. The result proves that the BSS greatly enhances fault information and supplies technological method for diagnosis of weak fault.
Mobile Ad Hoc networks has been widely applied to military field, emergency management, public service and so on. Because it is uncertain on network and communication, a great deal of energy will be consumed with nodes increasing and creating routing each other. The reformative on-demand multicast routing protocol was putted forward by researching the energy consuming of multicast routing protocol in Ad Hoc. It will decrease consumption in a big multicast flooding through studying the relaying group net structure based on map or wormhole. The energy consumption is reduced 30% by creating the two kinds of routing principles: minimization of energy consumption and minimization of maximum nodes energy consumption. The simulation result indicates that the reformative RODMRP is effective to reduce the energy consuming while routing protocol built.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.