Multi-fault classification of rotor systems based on phase feature of axis trajectory in noisy environments

Hua, Chunrong, Xiong, Libo, Lv, Lumei, Dong, Dawei and Ouyang, Huajiang ORCID: 0000-0003-0312-0326 (2023) Multi-fault classification of rotor systems based on phase feature of axis trajectory in noisy environments. Structural Health Monitoring, 23 (2). pp. 924-944.

PDF Multi-fault classification of rotor systems based on phase feature of axis trajectory in noisy environments(1).pdf - Author Accepted Manuscript Download (3MB) | Preview

Abstract

<jats:p> As it is difficult to distinguish multiple rotor faults with similar dynamic phenomena in noisy environments, a multi-fault classification method is proposed by combining the extracted trajectory phase feature, a parameter-optimized variational mode decomposition (VMD) method and a light gradient boosting machine (LightGBM) model. The trajectory phase feature is extracted from an axis trajectory by fusing the frequency, amplitude, and phase information related to rotor motion and can comprehensively describe the dynamic characteristics induced by different rotor faults. First, the vibration displacement signals in two orthogonal directions are collected to construct the axis trajectories with 12 rotor states including healthy, unbalance, misalignment, single crack, multiple cracks, and a mixture of them. Second, the trajectory phase feature is extracted from the vectorized axis trajectories, and the frequency spectra of trajectory phase angles under different rotor faults are analyzed through Fourier transform. Finally, a parameter-optimized VMD method combined with a LightGBM model is applied to classify multiple faults of rotor systems in different noisy environments based on the extracted trajectory phase feature. The 12 rotor states can be classified into nine categories based on the harmonic information of 1X–7X components (X is the rotating frequency of a rotor system) and other components with smaller amplitudes in the frequency spectra of trajectory phase angles. The average classification accuracy of the 12 rotor states exceeds 93.0%, and the recognition rate for each kind of fault is greater than 77.5% in noisy environments. The simulated and experimental results demonstrate the effectiveness and adaptability of the proposed multi-fault classification method. This work can provide a reference for the condition monitoring and fault diagnosis of rotor systems in engineering. </jats:p>

Item Type:	Article
Divisions:	Faculty of Science and Engineering > School of Engineering
Depositing User:	Symplectic Admin
Date Deposited:	18 Jul 2023 08:49
Last Modified:	27 Feb 2024 16:15
DOI:	10.1177/14759217231178652
Related URLs:	Publisher
URI:	https://livrepository.liverpool.ac.uk/id/eprint/3171707