Interpretability of deep convolutional neural networks on rolling bearing fault diagnosis

Yang, Huixin; Li, Xiang; Zhang, Wei

doi:10.1088/1361-6501/ac41a5

Cited by 53 publications

(32 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The recent studies [ 32 – 35 ] show the time-series data can be well processed by the deep neural network model, and higher feature extraction efficiency and better effects can be generally obtained using deep learning [ 36 , 37 ]. Different types of time-series data have been successfully processed using deep learning, including the medical data, financial data, condition monitoring data, and so on.…”

Section: Introductionmentioning

confidence: 99%

Deep Multi-Scale Residual Connected Neural Network Model for Intelligent Athlete Balance Control Ability Evaluation

Wang

et al. 2022

Computational Intelligence and Neuroscience

Self Cite

View full text Add to dashboard Cite

Athlete balance control ability plays an important role in different types of sports. Accurate and efficient evaluations of the balance control abilities can significantly improve the athlete management performance. With the rapid development of the athlete training field, intelligent and automatic evaluations have been highly demanded in the past years. This study proposes a deep learning-based athlete balance control ability evaluation method through processing the time-series movement pressure measurement data. An end-to-end model structure is proposed, which directly analyzes the raw data and provides the evaluation results, which largely facilitates practical utilization. A multi-scale feature extraction scheme is employed, by exploring the learned features in different scales. A residual connected neural network architecture is further proposed. By using the short-cut connection, the deep neural network model can be more efficiently trained. Experiments on the real athlete balance control ability tests are carried out for validations. Through comparisons with different related methods, the results show the proposed deep multi-scale residual connected neural network model is well suited for the athlete balance control ability evaluation problem, and promising for actual applications in the real scenarios.

show abstract

Section: Introductionmentioning

confidence: 99%

Deep Multi-Scale Residual Connected Neural Network Model for Intelligent Athlete Balance Control Ability Evaluation

Wang

et al. 2022

Computational Intelligence and Neuroscience

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, due to the over-parameterized black-box nature of the model, its interpretability in feature extraction still cannot be solved. It is usually difficult to explain the classification results of the model theoretically [53]. Therefore, to verify the effect of SC-ResNeSt on GAPF feature extraction layer by layer, the t-SNE algorithm is used to visualize the features of the output results of the Input Layer, 1-st Residual Block, 3-rd Residual Block and Output Layer of the network.…”

Section: Resultsmentioning

confidence: 99%

Fault Diagnosis Method for Imbalanced Data of Rotating Machinery Based on Time Domain Signal Prediction and SC-ResNeSt

et al. 2023

View full text Add to dashboard Cite

In an actual engineering environment, some rotating machines are usually in normal operation, but their time in a fault state is very short, which leads to a serious imbalance in the fault diagnosis datasets for rotating machinery, and gives the traditional network model the shortcomings of poor stability and low accuracy in practical engineering applications. To solve this problem, we propose a fault diagnosis method based on the combination of a new Dual-stage Attention-based Recurrent Neural Network (DA-RNN) and depth residual dispersion self-calibration convolution network (SC-ResNeSt). Firstly, a novel DA-RNN network with a gated cycle unit (GRU) as a coding-decoding unit was designed, and the network was used to predict and expand the scarce fault signals. Secondly, to make full use of the time domain information of vibration signals, a new image coding method, namely, Gram Angle Product Field (GAPF), was proposed. Then, because the traditional convolution layer lacks a dynamic receptive field to extract more representative features, self-calibrated convolution modules were introduced on the basis of the distraction network (ResNeSt), and a new network model, SC-ResNeSt, was established. Finally, the expanded vibration signal is converted into GAPF, which is used as the input for the SC-ResNeSt network to classify the fault types. To check the performance of the model, the Case Western Reserve University rolling bearing dataset and planetary gearbox dataset were used for testing. Ultimately, good results were obtained in a prediction experiment for bearing fault samples and a subsequent fault diagnosis experiment for bearings and gears, which verified the feasibility and practicability of the model.

show abstract

“…As artificial intelligence develops rapidly, many scholars use intelligent methods for predicting health status and evaluating the performance of rolling bearings [10,11]. Yang et al [12] presented a multisensory fusion technique for collaborative fault diagnosis. Li et al [13] utilized neuronal activation maximization and saliency map methods to enhance the fault diagnosis capabilities of deep convolutional neural networks (CNN).…”

Section: Introductionmentioning

confidence: 99%

Data-augmented patch variational autoencoding generative adversarial networks for rolling bearing fault diagnosis

Wang¹,

Jiang²,

Liu³

et al. 2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

Many recent studies have focused on imbalanced rolling bearing data for fault diagnosis. Complementing the imbalance dataset through data augmentation methods excellently solves this problem superior. In this paper, a patch variational autoencoding generative adversarial network (PVAEGAN) is proposed. Firstly, overlap sampling is designed to preprocess the input samples to alleviate noise interference. Secondly, the PVAEGAN is constructed, and the matrix discriminative output of the model allows it to focus on more features of the data during training. Thirdly, a stability-enhancing structure is designed for PVAEGAN to improve the stability of network parameter variations and inter-network stability for better model results. Furthermore, to verify the use of the multi-class comparison method, experiments are conducted. The results indicate that PVAEGAN can augment imbalanced datasets more effectively and with better robustness than other existing models.

show abstract

Interpretability of deep convolutional neural networks on rolling bearing fault diagnosis

Cited by 53 publications

References 58 publications

Deep Multi-Scale Residual Connected Neural Network Model for Intelligent Athlete Balance Control Ability Evaluation

Deep Multi-Scale Residual Connected Neural Network Model for Intelligent Athlete Balance Control Ability Evaluation

Fault Diagnosis Method for Imbalanced Data of Rotating Machinery Based on Time Domain Signal Prediction and SC-ResNeSt

Data-augmented patch variational autoencoding generative adversarial networks for rolling bearing fault diagnosis

Contact Info

Product

Resources

About