A Novel Multiscale Lightweight Fault Diagnosis Model Based on the Idea of Adversarial Learning

Zhang, Ping; Wen, Guangrui; Dong, Shuzhi; Lin, Hailong; Huang, Xin; Tian, Xiaojun; Chen, Xuefeng

doi:10.1109/tim.2021.3076841

Cited by 21 publications

(10 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Considering the harsh working environment of a coal mine, the collected idler running signals inevitably interfere with various noises, setting a higher standard for the robustness of the MSCNN-ELM method. Therefore, noise with various signal-to-noise ratios (SNR) ranging from 15 to −2.5 dB with an interval of −2.5 dB were added to the original vibration signal to simulate noise interference in industrial production [33]. The processed signals were converted into datasets and input into the MSCNN-ELM model to test the anti-interference performance of the model.…”

Section: The Effect Of Noise On the Modelmentioning

confidence: 99%

Application of Multi-Scale Convolutional Neural Networks and Extreme Learning Machines in Mechanical Fault Diagnosis

Zhang

Huang

et al. 2023

Machines

View full text Add to dashboard Cite

Extracting fault features in mechanical fault diagnosis is challenging and leads to low diagnosis accuracy. A novel fault diagnosis method using multi-scale convolutional neural networks (MSCNN) and extreme learning machines is presented in this research, which was conducted in three stages: First, the collected vibration signals were transformed into images using the continuous wavelet transform. Subsequently, an MSCNN was designed to extract all detailed features of the original images. The final feature maps were obtained by fusing multiple feature layers. The parameters in the network were randomly generated and remained unchanged, which could effectively accelerate the calculation. Finally, an extreme learning machine was used to classify faults based on the fused feature maps, and the potential relationship between the fault and labels was established. The effectiveness of the proposed method was confirmed. This method performs better in mechanical fault diagnosis and classification than existing methods.

show abstract

Section: The Effect Of Noise On the Modelmentioning

confidence: 99%

Application of Multi-Scale Convolutional Neural Networks and Extreme Learning Machines in Mechanical Fault Diagnosis

Zhang

Huang

et al. 2023

Machines

View full text Add to dashboard Cite

show abstract

“…Hence, the objective of this study is to mitigate the computational complexity of GMA-DRSN through the employment of a lightweight strategy while striving to uphold its superior diagnostic capacity. The currently prevalent lightweight strategies consist primarily of pruning [28,29], knowledge distillation [30,31], and lightweight module design [32,33]. For example, Zhu et al [28] enhanced the training efficiency of their denoising autoencoder network by utilizing a pruning strategy.…”

Section: Introductionmentioning

confidence: 99%

“…Deng et al [30] proposed a lightweight network for imbalance fault diagnosis through a knowledge distillation strategy. Zhang et al [33] implemented a lightweight design of the network by using a depthwise separable convolution module. However, both pruning and knowledge distillation strategies necessitate a large and complex model as the cutting object or teacher, which implies the presence of abundant training data.…”

Section: Introductionmentioning

confidence: 99%

LGMA-DRSN: a lightweight convex global multi-attention deep residual shrinkage network for fault diagnosis

Zhang

Chen

et al. 2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

Recently, the fault diagnosis domain has witnessed a surge in the popularity of the deep residual shrinkage network (DRSN) due to its robust denoising capabilities. In our previous research, an enhanced version of DRSN named global multi-attention DRSN (GMA-DRSN) is introduced to augment the feature extraction proficiency of DRSN specifically for noised vibration signals. However, the utilization of multiple attention structures in GMA-DRSN leads to an escalation in the computational complexity of the network, which may pose practical deployment challenges. To address this limitation, this paper proposes a lightweight variant of GMA-DRSN, referred to as LGMA-DRSN, building upon our prior work. Firstly, the numerical variation regularity of the adaptive inferred slope parameters in the global parametric rectifier linear unit (GPReLU) is analyzed, where we surprisingly find that a convex parameter combination always occurs in pairs. Based on this convex regularity, the sub-network structure of the adaptive inferred slope with attention mechanism is optimized, which greatly reduces the computational complexity compared to our previous work. Finally, the experimental outcomes demonstrate that LGMA-DRSN not only enhances diagnostic efficiency, but also ensures a high level of diagnostic accuracy in the presence of noise interference, when compared with our prior work.

show abstract

“…To address the aforementioned challenges, the adoption of lightweight strategies has emerged as a promising avenue. These strategies encompass techniques such as pruning [35,36], knowledge distillation [37,38], and lightweight design [39,40], which collectively offer effective solutions. For instance, Zhang et al [36] introduced a microscopic neural structure search approach, seamlessly integrated with pruning techniques to efficiently generate sub-networks characterized by reduced complexity and computational demands.…”

Section: Introductionmentioning

confidence: 99%

Deep residual shrinkage networks with adaptively convex global parametric rectifier linear units for fault diagnosis

Zhang,

Zhang

et al. 2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

In response to the challenge posed by traditional deep learning methods, which apply uniform nonlinear transformations to all vibration signals and thus struggle to address fault diagnosis under variable working conditions, a novel activation function called the convex global parametric rectifier linear unit (CGPReLU) is developed based on our prior research. Initially, an analysis of the numerical patterns governing the adaptive derivation process of GPReLU’s two slope parameters revealed the surprising observation that these convex parameter combinations invariably appear in pairs. This discovery serves as the primary motivation for the development of CGPReLU. Leveraging this convex regularity, we subsequently redesigned a lightweight convex sub-network for the adaptive derivation of the CGPReLU’s slope. Simultaneously, a deep residual shrinkage network with CGPReLU is constructed for fault diagnosis. Furthermore, we introduce an innovative evaluation metric designed to measure the collective influence of diagnostic accuracy and computational complexity after the process of model lightweight. Finally, it is experimentally demonstrated that the developed method can maintain a better diagnostic performance while greatly improving the diagnostic efficiency under variable operating conditions compared to our previous work.

show abstract

A Novel Multiscale Lightweight Fault Diagnosis Model Based on the Idea of Adversarial Learning

Cited by 21 publications

References 40 publications

Application of Multi-Scale Convolutional Neural Networks and Extreme Learning Machines in Mechanical Fault Diagnosis

Application of Multi-Scale Convolutional Neural Networks and Extreme Learning Machines in Mechanical Fault Diagnosis

LGMA-DRSN: a lightweight convex global multi-attention deep residual shrinkage network for fault diagnosis

Deep residual shrinkage networks with adaptively convex global parametric rectifier linear units for fault diagnosis

Contact Info

Product

Resources

About