Performance degradation assessment of rolling bearing under vibration signal monitoring based on optimized variational mode decomposition and improved fuzzy support vector data description
Open Access
- 12 June 2024
- journal article
- research article
- Published by AIP Publishing in Journal of Applied Physics
- Vol. 135 (22)
Abstract
Performance degradation assessment methods for rolling bearings under vibration signal monitoring typically involve extracting signal degradation features and inputting them directly into unoptimized assessment models. However, this method often fails to characterize degradation trends and detect early faults in bearings effectively. Moreover, it is susceptible to interference from outliers and false signal fluctuations, posing challenges for accurate performance degradation assessment. To solve the above problems, a novel performance degradation assessment method of rolling bearings based on optimized variational mode decomposition to construct the maximum information degradation feature set and improved hippopotamus optimization algorithm optimized fuzzy support vector data description is proposed. This method effectively suppresses the signal degradation feature pollution caused by the redundancy of irrelevant frequency components, realizes the screening of effective degradation feature sets, and further improves the accuracy of bearing performance degradation assessment. Through experimental verification, this research method uses early healthy rolling bearing samples to establish an assessment model, which can adaptively determine the starting point and degradation trend of bearing degradation. In comparison with other methods for performance degradation assessment under vibration monitoring, it offers distinct advantages.Keywords
Funding Information
- National Science Foundation for Young Scientists of China (No.62001079)
- Liaoning Province Department of Education Science and Technology Innovaion Characterisitic (No.JYTMS20230002)
- Basic Research Project of Liaoning Provincial Department of Education (No. LJKMZ20222192)
This publication has 44 references indexed in Scilit:
- A novel power transformer fault diagnosis method based on data augmentation for KPCA and deep residual networkEnergy Reports, 2023
- Fault diagnosis of high voltage circuit breaker based on multi-sensor information fusion with training weightsMeasurement, 2022
- A transient electromagnetic signal denoising method based on an improved variational mode decomposition algorithmMeasurement, 2021
- A hybrid prognostics approach for estimating remaining useful life of wind turbine bearingsEnergy Reports, 2020
- An optimized VMD method and its applications in bearing fault diagnosisMeasurement, 2020
- A sample entropy inspired affinity propagation method for bearing fault signal classificationDigital Signal Processing, 2020
- Rolling bearing fault diagnosis using generalized refined composite multiscale sample entropy and optimized support vector machineMeasurement, 2020
- Control chart and Six sigma based algorithms for identification of outliers in experimental data, with an application to particulate matter PM 10Atmospheric Pollution Research, 2017
- Support vector machine with genetic algorithm for machinery fault diagnosis of high voltage circuit breakerMeasurement, 2011
- Wavelet filter-based weak signature detection method and its application on rolling element bearing prognosticsJournal of Sound and Vibration, 2006