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 comprises a signal-processing module based on a modified total focusing method that creates a sequence of two-dimensional images of an evaluated specimen; an image-processing module, which filters and enhances these images; and an explainable AI module—a decision tree, which selects images of possible cracks, groups those of them that appear to represent the same crack and produces for each group a possible inspection report for perusal by a human inspector. AutoNDE has been trained on 16 datasets collected in a laboratory by imaging steel specimens with large smooth planar notches, both embedded and surface-breaking. It has been tested on two other similar datasets. The paper presents results of this training and testing and describes in detail an approach to dealing with the main source of error in ultrasonic data—undulations in the specimens’ surfaces.

Interpretable and Explainable Machine Learning for Ultrasonic Defect Sizing

“…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.…”

A Dataset of Pulsed Thermography for Automated Defect Depth Estimation

“…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].…”