Fault diagnosis of rotating machinery based on graph weighted reinforcement networks under small samples and strong noise

Yu, Xiaoxia; Tang, Baoping; Deng, Lei

doi:10.1016/j.ymssp.2022.109848

Cited by 47 publications

(11 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Shan et al [153] combined weighted graph-based label propagation and adversarial training to leverage the unlabeled data in the training process. Yu et al [154] developed a graphweighted reinforcement network, in which the adjacency matrix was determined by measuring the Euclidean distance of time-and frequency-domain features and a graph-weighting enhanced mechanism was used to aggregate the node features in graph.…”

Section: Gnnmentioning

confidence: 99%

A review on deep learning in planetary gearbox health state recognition: methods, applications, and dataset publication

Liu,

Cui,

Cheng

2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

Planetary gearboxes have various merits in mechanical transmission, but their complex structure and intricate operation modes bring large challenges in terms of fault diagnosis. Deep learning has attracted increasing attention in intelligent fault diagnosis and has been successfully adopted for planetary gearbox fault diagnosis, avoiding the difficulty in manually analyzing complex fault features with signal processing methods. This paper presents a comprehensive review of deep learning-based planetary gearbox health state recognition. First, the challenges caused by the complex vibration characteristics of planetary gearboxes in fault diagnosis are analyzed. Second, according to the popularity of deep learning in planetary gearbox fault diagnosis, we briefly introduce six mainstream algorithms, i.e., autoencoder (AE), deep Boltzmann machine (DBM), convolutional neural network (CNN), transformer, generative adversarial network (GAN), and graph neural network (GNN), and some variants of them. Then, the applications of these methods to planetary gearbox fault diagnosis are reviewed. Finally, the research prospects and challenges in this research are discussed. According to the challenges, a dataset is introduced in this paper to facilitate future investigations. We expect that this paper can provide new graduate students, institutions and companies with a preliminary understanding of methods used in this field. The dataset can be downloaded from https://github.com/Liudd-BJUT/WT-planetary-gearbox-dataset.

show abstract

Section: Gnnmentioning

confidence: 99%

A review on deep learning in planetary gearbox health state recognition: methods, applications, and dataset publication

Liu,

Cui,

Cheng

2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…Finally, the weighted features of each subgroup are combined to generate the aggregated output feature 𝑉 𝑘 of a single parent group. Where the aggregated features of the cth channel are calculated by (23):…”

Section: A Resnestmentioning

confidence: 99%

“…2) Due to the complex structure of rotating machinery in the actual engineering environment, the vibration signals collected by the sensors usually contain strong noise when operating in harsh environments, masking the fault information in the signals. Hence, it is difficult for traditional deep-learning models to extract valuable fault features from these signals [22], [23].…”

Section: Introductionmentioning

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

“…In addition, the digital twin technology and transfer learning theory have been applied to fault detection [11,12] and health management [13], to solve the challenges of limited actual fault data and insufficient accuracy of results. It can be seen that these studies mainly focus on mechanical parts with simple structures [14][15][16][17], such as bearings, while there is no relevant research report on complex mechanical equipment. In general, in order to save the costs of collecting fault samples, there are two acceptable approaches: one is the sample generation technique [18][19][20], the other is the transfer learning method [21][22][23].…”

Section: Introductionmentioning

confidence: 99%

A zero-shot fault attribute transfer learning method for compound fault diagnosis of power circuit breakers

Yang,

Lin,

Ruan

2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

Diagnosis of compound mechanical faults for power circuit breakers (CBs) is a challenging task. In traditional fault diagnosis methods, however, all fault types need to be collected in advance for the training of diagnosis model. Such processes have poor generalization capabilities for industrial scenarios with no or few data when faced with new faults. In this study, we propose a novel zero-shot learning method named DSR-AL to address this problem. An unsupervised neural network, namely, depthwise separable residual convolutional neural network (DSRCNN), is designed to directly learn features from 3D time-frequency images of CB vibration signals. Then we build fault attribute learners (ALs), for transferring fault knowledge to the target faults. Finally, the ALs are used to predict the attribute vector of the target faults, thus realizing the recognition of previously unseen faults. The orthogonal experiments are designed and conducted on real industrial switchgear to validate the effectiveness of the proposed diagnosis framework. Results show that it is feasible to diagnose target faults without using their samples for training, which greatly saves the costs of collecting fault samples. This will help to accurately identify the various faults that may occur during CB's life cycle, and facilitate the application of intelligent fault diagnosis system.

show abstract

Fault diagnosis of rotating machinery based on graph weighted reinforcement networks under small samples and strong noise

Cited by 47 publications

References 24 publications

A review on deep learning in planetary gearbox health state recognition: methods, applications, and dataset publication

A review on deep learning in planetary gearbox health state recognition: methods, applications, and dataset publication

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

A zero-shot fault attribute transfer learning method for compound fault diagnosis of power circuit breakers

Contact Info

Product

Resources

About