Deep residual networks-based intelligent fault diagnosis method of planetary gearboxes in cloud environments

Huang, Xinghua; Qi, Guanqiu; Mazur, Neal; Chai, Yi

doi:10.1016/j.simpat.2021.102469

Cited by 21 publications

(6 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, Zhao et al [109] proposed a multiple wavelet regularized deep residual network. The signals were transformed into 2D wavelet coefficient matrices by WPT, and the 2D matrices were divided into a primary group generated by the wavelet basis function and an auxiliary group produced by Jing et al [83] Frequency spectra of vibration signals 6 planet gears Huang et al [84] Multiscale components by WPT 2 shaft, and 1 planet gear Han et al [85] Raw vibration signals 4 sun gears, and 3 planet bearings Wang et al [86] Raw vibration signals 3 sun gears, 3 planet gears, 3 ring gears, and 2 conditions with fault sun gear and ring gear Chang et al [87] Frequency spectra of vibration signals [107] TFRs of vibration signals by WPT 4 sun gears, and 4 planet bearings Zhang et al [108] Raw vibration signals 4 sun gears, and 4 planet gears Zhao et al [109] TFRs of vibration signals by WPT 4 sun gears, and 4 planet bearings Huang et al [110] TFRs of vibration signals by WT 4 gears Zhang et al [111] TFRs of vibration signals by WPT 4 sun gears, and 4 rolling bearings Xie et al [112] RGB images of multisensory data by PCA 4 gears, and 4 rolling bearings the other type of wavelet basis functions. The primary group was adopted to train a deep network, and the other group was used to optimize a deep network that shared the same weights with the former one.…”

Section: Cnnmentioning

confidence: 99%

“…Finally, cross-entropy loss functions were applied to optimize the two deep networks. Huang et al [110] developed a ResNet-based planetary gearbox fault diagnosis method in which the wavelet TFRs were generated as input and a channel attention module was adopted to enhance the important features. It should be noted that different from that in the above publications, this method was implemented in a cloud environment to reduce the computational burden.…”

Section: Cnnmentioning

confidence: 99%

See 1 more Smart Citation

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: Cnnmentioning

confidence: 99%

Section: Cnnmentioning

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

“…Knowledge mapping provides an intelligent approach based on knowledge organization and construction to form a structured semantic knowledge base, which in turn graphically describes any physical concept and its relationships with each other [3]. A knowledge graph is symbolically represented as ( , , )…”

Section: Knowledge Graph-based Construction Of Behavior Mapping Of Su...mentioning

confidence: 99%

Research on Knowledge Graph-based Fault Diagnosis Method for Substation Equipment Operation

Zhang

Huang²,

Li³

et al. 2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

The current image processing-based fault diagnosis method for substation equipment operation realizes fault diagnosis by monitoring the thermal status of the equipment, which leads to low diagnostic accuracy due to the lack of analysis of alarm signals. In this regard, the research of substation equipment operation fault diagnosis method based on knowledge mapping is proposed. A fault diagnosis model is established by building a behavior map of substation accident-like alarm signals, analyzing the alarm behavior as well as the causes of faults, and predicting the posterior probability of faults. In the experiment, the diagnosis accuracy of the proposed method is verified. The analysis of the experimental results shows that the fault diagnosis model constructed by the proposed method has good diagnostic performance and high diagnostic accuracy.

show abstract

“…Looking into some typical deep networks, such as AlexNet [ 20 ], GoogLeNet [ 26 ], and ResNet [ 27 , 28 , 29 ], they are composed of repeating modules and structured by the branching and merging of various layers. Within each module, the pooling layer plays a vital role in achieving image transformation invariance, compact representation, yet effective expression in subsequent layers.…”

Section: Related Workmentioning

confidence: 99%

Discriminative Shape Feature Pooling in Deep Neural Networks

Dixit

2022

J. Imaging

Self Cite

View full text Add to dashboard Cite

Although deep learning approaches are able to generate generic image features from massive labeled data, discriminative handcrafted features still have advantages in providing explicit domain knowledge and reflecting intuitive visual understanding. Much of the existing research focuses on integrating both handcrafted features and deep networks to leverage the benefits. However, the issues of parameter quality have not been effectively solved in existing applications of handcrafted features in deep networks. In this research, we propose a method that enriches deep network features by utilizing the injected discriminative shape features (generic edge tokens and curve partitioning points) to adjust the network’s internal parameter update process. Thus, the modified neural networks are trained under the guidance of specific domain knowledge, and they are able to generate image representations that incorporate the benefits from both handcrafted and deep learned features. The comparative experiments were performed on several benchmark datasets. The experimental results confirmed our method works well on both large and small training datasets. Additionally, compared with existing models using either handcrafted features or deep network representations, our method not only improves the corresponding performance, but also reduces the computational costs.

show abstract

Deep residual networks-based intelligent fault diagnosis method of planetary gearboxes in cloud environments

Cited by 21 publications

References 36 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

Research on Knowledge Graph-based Fault Diagnosis Method for Substation Equipment Operation

Discriminative Shape Feature Pooling in Deep Neural Networks

Contact Info

Product

Resources

About