Crack Orientation Determination of 304 Austenitic Stainless Steel Based on Alternating Current Field Measurement

Yan, Liang; Wan, BenLi; Hu, Bin; Fan, Mengbao

doi:10.1007/s10921-022-00886-x

Cited by 1 publication

(2 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…At present, the research of crack length, area, depth and crack degree is mostly carried out under the condition that the crack direction is known, but the crack direction is unknown in practice, so the problem of crack direction has aroused widespread concern. For example, Yang Lijian [4] and Yan Liang [5] have successively put forward the electromagnetic detection method of crack direction. This method uses the relationship between the peak value of the wave valley of the electromagnetic field and the crack direction to realize the full-angle detection of the crack direction, with the error not exceeding 8.4 °.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Crack orientation recognition method based on prototype learning

Liu

Chen

et al. 2023

International Conference on Image, Signal Processing, and Pattern Recognition (ISPP 2023)

View full text Add to dashboard Cite

To address the problem that the direction of pipe cracks is difficult to detect, a crack direction recognition method based on prototype learning is proposed with a prototype network as a framework. First, through the convolutional layer of the prototype network, shallow features of crack directions are extracted to improve the generalization ability of the model on the data set of this paper. then, by improving the High-Resolution Network and introducing a location self-attention mechanism, and combined with a migration training method for the data set of this paper, a category that can accurately reflect the crack directions is constructed prototype learning mechanism. Finally, pattern recognition is performed by the metric classification methods, the effective classification of crack direction under small sample condition is achieved. The experimental results show that the recognition accuracy of the crack direction recognition method based on prototype learning can reach 99.2% with the sample parameters unchanged.

show abstract

Section: Introductionmentioning

confidence: 99%

“…In formula (5), 𝑑 represents the input dimension of Q and K. Because the inner product operation will produce large scalar results, saturate the function softmax, which is not conducive to the reverse transfer of gradient, so dividing by 𝑑 can make the model have a stable gradient.…”

mentioning

confidence: 99%

Crack orientation recognition method based on prototype learning

Liu

Chen

et al. 2023

International Conference on Image, Signal Processing, and Pattern Recognition (ISPP 2023)

View full text Add to dashboard Cite

show abstract

Crack Orientation Determination of 304 Austenitic Stainless Steel Based on Alternating Current Field Measurement

Cited by 1 publication

References 24 publications

Crack orientation recognition method based on prototype learning

Crack orientation recognition method based on prototype learning

Contact Info

Product

Resources

About