Deep Residual Networks With Adaptively Parametric Rectifier Linear Units for Fault Diagnosis

Zhao, Minghang; Zhong, Shisheng; Fu, Xuyun; Tang, Baoping; Dong, Shaojiang; Pecht, Michael

doi:10.1109/tie.2020.2972458

Cited by 143 publications

(45 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This parameter can be channel-shared or channel-wise. The Adaptively Parametric Rectifier Linear Units (APReLU) [32] integrates a subnetwork to adaptively estimate the parameters of PReLU. The Exponential Linear Unit (ELU) [33] uses an exponential function in the negative part to solve the ReLU's problem.…”

Section: Activation Functionmentioning

confidence: 99%

PSigmoid: Improving squeeze-and-excitation block with parametric sigmoid

et al. 2021

View full text Add to dashboard Cite

Squeeze-and-Excitation (SE) Networks won the last ImageNet Large-Scale Visual Recognition Challenge (ILSVRC) classification competition and is very popular in today's vision community. The SE block is the core of Squeeze-and-Excitation Network (SENet), which adaptively recalibrates channel-wise features and suppresses less useful ones. Since SE blocks can be directly used in existing models and effectively improve performance, SE blocks are widely used in a variety of tasks. In this paper, we propose a novel Parametric Sigmoid (PSigmoid) to enhance the SE block. We named the new module PSigmoid SE (PSE) block. The PSE block can not only suppress features in a channel-wise manner, but also enhance features. We evaluate the performance of our method on four common datasets including CIFAR-10, CIFAR-100, SVHN and Tiny ImageNet. Experimental results show the effectiveness of our method. In addition, we compare the differences between the PSE block and the SE block through a detailed analysis of the configuration. Finally, we use a combination of PSE block and SE block to obtain better performance.

show abstract

Section: Activation Functionmentioning

confidence: 99%

PSigmoid: Improving squeeze-and-excitation block with parametric sigmoid

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The following research proves that the improvement of network structure is conducive to extracting detailed fault features and achieving high diagnostic accuracy. Zhao proved that deep residual network (DRN) can efficiently extract the high-level fault features contained in the wavelet packet coefficients (Zhao et al, 2017;Zhao et al, 2020b). On the basis of DRN, the dynamic weight module was introduced to weight the fault features of different frequency bands in the time-frequency images, which improved the diagnosis accuracy (Zhao et al, 2017).…”

Section: Related Workmentioning

confidence: 99%

Intelligent Fault Diagnosis Method of Wind Turbines Planetary Gearboxes Based on a Multi-Scale Dense Fusion Network

Huang

Chai

2021

Front. Energy Res.

View full text Add to dashboard Cite

Due to the powerful capability of feature extraction, convolutional neural network (CNN) is increasingly applied to the fault diagnosis of key components of rotating machineries. Due to the shortcomings of traditional CNN-based fault diagnosis methods, the continuous convolution and pooling operations result in the constant decrease of feature resolution, which may cause the loss of some subtle fault information in the samples. This paper proposes a CNN-based model with improved structure multi-scale dense fusion network (MSDFN) to realize the fault diagnosis of wind turbines planetary gearboxes under complicated working conditions. First, the continuous wavelet transform is applied to preprocess the vibration signals, and the two-dimensional wavelet time-frequency diagrams are used as the network input. Then, the multi-scale feature fusion (MSFF) module and a feature of maximum (FoM) module are used in the extraction and classification stages of fault features, respectively. Next, the multi-scale features of each network layer are fused to enhance the fault features. Finally, the high fault diagnosis accuracy is achieved by extracting the separable fusion result of fault features. The proposed method achieves more than 99% fault diagnosis average accuracy on a planetary gearbox dataset. The comparative experimental results verify the effectiveness of the proposed method and its superiority to some mainstream approaches. The ablation study further confirms that MSFF module and FoM module play the positive role in fault diagnosis.

show abstract

“…In the process of neural network learning, the activation function is considerably important, and can help neural networks to learn and understand. The activation function often used is the Relu activation function [32], also known as the modified linear unit. The convergence speed of Relu is faster than that of Sigmoid and TANh.…”

Section: Adaptive Parameterized Aprelu Activation Functionmentioning

confidence: 99%

Maize Disease Recognition Based On Image Enhancement And OSCRNet

Zhang

Zhou

Chen

et al. 2021

Preprint

View full text Add to dashboard Cite

Background: Under natural light irradiation, there are significant challenges in the identification of maize leaf diseases because of the difficulties in extracting lesion features from constantly changing environments, uneven illumination reflection of the incident light source and many other factors.Results: In the present paper, a novel maize image recognition method was proposed. Firstly, an image enhancement framework of the maize leaf was designed, and a multi-scale image enhancement algorithm with color restoration was established to enhance the characteristics of the maize leaf in a complex environment and to solve the problems of high noise and blur of maize images. Subsequently, an OSCRNet maize leaf recognition network model based on the traditional ResNet backbone architecture was designed. In the OSCRNet maize leaf recognition network model, an octave convolution with characteristics to accelerate network training was adopted, reducing unnecessary redundant spatial information in the maize leaf images. Additionally, a self-calibrated convolution with multi-scale features was employed to realize the interactions of different feature information in the maize leaf images, enhance feature extraction, and solve the problems of similarity of maize disease features and easy learning disorders. Concurrently, batch normalization was employed to prevent network overfitting and enhance the robustness of the model. The experiment was conducted on the maize leaf image data set. The highest identification accuracy of rust, grey leaf disease, northern fusarium wilt, and healthy maize was 94.67%, 92.34%, 89.31% and 96.63%, respectively. Conclusions: The aforementioned methods were beneficial in solving the problems of slow efficiency, low accuracy and image recognition training, and also outperformed other comparison models. The present method demonstrates strong robustness for maize disease images collected in the natural environment, providing a reference for the intelligent diagnosis of other plant leaf diseases.

show abstract

Deep Residual Networks With Adaptively Parametric Rectifier Linear Units for Fault Diagnosis

Cited by 143 publications

References 45 publications

PSigmoid: Improving squeeze-and-excitation block with parametric sigmoid

PSigmoid: Improving squeeze-and-excitation block with parametric sigmoid

Intelligent Fault Diagnosis Method of Wind Turbines Planetary Gearboxes Based on a Multi-Scale Dense Fusion Network

Maize Disease Recognition Based On Image Enhancement And OSCRNet

Contact Info

Product

Resources

About