Graphic Augmented Defect Recognition for Phased Array Ultrasonic Testing on Tubular TKY Joints

Luo, Hongyu; Chen, Q. H.; Lin, Wei

doi:10.1007/s10921-020-00698-x

Cited by 6 publications

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More recent approaches have been used with the PAUT data. Luo et al [20] were able to construct an algorithm which utilized spatial clustering and segmentation to detect flaws from the S-scan data in TKY welded joints. While the algorithm used multiple angles, the algorithm relied only to the 2D data obatained from the S-scan.…”

Section: Machine Learning For Ut Datamentioning

confidence: 99%

“…The DCNN Virkkunen et al [40] utilized had less than 100,000 parameters. The ultrasonic data can be considered simple as there are a lot of similarities within the data, which enable the use of simpler mathematical approaches as for Luo et al [20] to a certain point. Moreover, the number of required extracted features for high classification accuracy has been low for shallower networks and SVMs.…”

Section: Machine Learning For Ut Datamentioning

confidence: 99%

See 1 more Smart Citation

Automated Flaw Detection in Multi-channel Phased Array Ultrasonic Data Using Machine Learning

et al. 2021

View full text Add to dashboard Cite

Modern ultrasonic inspections utilize ever-richer data-sets made possible by phased array equipment. A typical inspection may include tens of channels with different refraction angle, that are acquired at high speed. These rich data sets allow highly reliable and efficient inspection in complex cases, such as dissimilar metal or austenitic stainless steel welds. The rich data sets allow human inspectors to detect cracks with low signal-to-noise ratio from the wider signal patterns. There’s a clear trend in the industry to even richer data sets with full matrix capture (FMC) and related techniques. Convolutional neural networks have recently shown capability to detect flaws with human level accuracy in ultrasonic signals at the B-scan level. To enable automated flaw detection at human-level accuracy for critical applications, these neural networks need be developed to take advantage of today’s rich phased array data-sets. In the present paper, we extend previous work and develop convolutional neural networks that perform highly reliable flaw detection on typical multi-channel phased array data on austenitic welds. The results show, that the modern neural networks can accommodate the rich ultrasonic data and display high flaw detection performance.

show abstract

Section: Machine Learning For Ut Datamentioning

confidence: 99%

Section: Machine Learning For Ut Datamentioning

confidence: 99%