A physics-informed deep learning approach for bearing fault detection

Shen, Sheng; Lü, Hao; Sadoughi, Mohammadkazem; Hu, Chao; Nemani, Venkat Pavan; Thelen, Adam; Webster, Keith E.; Darr, Matthew J.; Sidon, Jeff; Kenny, Shawn

doi:10.1016/j.engappai.2021.104295

Cited by 126 publications

(43 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Overall, the model performs very well. To show the efficacy of the classification approach for the model suggested in this research, we evaluated it to classic ML and DL approaches such as Deep Belief Network (DBN) [35], Stacked Denoising Autoencoder (SDA) [36], Convolutional Neural Network [37]. Table I shows without a doubt that the results of this research's suggested method are better than those of the method proposed earlier.…”

Section: A Performance Evaluationmentioning

confidence: 96%

A Vision Transformer-Based Approach to Bearing Fault Classification via Vibration Signals

Zim¹,

Ashraf²,

Iqbal³

et al. 2022

Preprint

View full text Add to dashboard Cite

Rolling bearings are the most crucial components of rotating machinery. Identifying defective bearings in a timely manner may prevent the malfunction of an entire machinery system. The mechanical condition monitoring field has entered the big data phase as a result of the fast advancement of machine parts. When working with large amounts of data, the manual feature extraction approach has the drawback of being inefficient and inaccurate. Data-driven methods like the Deep Learning method have been successfully used in recent years for mechanical intelligent fault detection. Convolutional neural networks (CNNs) were mostly used in earlier research to detect and identify bearing faults. The CNN model, however, suffers from the drawback of having trouble managing fault-time information, which results in a lack of classification results. In this study, bearing defects have been classified using a state-of-the-art Vision Transformer (ViT). Bearing defects were classified using Case Western Reserve University (CWRU) bearing failure laboratory experimental data. The research took into account 13 distinct kinds of defects under 0-load situations in addition to normal bearing conditions. Using the short-time Fourier transform (STFT), the vibration signals were converted into 2D time-frequency images. The 2D time-frequency images are used as input parameters for the ViT. The model achieved an overall accuracy of 98.8%.

show abstract

Section: A Performance Evaluationmentioning

confidence: 96%

A Vision Transformer-Based Approach to Bearing Fault Classification via Vibration Signals

Zim¹,

Ashraf²,

Iqbal³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Others have used transfer learning approaches to learn domain invariant features between measured data, and simulated data, allowing improved remaining useful life prediction and a reduced reliance on real world data. Physics-based knowledge was also included in a CNN (Shen et al, 2021) by adding a penalisation to the network loss if predictions are made that are not compatible with expected bearing fault behaviour.…”

Section: Background On Condition Monitoring Approachesmentioning

confidence: 99%

Domain Knowledge Informed Unsupervised Fault Detection for Rolling Element Bearings

Marx

Gryllias²

2022

PHME_CONF

View full text Add to dashboard Cite

Early and accurate detection of rolling element bearing faults in rotating machinery is important for minimizing production downtime and reducing unnecessary preventative maintenance. Several fault detection methods based on signal processing and machine learning methods have been proposed. Particularly, supervised, data-driven approaches have proved to be very effective for fault detection and diagnostics of rolling element bearings. However, supervised methods rely heavily on the availability of failure data with volume, variety and veracity, which is mostly unavailable in industry. As an alternative data-driven strategy, unsupervised methods are trained on healthy data only and do not require any failure data. In contrast to supervised and un-supervised data-driven models, physics-based and phenomenological models are based on domain knowledge and not on historical data. Although these models are useful for studying the way in which damage is expected to manifest in a measured signal, they are difficult to calibrate and often lack the fidelity required to model reality. In this paper, an unsupervised data-driven anomaly detection method that exploits informative domain knowledge is proposed. Hereby, the versatility of unsupervised data-driven methods are combined with domain knowledge. In this approach, supplementary training data is generated by augmenting healthy data towards its possible future faulty state based on the characteristic bearing fault frequencies. Both healthy and augmented squared envelope spectrum data is used to train an autoencoder model that includes regularisation designed to constrain the latent features at the autoencoder bottleneck. Regularisation in the autoencoder loss enforces that the expected deviation of the healthy latent representation towards the augmented latent representation at dam aged conditions, is constrained to be maximally different for different fault modes. Consequently, the likelihood of a new test sample being healthy can be evaluated based on the projection of the sample onto an expected failure direction in the latent representation. A phenomenological and experimental dataset is used to demonstrate that the addition of augmented training data and a specialized autoencoder loss function can create a separable latent representation that can be used to generate interpretable health indicators.

show abstract

“…Because of the complex and harsh operating environments, it is easy to cause unexpected failures. 1 Therefore, to ensure the safe operation of mechanical equipment, it is of great significance to implement effective state monitoring and fault diagnosis. 2 As an important branch of machine learning methods, deep learning is characterized by adaptive extraction of data features based on deep neural network model for target tasks.…”

Section: Introductionmentioning

confidence: 99%

A wide kernel CNN-LSTM-based transfer learning method with domain adaptability for rolling bearing fault diagnosis with a small dataset

Zhu¹,

chen

Wei

et al. 2022

Advances in Mechanical Engineering

View full text Add to dashboard Cite

It is difficult to obtain sufficient data for some machines, in addition, different working conditions result in different distributions of training data and test data, which lead to the failure of traditional deep learning methods in engineering applications. To solve these problems, we propose a novel deep learning framework called 1D-WCLT for rolling bearing fault diagnosis that combines wide kernel deep convolutional neural network and long short-term memory (WDCNN-LSTM). In this approach, a wide convolution kernel is utilized for local convolution, because the local convolution receptive field is increased, the fault feature contained in the low-middle frequency component is extracted. It is worth mentioning that the network complexity has not increased. Then, the transfer learning is applied to solve related but different domain problems, the useful knowledge learned by WDCNN-LSTM model under sufficient data conditions is transferred to diagnosis tasks with small dataset. After that, some state-of-the-art methods are applied to compare with the proposed method. At the end, experimental results showed that the proposed approach is an excellent algorithm for fault feature extraction of machinery and has much better identification accuracy and applicability than the other existing techniques.

show abstract

A physics-informed deep learning approach for bearing fault detection

Cited by 126 publications

References 55 publications

A Vision Transformer-Based Approach to Bearing Fault Classification via Vibration Signals

A Vision Transformer-Based Approach to Bearing Fault Classification via Vibration Signals

Domain Knowledge Informed Unsupervised Fault Detection for Rolling Element Bearings

A wide kernel CNN-LSTM-based transfer learning method with domain adaptability for rolling bearing fault diagnosis with a small dataset

Contact Info

Product

Resources

About