Weak Fault Feature Extraction Method Based on Improved Stochastic Resonance
Zhen Yang1, Zhiqian Li2, Fengxing Zhou1
1Engineering Research Center for Metallurgical Automation and Measurement Technology of Ministry of Education, Wuhan University of Science and Technology, Wuhan 430081, China.
Sensors (Basel, Switzerland)
|September 9, 2022
Summary
This study enhances early weak fault detection in rotating machinery using an improved stochastic resonance (SR) method. The technique effectively extracts subtle bearing fault features, improving diagnostic accuracy and machinery health monitoring.
Area of Science:
- Mechanical Engineering
- Signal Processing
- Fault Diagnosis
Background:
- Early detection of weak faults in rotating machinery bearings is crucial for preventing catastrophic failures.
- Traditional methods struggle with extracting subtle fault features from noisy signals.
- Stochastic Resonance (SR) offers potential for enhancing weak signals but requires optimization for complex fault characteristics.
Purpose of the Study:
- To develop an improved stochastic resonance (SR) method for enhanced early weak fault feature extraction in bearings.
- To address the challenge of large parameter signals in actual fault data by converting them into a processable format for SR.
- To optimize the SR system parameters for superior performance in weak fault detection.
Main Methods:
- Introduced amplitude and frequency transform coefficients to convert large parameter fault signals into small parameter signals suitable for SR.
- Developed a Comprehensive Evaluation Index (CEI) using BP neural network, incorporating power spectrum kurtosis, correlation coefficient, structural similarity, RMSE, and approximate entropy.
- Employed adaptive weight particle swarm optimization (PSO) to optimize damping and amplitude transform coefficients using the CEI as a fitness function.
Main Results:
- The improved SR system successfully extracted weak fault features from bearing signals.
- Simulation and experimental results demonstrated the effectiveness of the proposed method.
- The method outperformed traditional second-order general scale transform adaptive SR in weak fault feature extraction.
Conclusions:
- The proposed improved stochastic resonance method, optimized via PSO and CEI, is effective for early weak fault feature extraction in rotating machinery.
- The signal transformation technique successfully adapted complex fault signals for SR processing.
- This approach offers a significant advancement in bearing fault diagnosis and condition monitoring.
Related Concept Videos
01:12Double Resonance Techniques: Overview
274
Double resonance techniques in Nuclear Magnetic Resonance (NMR) spectroscopy involve the simultaneous application of two different frequencies or radiofrequency pulses to manipulate and observe two distinct nuclear spins. One important application of double resonance is spin decoupling, which selectively suppresses coupling with one type of nucleus while observing the NMR signal from another nucleus, simplifying the spectrum and enhancing resolution.
Spin decoupling is usually achieved by...
Spin decoupling is usually achieved by...
274
01:14NMR Spectrometers: Resolution and Error Correction
765
When magnetic nuclei in a sample achieve resonance and undergo relaxation, the signal detected in NMR is an approximately exponential free induction decay. Fourier transform of an exponential decay yields a Lorentzian peak in the frequency domain. Lorentzian peaks in an NMR spectrum are defined by their amplitude, full width at half maximum, and position, where the peak width is governed by the spin-spin relaxation time alone. In real experiments, however, the applied magnetic field is rendered...
765
01:37Super-resolution Fluorescence Microscopy
7.1K
Super-resolution fluorescence microscopy (SRFM) provides a better resolution than conventional fluorescence microscopy by reducing the point spread function (PSF). PSF is the light intensity distribution from a point that causes it to appear blurred. Due to PSF, each fluorescing point appears bigger than its actual size, and it is the PSF interference of nearby fluorophores that causes the blurred image. Various approaches to achieving higher resolution through SRFM have recently been...
7.1K
01:18Fault Types
119
When analyzing a single line-to-ground fault from phase A to ground at a three-phase bus, it is important to consider the fault impedance. This impedance is zero for a bolted fault, equal to the arc impedance for an arcing fault, and represents the total fault impedance for a transmission-line insulator flashover. To derive sequence and phase currents, fault conditions are translated from the phase domain to the sequence domain.
For line-to-line faults occurring between phases B and C, the...
For line-to-line faults occurring between phases B and C, the...
119
01:14Sound Waves: Resonance
2.7K
Resonance is produced depending on the boundary conditions imposed on a wave. Resonance can be produced in a string under tension with symmetrical boundary conditions (i.e., has a node at each end). A node is defined as a fixed point where the string does not move. The symmetrical boundary conditions result in some frequencies resonating and producing standing waves, while other frequencies interfere destructively. Sound waves can resonate in a hollow tube, and the frequencies of the sound...
2.7K