Research on an ultrasonic detection method for weld defects based on neural network architecture search

Zhang, Rui; Gao, Mei-Rong; Zhang, Peng-Yun; Zhang, Yong-Mei; Fu, Liu-Hu; Chai, Yan-Feng

doi:10.1016/j.measurement.2023.113483

Cited by 6 publications

(3 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ResNet50 is a very effective neural network architecture for image classification and other computer vision problems [ 28 , [70] , [71] , [72] , [73] , [74] ]. Being pre-trained on large image datasets, ResNet50 can provide high performance without the need to train a neural network from scratch; it is further used to save training time and to aid the effective generalization of the models built by learning from visual patterns and features of the image set it was initially trained on.…”

Section: Methodsmentioning

confidence: 99%

“…In recent years, the excellent results achieved by convolutional neural networks for image classification have been demonstrated [ [26] , [27] , [28] , [29] ]. This type of deep learning model has been widely used [ 30 , 31 ] because of its advantages in bringing together feature extraction and classification results in a single structure.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep convolutional neural network for weld defect classification in radiographic images

Palma-Ramírez,

Ross-Veitía,

Font-Ariosa

et al. 2024

Heliyon

View full text Add to dashboard Cite

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Deep convolutional neural network for weld defect classification in radiographic images

Palma-Ramírez,

Ross-Veitía,

Font-Ariosa

et al. 2024

Heliyon

View full text Add to dashboard Cite

“…(5) Therefore, we propose to use the MTF to map onedimensional vibration signals to two-dimensional spatial domain images [27]. The specific encoding process includes the following steps:…”

Section: Markov Transfer Fieldmentioning

confidence: 99%

Interpretable coal-rock cutting vibration recognition with Markov transition field and selective neural networks

Wang,

Zhang,

Cao

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

To address the low accuracy of current one-dimensional signal recognition for coal-rock cutting vibration and the low efficiency of traditional static neural networks, this paper proposes an interpretable recognition method that combines Markov Transition Field (MTF) and channel-selective neural networks. Firstly, by decomposing and reconstructing the energy of wavelet packets and denoising the signal, it is transformed into MTF images with temporal correlation to improve signal processing efficiency. Then, a channel selective module is proposed to replace traditional convolutional layers, enhancing the model's ability to extract data features. A spatial shift mechanism is improved to alleviate the problem of weight degradation and improve the model's generalization capability. The test results on a self-constructed experimental dataset show that this method achieves a recognition accuracy of up to 97.375% without increasing additional parameters, significantly outperforming traditional methods and maintaining good robustness in noisy environments. This study improves the efficiency and accuracy of coal-rock cutting state recognition and provides new ideas for signal processing in environments with limited underground computing resources.

show abstract

Automated detection of multi-type defects of ultrasonic TFM images for aeroengine casing rings with complex sections based on deep learning

GUAN,

WANG,

HUA

et al. 2024

Chinese Journal of Aeronautics

View full text Add to dashboard Cite

Research on an ultrasonic detection method for weld defects based on neural network architecture search

Cited by 6 publications

References 29 publications

Deep convolutional neural network for weld defect classification in radiographic images

Deep convolutional neural network for weld defect classification in radiographic images

Interpretable coal-rock cutting vibration recognition with Markov transition field and selective neural networks

Automated detection of multi-type defects of ultrasonic TFM images for aeroengine casing rings with complex sections based on deep learning

Contact Info

Product

Resources

About