Development of an Explainable Augmented Intelligence (AI) System for Crack Characterization Using Ultrasonic Phased Array Data

Crack characterisation is one of the central tasks of NDT&E (Non-Destructive Testing and Evaluation) of industrial components and structures. A novel code containing a decision tree, that is, an explainable AI has been designed and developed for characterizing single large planar cracks. For the component surfaces whose undulation errors can be described using a normal distribution, a method for automatic estimation of the degree of the interpolating polynomial was developed. 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 chapter offers an approach to designing an explainable AI (Augmented Intelligence) to meet this challenge. It describes a novel C++ code called AutoNDE, which contains 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 customized decision tree, which selects images of possible cracks, groups those of them that appear to represent the same crack and for each group, produces 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, establishing values of various model parameters by trial and error It has been tested on two other similar datasets. The chapter 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. AutoNDE locates a number of points on the inspected surfaces and effects a polynomial surface interpolation. Under the assumption that the error in the location of these points obeys a normal distribution, a novel method is presented for automatic estimation of the polynomial degree. Notwithstanding various challenges, AutoNDE shows great promise, demonstrating the feasibility of an explainable AI, suitable for applications in industrial NDE, increasing its accuracy and efficiency.