Fault Pattern Recognition Method of Rolling Bearing Based on MTF-2DWDCNN

2-D fault feature images have advantages as neural network input for fault pattern recognition, but the most deep image recognition algorithms are non-sensitive to the time-series features of images. This paper proposes a new algorithm named MTF-2DWDCNN based on Markov transfer field(MTF) jointly improved deep convolutional neural networks with wide first-layer Kernel(WDCNN). Firstly, the original 2-D sequence signal is converted into a 2-D time series image by MTF, used as the input of the neural network; secondly, the convolution mode of the original WDCNN is improved to adapt to 2-D time series; finally, the accuracy and error experiments are carried out to verify its effectiveness. Experimental results show that the method proposed in this paper has certain advantages over traditional algorithms regarding recognition accuracy.

• Publication year

  2022

• Venue

  2022 International Conference on Sensing, Measurement & Data Analytics in the era of Artificial Intelligence (ICSMD)

• Publication date

  2022-11-30

• Fields of study

  Not labeled

• Identifiers
  DOI 10.1109/ICSMD57530.2022.10058407
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Incremental Learning for Remaining Useful Life Prediction via Temporal Cascade Broad Learning System With Newly Acquired Data

  2023cited by this paper
• Bearing Fault Reconstruction Diagnosis Method Based on ResNet-152 with Multi-Scale Stacked Receptive Field

  2022cited by this paper
• An artificial neural network methodology for damage detection: Demonstration on an operating wind turbine blade

  2021cited by this paper
• Transfer learning for remaining useful life prediction of multi-conditions bearings based on bidirectional-GRU network

  2021cited by this paper
• Fault Diagnosis of an Autonomous Vehicle With an Improved SVM Algorithm Subject to Unbalanced Datasets

  2021cited by this paper
• A novel temporal convolutional network with residual self-attention mechanism for remaining useful life prediction of rolling bearings

  2021cited by this paper
• Rolling Bearing Fault Diagnosis Method Based on Multilayer Noise Reduction Technology and Improved Convolutional Neural Network

  2021cited by this paper
• A Novel Real-Time Fault Diagnosis Method for Planetary Gearbox Using Transferable Hidden Layer

  2020cited by this paper
• Fault Diagnosis of a Rolling Bearing Using Wavelet Packet Denoising and Random Forests

  2017cited by this paper
• Heterogeneous Feature Models and Feature Selection Applied to Bearing Fault Diagnosis

  2015cited by this paper

• Spatial Domain Image Fusion with Particle Swarm Optimization and Lightweight AlexNet for Robotic Fish Sensor Fault Diagnosis

  2023cites this paper