Paper Title:
Application of Non-Negative Tensor Factorization in Intelligent Fault Diagnosis of Gearboxes
  Abstract

In this paper, a novel approach is proposed to extract features from the bispectra of mechanical fault signals using non-negative tensor factorization (NTF) for the purpose of establishing an intrinsic relationship between mechanical faults and extracted characteristics. First, the bispectra of mechanical signals are obtained and stacked to form a three-dimensional (3D) tensor. Then, an NTF method is applied to extract features, which are represented by a series of “basis images,” from this tensor. Finally, coefficients indicating these basis images’ weights in constituting original bispectral images are calculated for fault classification. Experiments on fault datasets of gearboxes showed that the results of the proposed method not only reveal some nonlinear features of the system, but also have low data dimensions and intuitive meanings with regard to fault characteristic frequencies, which bring great convenience to an explanation of the relationship between mechanical faults and the corresponding bispectra.

  Info
Periodical
Advanced Materials Research (Volumes 201-203)
Edited by
Daoguo Yang, Tianlong Gu, Huaiying Zhou, Jianmin Zeng and Zhengyi Jiang
Pages
2132-2143
DOI
10.4028/www.scientific.net/AMR.201-203.2132
Citation
S. Peng, F. Y. Xu, M. P. Jia, J. Z. Hu, "Application of Non-Negative Tensor Factorization in Intelligent Fault Diagnosis of Gearboxes", Advanced Materials Research, Vols. 201-203, pp. 2132-2143, 2011
Online since
February 2011
Export
Price
$32.00
Share

In order to see related information, you need to Login.

In order to see related information, you need to Login.

Authors: Chang Liu, Kun He, Ji Liu Zhou, Yan Li Zhu
Abstract:Facial Expression recognition based on Non-negative Matrix Factorization (NMF) requires the object images should be vectorized. The...
111
Authors: Yan Ling Hao, Liang Wang
Chapter 22: Computer-Aided Engineering in Manufacturing
Abstract:A compressed sensing (CS) recognition algorithm for sonar image based on non-negative matrix factorization and adjacency spectra (A-NMF)...
5818
Authors: Ning Li, Hai Ting Chen
Chapter 2: Dynamics of Mechanisms and Systems
Abstract:Blind source separation (BSS) has been successfully used to extract undetected fault vibration sources from mixed observation signals by...
760
Authors: Naoki Yamamoto, Jun Murakami, Kei Fujii, Chiharu Okuma, Satoko Saito, Takashi Izumi, Nozomi Hayashida
Chapter 4: Methods, Techniques and Equipments for Measurement, Test, Detection and Monitoring
Abstract:In this paper, we describe about a manner of adapting the nonnegative matrix factorization (NMF) method to the medical data, especially...
630
Authors: Bing Li, Yang Zhen, Lei Zhang, Zhen Hua Fu
Chapter 8: Communication, Signal and Image Processing, Data Acquisition, Identification and Recognation Technologies
Abstract:Assessing the complexity degree of electromagnetic environments (EME) is a typical pattern recognition problem. Feature extraction is the...
2100