Frequency-Domain Fusing Convolutional Neural Network: A Unified Architecture Improving Effect of Domain Adaptation for Fault Diagnosis

Li, Xudong; Zheng, Jianhua; Li, Mingtao; Ma, Wenzhen; Hu, Yang

doi:10.3390/s21020450

Cited by 21 publications

(5 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Alternatively, the literature also presents related works that employ specific strategies. These include heuristic solutions like the Genetic Algorithm (GA) [ 16 , 17 ], Neural Networks (NN) [ 18 , 19 ] or zero crossing detector algorithms.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

An Edge Computing Application of Fundamental Frequency Extraction for Ocean Currents and Waves

Hernandez-Gonzalez,

Montiel-Caminos,

Sosa

et al. 2024

Sensors

View full text Add to dashboard Cite

This paper describes the design and optimization of a smart algorithm based on artificial intelligence to increase the accuracy of an ocean water current meter. The main purpose of water current meters is to obtain the fundamental frequency of the ocean waves and currents. The limiting factor in those underwater applications is power consumption and that is the reason to use only ultra-low power microcontrollers. On the other hand, nowadays extraction algorithms assume that the processed signal is defined in a fixed bandwidth. In our approach, belonging to the edge computing research area, we use a deep neural network to determine the narrow bandwidth for filtering the fundamental frequency of the ocean waves and currents on board instruments. The proposed solution is implemented on an 8 MHz ARM Cortex-M0+ microcontroller without a floating point unit requiring only 9.54 ms in the worst case based on a deep neural network solution. Compared to a greedy algorithm in terms of computational effort, our worst-case approach is 1.81 times faster than a fast Fourier transform with a length of 32 samples. The proposed solution is 2.33 times better when an artificial neural network approach is adopted.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Although classification is performed using a DNN, this approach focuses on high-level comparison of feature extraction algorithms. In a similar way, the authors of [ 19 ] present a Fault Diagnosis method based on a CNN to detect the variation in the signal features.…”

Section: Related Workmentioning

confidence: 99%

An Edge Computing Application of Fundamental Frequency Extraction for Ocean Currents and Waves

Hernandez-Gonzalez,

Montiel-Caminos,

Sosa

et al. 2024

Sensors

View full text Add to dashboard Cite

show abstract

“…Li et al proposed a frequency-domain fusion CNN. The network can obtain the frequency-domain characteristics of signals in different frequency bands to solve the problem of inconsistent distribution of training data sets and online test data sets [37]. Whether it is to obtain more comprehensive and diversified features from vibration signals or to mine the time-frequency characteristics of fault information, both ideas have achieved effective results in solving the inconsistency of data distribution.…”

Section: Introductionmentioning

confidence: 99%

Bearing fault diagnosis based on inverted Mel-scale frequency cepstral coefficients and deformable convolution networks

Zhao¹,

baofu²,

yuhang³

et al. 2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

In the online test of bearing fault diagnosis algorithm based on data-driven, it is difficult to guarantee that the training and testing data come from the same time series distribution. Inconsistent distribution will lead to a decline in diagnostic performance. In addition, the convolutional neural network is limited by the fixed shape of its convolution kernel, which makes it difficult to fully extract the spatial constraint features between fault data. To solve the above problems, this paper proposes a bearing fault diagnosis method based on inverted Mel-scale frequency cepstrum coefficients and deformable convolution networks. The core of traditional Mel-scale frequency cepstrum coefficients is to construct a non-uniformly distributed frequency domain filter bank. It is characterized by the dense distribution of low-frequency regions and the sparse distribution of high-frequency regions. Considering that the features that can well characterize the fault information are concentrated in the high-frequency part, we reconstruct the traditional Mel-scale frequency cepstrum coefficients filter bank and propose a feature extraction method of inverted Mel-scale frequency cepstrum coefficients. This method can obtain the frequency domain characteristics of bearing vibration signals, highlight the fault information contained in the high-frequency region, and reduce the influence of time series distribution inconsistency between training samples and testing samples on the diagnosis accuracy. In order to further improve the spatial discrimination between different fault categories, the deformable convolution networks model is introduced to extract the spatial distribution information of fault features and improve the accuracy of fault diagnosis. Finally, two public datasets and an experimental platform data verify that the method can achieve high-precision fault diagnosis, and inverted Mel-scale Frequency cepstrum coefficients are effective in solving the problem of inconsistent distribution.

show abstract

“…In detail, a convolutional neural network with automated hyper-parameter tuning based on Bayesian optimization was presented by Kolar in 2021 [32]. Li has suggested a Frequency-Domain Fusing Convolutional Neural Network (FFCNN) as a representation adaptation-based strategy for filtering inputs from various frequency bands and fusing them into new input signals by using a frequencydomain fusing layer [33]. Other issues with radial internal clearance and the meshing force of a gear system have been considered recently.…”

Section: Introductionmentioning

confidence: 99%

Unsupervised Method Based on Adversarial Domain Adaptation for Bearing Fault Diagnosis

2023

View full text Add to dashboard Cite

This paper contributes to improving a bottleneck residual block-based feature extractor as a set of layers for transforming raw data into features for classification. This structure is utilized to avoid the issues of the deep learning network, such as overfitting problems and low computational efficiency caused by redundant computation, high dimensionality, and gradient vanishing. With this structure, a domain adversarial neural network (DANN), a domain adversarial unsupervised model, and a maximum classifier discrepancy (MCD), a domain adaptation model, have been applied to conduct a binary classification of fault diagnosis data. In addition, a pseudo-label is applied to MCD for comparison with the original one. In comparison, several popular models are selected for transferability estimation and analysis. The experimental results have shown that DANN and MCD with this improved feature extractor have achieved high classification accuracy, with 96.84% and 100%, respectively. Meanwhile, after using the pseudo-label semi-supervised learning, the average classification accuracy of the MCD model increased by 15%, increasing to 94.19%.

show abstract

Frequency-Domain Fusing Convolutional Neural Network: A Unified Architecture Improving Effect of Domain Adaptation for Fault Diagnosis

Cited by 21 publications

References 43 publications

An Edge Computing Application of Fundamental Frequency Extraction for Ocean Currents and Waves

An Edge Computing Application of Fundamental Frequency Extraction for Ocean Currents and Waves

Bearing fault diagnosis based on inverted Mel-scale frequency cepstral coefficients and deformable convolution networks

Unsupervised Method Based on Adversarial Domain Adaptation for Bearing Fault Diagnosis

Contact Info

Product

Resources

About