2021
DOI: 10.3390/app112210867
|View full text |Cite|
|
Sign up to set email alerts
|

Towards Explainable Augmented Intelligence (AI) for Crack Characterization

Abstract: Crack characterization is one of the central tasks of NDT&E (the Non-destructive Testing and Evaluation) of industrial components and structures. These days data necessary for carrying out this task are often collected using ultrasonic phased arrays. Many ultrasonic phased array inspections are automated but interpretation of the data they produce is not. This paper offers an approach to designing an explainable AI (Augmented Intelligence) to meet this challenge. It describes a C code called AutoNDE, which… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2

Citation Types

0
2
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
5

Relationship

0
5

Authors

Journals

citations
Cited by 6 publications
(2 citation statements)
references
References 24 publications
0
2
0
Order By: Relevance
“…Saliency-map based explanations have been produced using LIME, for ultrasonic defect detection [24]. Text-based explanations have been used with a human-designed decision tree for crack characterization [25], an effective approach when the decision-making process of the model is simple enough to be explained in a small number of sentences. Improving the interpretability of ML methods for ultrasonic NDE data has been achieved by replacing the trainable convolutional filters of a CNN with filters matched to the shape of Lamb waves [26] in application to localizing damage in aluminum plate using guided waves.…”
Section: Introductionmentioning
confidence: 99%
“…Saliency-map based explanations have been produced using LIME, for ultrasonic defect detection [24]. Text-based explanations have been used with a human-designed decision tree for crack characterization [25], an effective approach when the decision-making process of the model is simple enough to be explained in a small number of sentences. Improving the interpretability of ML methods for ultrasonic NDE data has been achieved by replacing the trainable convolutional filters of a CNN with filters matched to the shape of Lamb waves [26] in application to localizing damage in aluminum plate using guided waves.…”
Section: Introductionmentioning
confidence: 99%
“…In recent years, significant efforts have been dedicated to applying Artificial Intelligence (AI) techniques to the NDE data analysis. This includes the characterization of defects within ultrasound data [12,13], as well as advancements in CT data processing [14,15]. For IRT data analysis, current research primarily targets defect detection and the improvement of infrared imagery quality [16,17].…”
Section: Introductionmentioning
confidence: 99%