Synthesis versus analysis priors via generalized minimax-concave penalty for sparsity-assisted machinery fault diagnosis

Shibin Wang, Ivan Selesnick, Gaigai Cai, Baoqing Ding, Xuefeng Chen

Research output: Contribution to journalArticle

Abstract

Sparse priors for signals play a key role in sparse signal modeling, and sparsity-assisted signal processing techniques have been studied widely for machinery fault diagnosis. In this paper, synthesis and analysis priors are introduced for sparse regularization problems via the generalized minimax-concave (GMC) penalty to improve the performance of signal denoising or signal decomposition for the purpose of machinery fault diagnosis. Firstly, the GMC-synthesis and GMC-analysis methods are proposed simultaneously for sparse regularization. Secondly, the gap between GMC-synthesis and GMC-analysis is explored systematically via theoretical and numerical analysis, especially via comparing the performance of GMC-synthesis and GMC-analysis for machinery fault diagnosis, including bearing fault diagnosis and gearbox fault diagnosis. Thirdly, a majorization-minimization-like (MM-like) algorithm is proposed to solve the optimization problem of GMC-synthesis and GMC-analysis. Furthermore, the early stop criterion and the adaptive strategy for regularization parameter selection is also provided in this paper. The results of the numerical simulation, experiment verification, and practical applications show that GMC-synthesis performs better for fault feature extraction than GMC-analysis and the other methods, including ℓ 1 -synthesis, ℓ 1 -analysis, and spectral kurtosis.

Original languageEnglish (US)
Pages (from-to)202-233
Number of pages32
JournalMechanical Systems and Signal Processing
Volume127
DOIs
StatePublished - Jul 15 2019

Fingerprint

Failure analysis
Machinery
Bearings (structural)
Signal denoising
Feature extraction
Numerical analysis
Signal processing
Decomposition
Computer simulation
Experiments

Keywords

  • Convex optimization
  • Generalized minimax-concave penalty
  • Machinery fault diagnosis
  • Nonconvex sparse regularization
  • Sparse representation

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Signal Processing
  • Civil and Structural Engineering
  • Aerospace Engineering
  • Mechanical Engineering
  • Computer Science Applications

Cite this

Synthesis versus analysis priors via generalized minimax-concave penalty for sparsity-assisted machinery fault diagnosis. / Wang, Shibin; Selesnick, Ivan; Cai, Gaigai; Ding, Baoqing; Chen, Xuefeng.

In: Mechanical Systems and Signal Processing, Vol. 127, 15.07.2019, p. 202-233.

Research output: Contribution to journalArticle

@article{583c1a238f474c28bbfb9011f74da85b,
title = "Synthesis versus analysis priors via generalized minimax-concave penalty for sparsity-assisted machinery fault diagnosis",
abstract = "Sparse priors for signals play a key role in sparse signal modeling, and sparsity-assisted signal processing techniques have been studied widely for machinery fault diagnosis. In this paper, synthesis and analysis priors are introduced for sparse regularization problems via the generalized minimax-concave (GMC) penalty to improve the performance of signal denoising or signal decomposition for the purpose of machinery fault diagnosis. Firstly, the GMC-synthesis and GMC-analysis methods are proposed simultaneously for sparse regularization. Secondly, the gap between GMC-synthesis and GMC-analysis is explored systematically via theoretical and numerical analysis, especially via comparing the performance of GMC-synthesis and GMC-analysis for machinery fault diagnosis, including bearing fault diagnosis and gearbox fault diagnosis. Thirdly, a majorization-minimization-like (MM-like) algorithm is proposed to solve the optimization problem of GMC-synthesis and GMC-analysis. Furthermore, the early stop criterion and the adaptive strategy for regularization parameter selection is also provided in this paper. The results of the numerical simulation, experiment verification, and practical applications show that GMC-synthesis performs better for fault feature extraction than GMC-analysis and the other methods, including ℓ 1 -synthesis, ℓ 1 -analysis, and spectral kurtosis.",
keywords = "Convex optimization, Generalized minimax-concave penalty, Machinery fault diagnosis, Nonconvex sparse regularization, Sparse representation",
author = "Shibin Wang and Ivan Selesnick and Gaigai Cai and Baoqing Ding and Xuefeng Chen",
year = "2019",
month = "7",
day = "15",
doi = "10.1016/j.ymssp.2019.02.053",
language = "English (US)",
volume = "127",
pages = "202--233",
journal = "Mechanical Systems and Signal Processing",
issn = "0888-3270",
publisher = "Academic Press Inc.",

}

TY - JOUR

T1 - Synthesis versus analysis priors via generalized minimax-concave penalty for sparsity-assisted machinery fault diagnosis

AU - Wang, Shibin

AU - Selesnick, Ivan

AU - Cai, Gaigai

AU - Ding, Baoqing

AU - Chen, Xuefeng

PY - 2019/7/15

Y1 - 2019/7/15

N2 - Sparse priors for signals play a key role in sparse signal modeling, and sparsity-assisted signal processing techniques have been studied widely for machinery fault diagnosis. In this paper, synthesis and analysis priors are introduced for sparse regularization problems via the generalized minimax-concave (GMC) penalty to improve the performance of signal denoising or signal decomposition for the purpose of machinery fault diagnosis. Firstly, the GMC-synthesis and GMC-analysis methods are proposed simultaneously for sparse regularization. Secondly, the gap between GMC-synthesis and GMC-analysis is explored systematically via theoretical and numerical analysis, especially via comparing the performance of GMC-synthesis and GMC-analysis for machinery fault diagnosis, including bearing fault diagnosis and gearbox fault diagnosis. Thirdly, a majorization-minimization-like (MM-like) algorithm is proposed to solve the optimization problem of GMC-synthesis and GMC-analysis. Furthermore, the early stop criterion and the adaptive strategy for regularization parameter selection is also provided in this paper. The results of the numerical simulation, experiment verification, and practical applications show that GMC-synthesis performs better for fault feature extraction than GMC-analysis and the other methods, including ℓ 1 -synthesis, ℓ 1 -analysis, and spectral kurtosis.

AB - Sparse priors for signals play a key role in sparse signal modeling, and sparsity-assisted signal processing techniques have been studied widely for machinery fault diagnosis. In this paper, synthesis and analysis priors are introduced for sparse regularization problems via the generalized minimax-concave (GMC) penalty to improve the performance of signal denoising or signal decomposition for the purpose of machinery fault diagnosis. Firstly, the GMC-synthesis and GMC-analysis methods are proposed simultaneously for sparse regularization. Secondly, the gap between GMC-synthesis and GMC-analysis is explored systematically via theoretical and numerical analysis, especially via comparing the performance of GMC-synthesis and GMC-analysis for machinery fault diagnosis, including bearing fault diagnosis and gearbox fault diagnosis. Thirdly, a majorization-minimization-like (MM-like) algorithm is proposed to solve the optimization problem of GMC-synthesis and GMC-analysis. Furthermore, the early stop criterion and the adaptive strategy for regularization parameter selection is also provided in this paper. The results of the numerical simulation, experiment verification, and practical applications show that GMC-synthesis performs better for fault feature extraction than GMC-analysis and the other methods, including ℓ 1 -synthesis, ℓ 1 -analysis, and spectral kurtosis.

KW - Convex optimization

KW - Generalized minimax-concave penalty

KW - Machinery fault diagnosis

KW - Nonconvex sparse regularization

KW - Sparse representation

UR - http://www.scopus.com/inward/record.url?scp=85062697274&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85062697274&partnerID=8YFLogxK

U2 - 10.1016/j.ymssp.2019.02.053

DO - 10.1016/j.ymssp.2019.02.053

M3 - Article

AN - SCOPUS:85062697274

VL - 127

SP - 202

EP - 233

JO - Mechanical Systems and Signal Processing

JF - Mechanical Systems and Signal Processing

SN - 0888-3270

ER -