A Novel Fault Diagnosis Method of Rolling Bearing Based on Integrated Vision Transformer Model

Fault diagnosis and prognosis (FDP) tries to recognize and locate the faults from the captured sensory data, and also predict their failures in advance, which can greatly help to take appropriate actions for maintenance and avoid serious consequences in industrial systems. In recent years, deep learning methods are being widely introduced into FDP due to the powerful feature representation ability, and its rapid development is bringing new opportunities to the promotion of FDP. In order to facilitate the related research, we give a summary of recent advances in deep learning techniques for industrial FDP in this paper. Related concepts and formulations of FDP are firstly given. Seven commonly used deep learning architectures, especially the emerging generative adversarial network, transformer, and graph neural network, are reviewed. Finally, we give insights into the challenges in current applications of deep learning-based methods from four different aspects of imbalanced data, compound fault types, multimodal data fusion, and edge device implementation, and provide possible solutions, respectively. This paper tries to give a comprehensive guideline for further research into the problem of intelligent industrial FDP for the community.

“…Ref. [ 36 ] use an integrated vision transformer (ViT) based on the soft voting fusion method to diagnose the bearing fault with high accuracy and generalization. For RUL prediction, Ref.…”

Section: Part Ii: Supervised DL Methods For Intelligent Industrial Fdpmentioning

confidence: 99%

Section: Modern Deep Learning Techniques For Intelligent Industrial Fdpmentioning

confidence: 99%

Deep Learning Techniques in Intelligent Fault Diagnosis and Prognosis for Industrial Systems: A Review

Qiu

Cui

Ping

et al. 2023

“…The unique output mechanism of the Transformer model can largely reduce the error accumulation during forecasting. Tang et al [ 32 ] used discrete wavelet transform (DWT) and continuous wavelet transform (CWT) to convert vibration signals into a time-frequency representation (TFR) map and performed preliminary prediction analysis of TFR map by multiple individual ViT models [ 33 ] which had better results compared with integrated CNN and individual ViT. Zhang et al [ 34 ] proposed a self-attention-based perception and prediction framework based on Transformer, called DeepHealth.…”

Section: Introductionmentioning

confidence: 99%

Time Series Forecasting of Motor Bearing Vibration Based on Informer

Yang

Liu

et al. 2022

Electric energy, as an economical and clean energy, plays a significant role in the development of science and technology and the economy. The motor is the core equipment of the power station; therefore, monitoring the motor vibration and predicting time series of the bearing vibration can effectively avoid hazards such as bearing heating and reduce energy consumption. Time series forecasting methods of motor bearing vibration based on sliding window forecasting, such as CNN, LSTM, etc., have the problem of error accumulation, and the longer the time-series forecasting, the larger the error. In order to solve the problem of error accumulation caused by the conventional methods of time series forecasting of motor bearing vibration, this paper innovatively introduces Informer into time series forecasting of motor bearing vibration. Based on Transformer, Informer introduces ProbSparse self-attention and self-attention distilling, and applies random search to optimize the model parameters to reduce the error accumulation in forecasting, achieve the optimization of time and space complexity and improve the model forecasting. Comparing the forecasting results of Informer and those of other forecasting models in three publicly available datasets, it is verified that Informer has excellent performance in time series forecasting of motor bearing vibration and the forecasting results reach 10−2∼10−6.

“…Tang et al propose a multiscale CNN that integrates a vision transformer (ViT) and continuous wavelet transform (CWT). The model integrating CWT and ViT can offer more hidden fault-related information from multi-scale components and achieve higher generalization and anti-noise performance [21]. Qiao et al proposed an adaptive weighted multiscale convolutional neural network (AWMSCNN) to address the domain shift problem that may be caused by fault diagnosis under variable working conditions.…”

Section: Introductionmentioning

confidence: 99%

A Robust Deep Neural Network for Rolling Element Fault Diagnosis under Various Operating and Noisy Conditions

Lee

Zhuo

Le³

2022

This study proposes a new intelligent diagnostic method for bearing faults in rotating machinery. The method uses a combination of nonlinear mode decomposition based on the improved fast kurtogram, gramian angular field, and convolutional neural network to detect the bearing state of rotating machinery. The nonlinear mode decomposition based on the improved fast kurtogram inherits the advantages of the original algorithm while improving the computational efficiency and signal-to-noise ratio. The gramian angular field can construct a two-dimensional image without destroying the time relationship of the signal. Therefore, the proposed method can perform fault diagnosis on rotating machinery under complex operating conditions. The proposed method is verified on the Paderborn dataset under heavy noise and multiple operating conditions to evaluate its effectiveness. Experimental results show that the proposed model outperforms wavelet denoising and the traditional adaptive decomposition method. The proposed model achieves over 99.6% accuracy in all four operating conditions provided by this dataset, and 93.8% accuracy in a strong noise environment with a signal-to-noise ratio of −4 dB.