Uncertainty Quantification for Deep Learning in Ultrasonic Crack Characterization

Pyle, Richard J.; Hughes, Rhidian; Ali, Amine Ait Si; Wilcox, Paul D.

doi:10.1109/tuffc.2022.3176926

Cited by 19 publications

(12 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The resulting A-Scans are then filtered and imaged, as described above, to form the four relevant PWI images. This simulation approach follows the one used in [9], [14], [15].…”

Section: A Inspection Imaging and Simulation Methodologiesmentioning

confidence: 99%

“…This section describes the inspection setup, the experimental and numerical procedures used to create PWI data, and the parameter space covered by that data. Following on from previous work, these setups and procedures are the same as those used in [9], [14] & [15].…”

Section: Inspection Setup and Data Setsmentioning

confidence: 99%

“…This drastically lowers the amount of experimental data required to implement ML based defect sizing. It has also been shown that domain adaptation can be used to further increase sizing accuracy if a small amount of experimental training data is available to supplement simulated training data [14] and effective uncertainty quantification is possible using a deep ensemble [15]. However, qualification of inspections using ML for safety critical applications such as pipeline inspection is still a challenge due to the 'black-box' nature of ML making it hard to build trust in, and certify, its predictions.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Interpretable and Explainable Machine Learning for Ultrasonic Defect Sizing

Pyle

Hughes

Wilcox

2023

IEEE Trans. Ultrason., Ferroelect., Freq. Contr.

Self Cite

View full text Add to dashboard Cite

“…The resulting A-Scans are then filtered and imaged, as described above, to form the four relevant PWI images. This simulation approach follows the one used in [9], [14], [15].…”

Section: A Inspection Imaging and Simulation Methodologiesmentioning

confidence: 99%

Section: Inspection Setup and Data Setsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Interpretable and Explainable Machine Learning for Ultrasonic Defect Sizing

Pyle

Hughes

Wilcox

2023

IEEE Trans. Ultrason., Ferroelect., Freq. Contr.

Self Cite

View full text Add to dashboard Cite

“…Deep ensembles of machine learning networks have been shown to increase prediction accuracy and provide a measure of uncertainty. 33 To determine a sufficient number of networks (members) in the ensemble, increasing numbers of members were included in the ensemble and the SD of the RMSE was computed. This process was repeated with random (unique) shuffles of the order in which the networks were included in the ensemble.…”

Section: Deep Ensemblementioning

confidence: 99%

A comparison of ultrasonic temperature monitoring using machine learning and physics-based methods for high-cycle thermal fatigue monitoring

Clarkson,

Zhang,

Cegla

2023

Structural Health Monitoring

View full text Add to dashboard Cite

Failure of pipe network components in so-called mixing zones due to high-cycle thermal fatigue (HCTF) can occur within nuclear power plants where fluids of different thermal and hydraulic properties interact. Given that the consequences of such failures are potentially deadly, a method to monitor HCTF non-invasively in real-time is expected to be of great use. This method may be realised by a technique to determine the inaccessible temperature distribution of a component since thermal gradients drive HCTF. Previous work showed that a physics-based method called the inverse thermal modelling (ITM) method can obtain the temperature distribution from external temperature and ultrasonic time of flight (TOF) measurements. This study investigated whether the long-short-term memory (LSTM) machine learning architecture could be a faster alternative to the ITM method for data inversion. On experimental data, a 25-member ensemble of LSTM networks achieved an ensemble median root mean square error (RMSE) of 1.04°C and an ensemble median mean error of 0.194°C (both relative to a resistance temperature device measurement). These values are similar to the ITM method which achieved a RMSE of 1.04°C and a mean error of 0.196°C. The single LSTM network and the ITM method achieved a computation-to-real-world time ratio of 0.008% and 14%, respectively demonstrating that both methods can invert data in real-time. Simulation studies revealed that LSTM performance is sensitive to small differences between the training and real-world parameters leading to unacceptable errors. However, these errors can be detected via an ensemble of independent networks and, corrected by simply adding a correction factor to the TOF prior to being input into the networks. The results show that LSTM has the potential to be an alternative to the ITM method; however, the authors favour ITM for temperature distribution monitoring given its interpretability.

show abstract

“…Aiming at the requirement of ultrasonic atlas target detection of workpiece weld defects, a large number of scholars have conducted extensive research to solve the problem of ultrasonic atlas target detection, especially the classification of defects to be detected. Richard et al 11 used the training of convolutional neural network to characterize crack defects in pipeline crack detection. Compared with the traditional image-based crack characterization method, it is proved that the accuracy of the deep learning method to characterize the length and angle of crack defects was significantly improved.…”

Section: Introductionmentioning

confidence: 99%

An improved faster RCNN-based weld ultrasonic atlas defect detection method

Chen

Wang

Huang

2022

Measurement and Control

View full text Add to dashboard Cite

In view of the complex multi-scale target detection environment of ultrasonic atlas of weld defect and the poor detection performance of existing algorithms for the multiple small target defects, the Faster RCNN convolution neural network is applied to weld defect detection, and a Fast RCNN deep learning network is proposed in combination with an improved ResNet 50. Based on the coexistence of multiple small targets and multi-scale target detection, this paper proposes to combine deformable network, FPN network and ResNet50 to improve the detection performance of the algorithm for multi-scale targets, especially small targets. Based on the efficiency and accuracy of candidate frame selection, K-means clustering algorithm and ROI Align algorithm are proposed, and the anchors points and candidate frames suitable for weld defect data sets are customized for accurate positioning. Through the self-made ultrasonic atlas data set of weld defects and experimental verification of the improved algorithm in this paper, the overall mean average precision has reaches 93.72%, and the average precision of small target defects such as “stoma” and “crack” has reaches 92.5% and 88.9% respectively, which is 4.8% higher than the original Faster RCNN algorithm. At the same time, through the ablation experiments and comparison experiments with other mainstream target detection algorithms, it is proved that the improved method proposed in this paper improves the detection performance and is superior to other algorithms. The actual industrial detection scene proves that it basically meets the requirements of weld defect detection, and can provide a reference for the intelligent detection method of weld defects.

show abstract

Uncertainty Quantification for Deep Learning in Ultrasonic Crack Characterization

Cited by 19 publications

References 54 publications

Interpretable and Explainable Machine Learning for Ultrasonic Defect Sizing

Interpretable and Explainable Machine Learning for Ultrasonic Defect Sizing

A comparison of ultrasonic temperature monitoring using machine learning and physics-based methods for high-cycle thermal fatigue monitoring

An improved faster RCNN-based weld ultrasonic atlas defect detection method

Contact Info

Product

Resources

About