Quadratic Time-Frequency Analysis of Vibration Signals for Diagnosing Bearing Faults

• URL: http://arxiv.org/abs/2401.01172v2
• Date: Thu, 8 Feb 2024 17:14:54 GMT
• Title: Quadratic Time-Frequency Analysis of Vibration Signals for Diagnosing Bearing Faults
• Authors: Mohammad Al-Sa'd, Tuomas Jalonen, Serkan Kiranyaz, and Moncef Gabbouj
• Abstract summary: This paper presents a fusion of time-frequency analysis and deep learning techniques to diagnose bearing faults under varying noise levels. We design a time-frequency convolutional neural network (TF-CNN) to diagnose various faults in rolling-element bearings.
• Score: 15.613528945524791
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Diagnosis of bearing faults is paramount to reducing maintenance costs and operational breakdowns. Bearing faults are primary contributors to machine vibrations, and analyzing their signal morphology offers insights into their health status. Unfortunately, existing approaches are optimized for controlled environments, neglecting realistic conditions such as time-varying rotational speeds and the vibration's non-stationary nature. This paper presents a fusion of time-frequency analysis and deep learning techniques to diagnose bearing faults under time-varying speeds and varying noise levels. First, we formulate the bearing fault-induced vibrations and discuss the link between their non-stationarity and the bearing's inherent and operational parameters. We also elucidate quadratic time-frequency distributions and validate their effectiveness in resolving distinctive dynamic patterns associated with different bearing faults. Based on this, we design a time-frequency convolutional neural network (TF-CNN) to diagnose various faults in rolling-element bearings. Our experimental findings undeniably demonstrate the superior performance of TF-CNN in comparison to recently developed techniques. They also assert its versatility in capturing fault-relevant non-stationary features that couple with speed changes and show its exceptional resilience to noise, consistently surpassing competing methods across various signal-to-noise ratios and performance metrics. Altogether, the TF-CNN achieves substantial accuracy improvements up to 15%, in severe noise conditions.

Related papers

• Real-Time Vibration-Based Bearing Fault Diagnosis Under Time-Varying Speed Conditions [15.613528945524791]
  This paper presents an efficient real-time convolutional neural network (CNN) for diagnosing multiple bearing faults. We conducted experiments on both healthy bearings and bearings afflicted with inner race, outer race, and roller ball faults.
  arXiv  Detail & Related papers  (2023-11-30T13:30:00Z)
• A Closer Look at Bearing Fault Classification Approaches [1.9531938396288886]
  Rolling bearing fault diagnosis has garnered increased attention in recent years. Recent technological advances have enabled monitoring the health of these assets at scale. Rolling bearing fault diagnosis has garnered increased attention in recent years.
  arXiv  Detail & Related papers  (2023-09-29T06:11:11Z)
• Causal Disentanglement Hidden Markov Model for Fault Diagnosis [55.90917958154425]
  We propose a Causal Disentanglement Hidden Markov model (CDHM) to learn the causality in the bearing fault mechanism. Specifically, we make full use of the time-series data and progressively disentangle the vibration signal into fault-relevant and fault-irrelevant factors. To expand the scope of the application, we adopt unsupervised domain adaptation to transfer the learned disentangled representations to other working environments.
  arXiv  Detail & Related papers  (2023-08-06T05:58:45Z)
• Modelling non-Markovian noise in driven superconducting qubits [2.7648976108201815]
  Non-Markovian noise can be a significant source of errors in superconducting qubits. We develop gate sequences that allow us to characterise and model the effects of non-Markovian noise on both idle and driven qubits.
  arXiv  Detail & Related papers  (2023-06-22T16:30:29Z)
• Novel features for the detection of bearing faults in railway vehicles [88.89591720652352]
  We introduce Mel-Frequency Cepstral Coefficients (MFCCs) and features extracted from the Amplitude Modulation Spectrogram (AMS) as features for the detection of bearing faults.
  arXiv  Detail & Related papers  (2023-04-14T10:09:50Z)
• Improve Noise Tolerance of Robust Loss via Noise-Awareness [60.34670515595074]
  We propose a meta-learning method which is capable of adaptively learning a hyper parameter prediction function, called Noise-Aware-Robust-Loss-Adjuster (NARL-Adjuster for brevity) Four SOTA robust loss functions are attempted to be integrated with our algorithm, and comprehensive experiments substantiate the general availability and effectiveness of the proposed method in both its noise tolerance and performance.
  arXiv  Detail & Related papers  (2023-01-18T04:54:58Z)
• Stabilizing and improving qubit coherence by engineering noise spectrum of two-level systems [52.77024349608834]
  Superconducting circuits are a leading platform for quantum computing. Charge fluctuators inside amorphous oxide layers contribute to both low-frequency $1/f$ charge noise and high-frequency dielectric loss. We propose to mitigate those harmful effects by engineering the relevant TLS noise spectral densities.
  arXiv  Detail & Related papers  (2022-06-21T18:37:38Z)
• A Multi-size Kernel based Adaptive Convolutional Neural Network for Bearing Fault Diagnosis [5.811146610419976]
  We propose a data-driven diagnostic algorithm based on the characteristics of bearing vibrations called multi-size kernel based adaptive convolutional neural network (MSKACNN) MSKACNN provides vibration feature learning and signal classification capabilities to identify and analyze bearing faults.
  arXiv  Detail & Related papers  (2022-03-29T06:43:30Z)
• Frequency fluctuations of ferromagnetic resonances at milliKelvin temperatures [50.591267188664666]
  Noise is detrimental to device performance, especially for quantum coherent circuits. Recent efforts have demonstrated routes to utilizing magnon systems for quantum technologies, which are based on single magnons to superconducting qubits. Researching the temporal behavior can help to identify the underlying noise sources.
  arXiv  Detail & Related papers  (2021-07-14T08:00:37Z)
• Stabilization of Qubit Relaxation Rates by Frequency Modulation [68.8204255655161]
  Temporal, spectral, and sample-to-sample fluctuations in coherence properties of qubits form an outstanding challenge for the development of upscaled fault-tolerant quantum computers. A ubiquitous source for these fluctuations in superconducting qubits is a set of atomic-scale defects with a two-level structure. We show that frequency modulation of a qubit or, alternatively, of the two-level defects, leads to averaging of the qubit relaxation rate over a wide interval of frequencies.
  arXiv  Detail & Related papers  (2021-04-08T11:32:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.