Loading [MathJax]/extensions/MathZoom.js
Local-Dictionary Sparsity Discriminant Preserving Projections for Rotating Machinery Fault Diagnosis Based on Pre-Selected Multi-Domain Features | IEEE Journals & Magazine | IEEE Xplore

Local-Dictionary Sparsity Discriminant Preserving Projections for Rotating Machinery Fault Diagnosis Based on Pre-Selected Multi-Domain Features


Abstract:

In this paper, a novel fault diagnosis framework for rotating machinery is put forward, centering on a firstly proposed dimensionality reduction algorithm named local-dic...Show More

Abstract:

In this paper, a novel fault diagnosis framework for rotating machinery is put forward, centering on a firstly proposed dimensionality reduction algorithm named local-dictionary sparsity discriminant preserving projections (LDSDPP). To involve abundant fault-related information for model construction, multi-domain features are extracted directly from vibration signals as along as their sub-band signals decomposed via time-frequency domain analysis. To reduce computational complexity and improve modelling accuracy, features are pre-processed and those highly related to faults are selected based on filtering models. For feature reduction, sparsity and local structures of data points are introduced in LDSDPP by constructing graphs using sparse representation based on a local dictionary containing only neighbors for each sample. Moreover, the global information of data samples is also integrated into LDSDPP for better discriminant power. Experiments based on two datasets have demonstrated the effectiveness of the proposed framework and the superiority of LDSDPP to other comparable algorithms in classification performance.
Published in: IEEE Sensors Journal ( Volume: 22, Issue: 9, 01 May 2022)
Page(s): 8781 - 8794
Date of Publication: 23 March 2022

ISSN Information:

Funding Agency:


I. Introduction

As a very critical part in modern mechanical and electrical industrial systems, rotating machinery has been widely utilized in different application scenarios [1]. However, failures (e.g. rotor imbalance and misalignment, outer/inner race defects of bearings) inevitably occur especially under harsh operating environments, which are very prone to cause performance degradation, or even worse, economic loss and severe casualty [2], [3]. To prevent these and take measures in the initial phase, it is of great importance to develop effective and efficient methods for early fault diagnosis and build health condition monitoring systems of rotating machinery.

References

References is not available for this document.