Adaptive Suppression of Mode Mixing in CEEMD Based on Genetic Algorithm for Motor Bearing Fault Diagnosis

Ke, Zhe; Di, Chong; Bao, Xiaohua

doi:10.1109/tmag.2021.3082138

Cited by 20 publications

(11 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Equation (5) shows that updating chameleons' positions during prey tracking involves using their central and current positions and adjusting hunting direction with a rotation matrix. While this offers guidance, it introduces randomness and uncertainty.…”

Section: Bubble-net Hunting Strategymentioning

confidence: 99%

Vibration Signal Noise-Reduction Method of Slewing Bearings Based on the Hybrid Reinforcement Chameleon Swarm Algorithm, Variate Mode Decomposition, and Wavelet Threshold (HRCSA-VMD-WT) Integrated Model

Li,

Yao,

Zhang

et al. 2024

Sensors

View full text Add to dashboard Cite

To enhance fault detection in slewing bearing vibration signals, an advanced noise-reduction model, HRCSA-VMD-WT, is designed for effective signal noise elimination. This model innovates by refining the Chameleon Swarm Algorithm (CSA) into a more potent Hybrid Reinforcement CSA (HRCSA), incorporating strategies from Chaotic Reverse Learning (CRL), the Whale Optimization Algorithm’s (WOA) bubble-net hunting, and the greedy strategy with the Cauchy mutation to diversify the initial population, accelerate convergence, and prevent local optimum entrapment. Furthermore, by optimizing Variate Mode Decomposition (VMD) input parameters with HRCSA, Intrinsic Mode Function (IMF) components are extracted and categorized into noisy and pure signals using cosine similarity. Subsequently, the Wavelet Threshold (WT) denoising targets the noisy IMFs before reconstructing the vibration signal from purified IMFs, achieving significant noise reduction. Comparative experiments demonstrate HRCSA’s superiority over Particle Swarm Optimization (PSO), WOA, and Gray Wolf Optimization (GWO) regarding convergence speed and precision. Notably, HRCSA-VMD-WT increases the Signal-to-Noise Ratio (SNR) by a minimum of 74.9% and reduces the Root Mean Square Error (RMSE) by at least 41.2% when compared to both CSA-VMD-WT and Empirical Mode Decomposition with Wavelet Transform (EMD-WT). This study improves fault detection accuracy and efficiency in vibration signals and offers a dependable and effective diagnostic solution for slewing bearing maintenance.

show abstract

Section: Bubble-net Hunting Strategymentioning

confidence: 99%

Vibration Signal Noise-Reduction Method of Slewing Bearings Based on the Hybrid Reinforcement Chameleon Swarm Algorithm, Variate Mode Decomposition, and Wavelet Threshold (HRCSA-VMD-WT) Integrated Model

Li,

Yao,

Zhang

et al. 2024

Sensors

View full text Add to dashboard Cite

show abstract

“…Information is acquired using a variety of techniques, which can be roughly categorized based on the measurements made: temperature, wear debris analysis, vibration, and acoustic measures [6]. Due to their easy-to-measure signals and convincing analysis, vibration measurements are among those that are frequently utilized in the condition monitoring and diagnosis of rotating machinery [7], [53], [54].…”

Section: B Rotating Machinery Databasesmentioning

confidence: 99%

Prognostics and Health Management of Rotating Machinery via Quantum Machine Learning

et al. 2023

View full text Add to dashboard Cite

Prognostics and Health Management (PHM) concerns predicting machines' behavior to support maintenance decisions through failure modes diagnosis and prognosis. Diagnosis is broadly applied in the context of rotating machines' state classification using several traditional Machine Learning (ML) and Deep Learning (DL) methods. Recently, Quantum Computing (QC), a new and expanding research field, has contributed to different purposes and contexts, such as optimization, artificial intelligence, simulation, cybersecurity, pharmaceutics, and the energy sector. Despite the current limitations in terms of hardware, QC has been studied as an alternative for improving models' speed and computational efficiency. Specifically, this paper proposes a Quantum Machine Learning (QML) approach to diagnose rolling bearings, which are essential components in rotating machinery, based on vibration signals. We apply hybrid models involving the encoding and construction of parameterized quantum circuits (PQC) connected to a classical neural network, the Multi-Layer Perceptron (MLP). We consider combinations of the Variational Quantum Eigensolver (VQE) framework with rotation gates and different entanglement (two-qubits) gates (CNOT, CZ and iSWAP). For each PQC configuration, we assess the impact of the number of layers (1, 5 and 10). We use two databases of different complexity levels not previously explored with QML, namely CWRU and JNU, with 10 and 12 failure modes, respectivel. For CWRU, all QML models presented higher accuracy than the classical MLP. For JNU, all QML models were superior to classical MLP as well. These results suggest that, despite the current limitations of quantum environments, QML models are promising tools to be further investigated in PHM.

show abstract

“…The following steps illustrate how the signal x ( t ) sifting procedure works (Ke et al , 2022): Step 1: Find every maximum and minimum point in f ( t ). The peaks used to generate the top envelope and the minimum used to generate the bottom envelope are interpolated, accordingly. Step 2: Determine the difference between f ( t ) and m 1 to get the component h 1 , and the mean of the upper and lower envelops is m 1 .…”

Section: Theory Of Empirical Mode Decomposition and Intrinsic Mode Fu...mentioning

confidence: 99%

Fault diagnosis of wind turbine power converter using intrinsic mode functions with relative energy entropy

Manikandan

2023

View full text Add to dashboard Cite

Purpose The purpose of this paper is to prevent the destruction of other parts of a wind energy conversion system because of faults, the diagnosis of insulated-gate bipolar transistor (IGBT) faults has become an essential topic of study. Demand for sustainable energy sources has been prompted by rising environmental pollution and energy requirements. Renewable energy has been identified as a viable substitute for conventional fossil fuel energy generation. Because of its rapid installation time and adaptable expenditure for construction scale, wind energy has emerged as a great energy resource. Power converter failure is particularly significant for the reliable operation of wind power conversion systems because it not only has a high yearly fault rate but also a prolonged downtime. The power converters will continue to operate even after the failure, especially the open-circuit fault, endangering their other parts and impairing their functionality. Design/methodology/approach The most widely used signal processing methods for locating open-switch faults in power devices are the short-time Fourier transform and wavelet transform (WT) – based on time–frequency analysis. To increase their effectiveness, these methods necessitate the intensive use of computational resources. This study suggests a fault detection technique using empirical mode decomposition (EMD) that examines the phase currents from a power inverter. Furthermore, the intrinsic mode function’s relative energy entropy (REE) and simple logical operations are used to locate IGBT open switch failures. Findings The presented scheme successfully locates and detects 21 various classes of IGBT faults that could arise in a two-level three-phase voltage source inverter (VSI). To verify the efficacy of the proposed fault diagnosis (FD) scheme, the test is performed under various operating conditions of the power converter and induction motor load. The proposed method outperforms existing FD schemes in the literature in terms of fault coverage and robustness. Originality/value This study introduces an EMD–IMF–REE-based FD method for VSIs in wind turbine systems, which enhances the effectiveness and robustness of the FD method.

show abstract

Adaptive Suppression of Mode Mixing in CEEMD Based on Genetic Algorithm for Motor Bearing Fault Diagnosis

Cited by 20 publications

References 11 publications

Vibration Signal Noise-Reduction Method of Slewing Bearings Based on the Hybrid Reinforcement Chameleon Swarm Algorithm, Variate Mode Decomposition, and Wavelet Threshold (HRCSA-VMD-WT) Integrated Model

Vibration Signal Noise-Reduction Method of Slewing Bearings Based on the Hybrid Reinforcement Chameleon Swarm Algorithm, Variate Mode Decomposition, and Wavelet Threshold (HRCSA-VMD-WT) Integrated Model

Prognostics and Health Management of Rotating Machinery via Quantum Machine Learning

Fault diagnosis of wind turbine power converter using intrinsic mode functions with relative energy entropy

Contact Info

Product

Resources

About