Fusing Spectral Correlation Density Imaging with Deep Learning for Intelligent Fault Diagnosis in Rotating Machinery

• URL: http://arxiv.org/abs/2509.16580v1
• Date: Sat, 20 Sep 2025 08:58:08 GMT
• Title: Fusing Spectral Correlation Density Imaging with Deep Learning for Intelligent Fault Diagnosis in Rotating Machinery
• Authors: Dilshara Herath, Chinthaka Abeyrathne, Chamindu Adithya, Chathura Seneviratne,
• Abstract summary: This study leverages the cyclostationary properties of vibration data through Spectral Correlation Density (SCD) images to enhance fault detection.<n>Three convolutional neural network (CNN) models, Custom CNN, ResNet152V2, and EfficientNetB0, were developed to classify seven bearing conditions.<n>The models' high accuracies across different housings demonstrate a robust solution suitable for cost-effective condition monitoring deployable near sensing platforms.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Bearing fault diagnosis in rotating machinery is critical for ensuring operational reliability, therefore early fault detection is essential to avoid catastrophic failures and expensive emergency repairs. Traditional methods like Fast Fourier Transform (FFT) often fail to capture the complex, non-stationary nature of vibration signals. This study leverages the cyclostationary properties of vibration data through Spectral Correlation Density (SCD) images to enhance fault detection and apply deep learning for classification. Using a publicly available dataset with bearing faults seeded in two distinct housings (A and B) under varying load conditions (0 Nm, 2 Nm, 4 Nm), we processed vibration signals into 2D SCD images to reveal fault-specific periodicities, such as broadband spectra (2000--8000 Hz) for larger faults. Three convolutional neural network (CNN) models, Custom CNN, ResNet152V2, and EfficientNetB0, were developed to classify seven bearing conditions. The custom CNN achieved the highest accuracies of 96.58\% and 94.95\% on Housing A and B, respectively, followed by ResNet152V2 at 96.49\% and 95.35\%, and EfficientNetB0 at 94.16\% and 91.65\%, respectively. The models' high accuracies across different housings demonstrate a robust solution suitable for cost-effective condition monitoring deployable near sensing platforms, contributing to applied machine learning for edge intelligence and showcasing effective signal processing strategies for handling complex, potentially large-scale vibration data.

Related papers

• Multimodal Bearing Fault Classification Under Variable Conditions: A 1D CNN with Transfer Learning [0.46085106405479537]
  Bearing failures constitute up to 90% of mechanical faults.<n>This study proposes a multimodal bearing fault classification approach.<n>It relies on vibration and motor phase current signals within a one-dimensional convolutional neural network (1D CNN) framework.
  arXiv  Detail & Related papers  (2025-02-23T19:11:25Z)
• Advanced technology in railway track monitoring using the GPR Technique: A Review [41.94295877935867]
  Ground Penetrating Radar (GPR) is an electromagnetic survey technique that can be used to monitor railway tracks.<n>It can detect defects such as ballast pockets, fouled ballast, poor drainage, and subgrade settlement.<n>This paper demonstrates the current techniques for using synthetic modeling to calibrate real-world GPR data.<n>Deep learning techniques, particularly Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) are also highlighted for their effectiveness in recognizing patterns associated with defects in GPR images.
  arXiv  Detail & Related papers  (2025-01-19T18:01:39Z)
• A Multimodal Lightweight Approach to Fault Diagnosis of Induction Motors in High-Dimensional Dataset [1.148237645450678]
  An accurate AI-based diagnostic system for induction motors (IMs) holds the potential to enhance proactive maintenance, mitigating unplanned downtime and curbing overall maintenance costs within an industrial environment.<n>Researchers have proposed various fault diagnosis approaches using signal processing (SP), machine learning (ML), deep learning (DL) and hybrid architectures for BRB faults.<n>This paper implements large-scale data of BRB faults by using a transfer-learning-based lightweight DL model named ShuffleNetV2 for diagnosing one, two, three, and four BRB faults using current and vibration signal data.
  arXiv  Detail & Related papers  (2025-01-07T12:40:11Z)
• An Improved Fault Diagnosis Strategy for Induction Motors Using Weighted Probability Ensemble Deep Learning [1.438310481395707]
  Early detection of faults in induction motors is crucial for ensuring uninterrupted operations in industrial settings.<n>WPEDL methodology is tailored for effectively diagnosing induction motor faults using high-dimensional data extracted from vibration and current features.<n>Our proposed model outperforms other models, achieving an accuracy of 98.89%.
  arXiv  Detail & Related papers  (2024-12-24T08:02:44Z)
• Evaluating ML Robustness in GNSS Interference Classification, Characterization & Localization [42.14439854721613]
  Jamming devices disrupt signals from the global navigation satellite system (GNSS)<n>This paper introduces an extensive dataset comprising snapshots obtained from a low-frequency antenna.<n>Our objective is to assess the resilience of machine learning (ML) models against environmental changes.
  arXiv  Detail & Related papers  (2024-09-23T15:20:33Z)
• Wavelet-based Bi-dimensional Aggregation Network for SAR Image Change Detection [53.842568573251214]
  Experimental results on three SAR datasets demonstrate that our WBANet significantly outperforms contemporary state-of-the-art methods. Our WBANet achieves 98.33%, 96.65%, and 96.62% of percentage of correct classification (PCC) on the respective datasets.
  arXiv  Detail & Related papers  (2024-07-18T04:36:10Z)
• TDANet: A Novel Temporal Denoise Convolutional Neural Network With Attention for Fault Diagnosis [0.5277756703318045]
  This paper proposes the Temporal Denoise Convolutional Neural Network With Attention (TDANet) to improve fault diagnosis performance in noise environments. The TDANet model transforms one-dimensional signals into two-dimensional tensors based on their periodic properties, employing multi-scale 2D convolution kernels to extract signal information both within and across periods. Evaluation on two datasets, CWRU (single sensor) and Real aircraft sensor fault (multiple sensors), demonstrates that the TDANet model significantly outperforms existing deep learning approaches in terms of diagnostic accuracy under noisy environments.
  arXiv  Detail & Related papers  (2024-03-29T02:54:41Z)
• Global Context Aggregation Network for Lightweight Saliency Detection of Surface Defects [70.48554424894728]
  We develop a Global Context Aggregation Network (GCANet) for lightweight saliency detection of surface defects on the encoder-decoder structure. First, we introduce a novel transformer encoder on the top layer of the lightweight backbone, which captures global context information through a novel Depth-wise Self-Attention (DSA) module. The experimental results on three public defect datasets demonstrate that the proposed network achieves a better trade-off between accuracy and running efficiency compared with other 17 state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-09-22T06:19:11Z)
• 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)
• Detecting train driveshaft damages using accelerometer signals and Differential Convolutional Neural Networks [67.60224656603823]
  This paper proposes the development of a railway axle condition monitoring system based on advanced 2D-Convolutional Neural Network (CNN) architectures. The resultant system converts the railway axle vibration signals into time-frequency domain representations, i.e., spectrograms, and, thus, trains a two-dimensional CNN to classify them depending on their cracks.
  arXiv  Detail & Related papers  (2022-11-15T15:04:06Z)
• A Vision Transformer-Based Approach to Bearing Fault Classification via Vibration Signals [4.287341231968003]
  This study uses a state-of-the-art Vision Transformer (ViT) to classify bearing defects. The model achieved an overall accuracy of 98.8%.
  arXiv  Detail & Related papers  (2022-08-15T08:37:30Z)

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.