Scholarlink

Purpose <p>In vibration-based condition monitoring of rotating machinery, machine learning (ML) models have demonstrated significant diagnostic capabilities; however, their efficacy is fundamentally constrained by the selection and quality of input parameters. Current literature highlights a critical limitation: the absence of a unified parametric framework, with researchers consistently employing different vibration parameters and signal processing techniques for individual machine configurations. This inconsistency creates implementation challenges for industrial applications, where standardised methodologies are essential for reliable diagnostics across diverse mechanical systems.</p> Method <p>This study addresses this fundamental gap by proposing a standardised set of vibration parameters derived from <i>poly</i>-Coherent Composite Spectrum (<i>p</i>CCS) analysis that effectively captures fault signatures across different rotating machine configurations while significantly reducing computational overhead. The methodology integrates carefully selected time-domain parameters with frequency-domain parameters to comprehensively characterise rotor and bearing faults.</p> Result <p>Experimental validation is conducted on two distinctly different test rigs—a multi-rotor system operating across different speed regimes and a bearing configuration operating at three different speeds—representing completely different machine dynamics. Despite these substantial differences in mechanical configuration, the artificial neural network trained on these standardised parameters accurately classified multiple fault conditions (healthy states, misalignment, unbalance, shaft cracks, rotor-stator rub, and bearing faults) with near-perfect accuracy across all tested speeds and configurations.</p> Conclusion <p>The results demonstrate that the proposed and properly selected vibration parameters based on rotordynamic principles can serve as standardised diagnostic features applicable to any rotating machine, offering a significant advancement toward unified condition monitoring frameworks for industrial implementation.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Standardisation of Vibration-based Parameters for Rotor and Bearing for Machine Faults Detection Using Machine Learning Model

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年9月5日

查看全文
  • Khalid Almutairi,
  • Haobin Wen,
  • Jyoti K. Sinha

摘要

Purpose

In vibration-based condition monitoring of rotating machinery, machine learning (ML) models have demonstrated significant diagnostic capabilities; however, their efficacy is fundamentally constrained by the selection and quality of input parameters. Current literature highlights a critical limitation: the absence of a unified parametric framework, with researchers consistently employing different vibration parameters and signal processing techniques for individual machine configurations. This inconsistency creates implementation challenges for industrial applications, where standardised methodologies are essential for reliable diagnostics across diverse mechanical systems.

Method

This study addresses this fundamental gap by proposing a standardised set of vibration parameters derived from poly-Coherent Composite Spectrum (pCCS) analysis that effectively captures fault signatures across different rotating machine configurations while significantly reducing computational overhead. The methodology integrates carefully selected time-domain parameters with frequency-domain parameters to comprehensively characterise rotor and bearing faults.

Result

Experimental validation is conducted on two distinctly different test rigs—a multi-rotor system operating across different speed regimes and a bearing configuration operating at three different speeds—representing completely different machine dynamics. Despite these substantial differences in mechanical configuration, the artificial neural network trained on these standardised parameters accurately classified multiple fault conditions (healthy states, misalignment, unbalance, shaft cracks, rotor-stator rub, and bearing faults) with near-perfect accuracy across all tested speeds and configurations.

Conclusion

The results demonstrate that the proposed and properly selected vibration parameters based on rotordynamic principles can serve as standardised diagnostic features applicable to any rotating machine, offering a significant advancement toward unified condition monitoring frameworks for industrial implementation.