TDMSAE: A transferable decoupling multi-scale autoencoder for mechanical fault diagnosis

Yu, Shihang; Wang, Min; Pang, Shanchen; Song, Limei; Zhai, Xue; Zhao, Yawu

doi:10.1016/j.ymssp.2022.109789

Cited by 28 publications

(8 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The traditional three-frequency, six-step phase unfolding algorithm is slow, inaccurate, and relatively influenced by the environment due to ambient light and reflected light from the object's surface [22][23][24][25][26]. The industrial field is the intended application scenario for the algorithm proposed in this paper.…”

Section: Measurement Device and Methodsmentioning

confidence: 99%

Enhanced curve-based segmentation method for point clouds of curved and irregular structures

Song,

Zhang,

et al. 2024

Meas. Sci. Technol.

Self Cite

View full text Add to dashboard Cite

This paper proposes an improved method for model-based segmentation of curved and irregular mounded structures in 3D measurements. The proposed method divides the point cloud data into several levels according to the reasonable width calculated from the density of points, and then fits a curve model with 2D points to each level separately. The classification results of specific types are merged to obtain specific structural measurement data in 3D space. Experiments were conducted on the proposed method using the region growth algorithm (SRG) and the model-based segmentation method (MS) provided in the PCL library as the control group. The results show that the proposed method achieves higher accuracy with a mean intersection merge ratio (MloU) of more than 0.8238, which is at least37.92% higher than SRG and MS. The proposed method is also faster with a time-consuming only 1/5 of SRG and 1/2 of MS. Therefore, the proposed method is an effective and efficient way to segment the measurement data of curved and irregular mounded structures in 3D measurements. The method proposed in this paper has also applied in the practical robotic grinding task, the root mean square error of the grinding amount is less than 2 mm, and good grinding results are achieved.grinding results are achieved.

show abstract

Section: Measurement Device and Methodsmentioning

confidence: 99%

Enhanced curve-based segmentation method for point clouds of curved and irregular structures

Song,

Zhang,

et al. 2024

Meas. Sci. Technol.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The data involved in training and testing are randomly selected from this dataset, of which 80% is used as the training set and 20% as the testing set. In addition, a 5-fold cross-validation ( 23 , 24 ) is performed on the training set with a 4:1 ratio of data used for training and validation, and the best model is tested in an unseen test set to obtain the final results, with all models involved in the comparison undergoing the above process. We extended the training data with rotation, Gaussian noise and mixup.…”

Section: Methodsmentioning

confidence: 99%

DMFF-Net: A dual encoding multiscale feature fusion network for ovarian tumor segmentation

Wang

Zhou

Wang

et al. 2023

Front. Public Health

Self Cite

View full text Add to dashboard Cite

Ovarian cancer is a serious threat to the female reproductive system. Precise segmentation of the tumor area helps the doctors to further diagnose the disease. Automatic segmentation techniques for abstracting high-quality features from images through autonomous learning of model have become a hot research topic nowadays. However, the existing methods still have the problem of poor segmentation of ovarian tumor details. To cope with this problem, a dual encoding based multiscale feature fusion network (DMFF-Net) is proposed for ovarian tumor segmentation. Firstly, a dual encoding method is proposed to extract diverse features. These two encoding paths are composed of residual blocks and single dense aggregation blocks, respectively. Secondly, a multiscale feature fusion block is proposed to generate more advanced features. This block constructs feature fusion between two encoding paths to alleviate the feature loss during deep extraction and further increase the information content of the features. Finally, coordinate attention is added to the decoding stage after the feature concatenation, which enables the decoding stage to capture the valid information accurately. The test results show that the proposed method outperforms existing medical image segmentation algorithms for segmenting lesion details. Moreover, the proposed method also performs well in two other segmentation tasks.

show abstract

“…Gu et al [ 7 ] proposed a scale attention module to obtain multiple-scale feature maps. Yu et al [ 26 ] constructed a six-layer residual neural network to fully extract the features of mechanical vibration signals and visualize them using gradient and feature vector-based class activation maps. Cao et al [ 27 ] proposed a transformer-based U-shaped encoder–decoder structure called Swin-Unet, which fuses the extracted contextual features with the multi-scale features of the encoder through a jump connection to compensate for the spatial loss caused by downsampling.…”

Section: Introductionmentioning

confidence: 99%

WRANet: wavelet integrated residual attention U-Net network for medical image segmentation

Zhao

Wang

Zhang

et al. 2023

Complex Intell. Syst.

Self Cite

View full text Add to dashboard Cite

Medical image segmentation is crucial for the diagnosis and analysis of disease. Deep convolutional neural network methods have achieved great success in medical image segmentation. However, they are highly susceptible to noise interference during the propagation of the network, where weak noise can dramatically alter the network output. As the network deepens, it can face problems such as gradient explosion and vanishing. To improve the robustness and segmentation performance of the network, we propose a wavelet residual attention network (WRANet) for medical image segmentation. We replace the standard downsampling modules (e.g., maximum pooling and average pooling) in CNNs with discrete wavelet transform, decompose the features into low- and high-frequency components, and remove the high-frequency components to eliminate noise. At the same time, the problem of feature loss can be effectively addressed by introducing an attention mechanism. The combined experimental results show that our method can effectively perform aneurysm segmentation, achieving a Dice score of 78.99%, an IoU score of 68.96%, a precision of 85.21%, and a sensitivity score of 80.98%. In polyp segmentation, a Dice score of 88.89%, an IoU score of 81.74%, a precision rate of 91.32%, and a sensitivity score of 91.07% were achieved. Furthermore, our comparison with state-of-the-art techniques demonstrates the competitiveness of the WRANet network.

show abstract

TDMSAE: A transferable decoupling multi-scale autoencoder for mechanical fault diagnosis

Cited by 28 publications

References 30 publications

Enhanced curve-based segmentation method for point clouds of curved and irregular structures

Enhanced curve-based segmentation method for point clouds of curved and irregular structures

DMFF-Net: A dual encoding multiscale feature fusion network for ovarian tumor segmentation

WRANet: wavelet integrated residual attention U-Net network for medical image segmentation

Contact Info

Product

Resources

About