Machine learning for ultrasonic nondestructive examination of welding defects: A systematic review

Recent years have seen a substantial increase in the application of machine learning (ML) for automated analysis of nondestructive examination (NDE) data. One of the applications of interest is the use of ML for the analysis of data from in-service inspection of welds in nuclear power and other industries. These types of inspections are performed in accordance with criteria described in the ASME Boiler and Pressure Vessel Code and require the use of reliable NDE techniques. The rapid growth in ML methods and the diversity of possible approaches indicate a need to assess the current capabilities of ML and automated data analysis for NDE and identify any gaps or shortcomings in current ML technologies as applied to the automated analysis of NDE data. In particular, there is a need to determine the impact of ML on the NDE reliability. This paper discusses the findings from a literature survey on the current state of ML for the automated analysis of data from ultrasonic NDE of weld flaws. It discusses an overview of ultrasonic NDE as used for weld inspections in nuclear power and other industries. Data sets and ML models used in the literature are summarized, along with a generally applicable workflow for ML. Findings on the capabilities, limitations and potential gaps in feature selection, data selection, and ML model optimization are discussed. The paper identified several needs for quantifying and validating the performance of ML methods for ultrasonic NDE, including the need for common data sets.

Automated summary

In recent years, there has been an increase in the use of machine learning for automated analysis of nondestructive examination (NDE) data, particularly in weld inspections for nuclear power and other industries. This paper discusses the current state of machine learning for automated analysis of ultrasonic NDE data on weld flaws. The findings from a literature survey, including data sets, machine learning models, and workflow, are summarized. The paper also highlights the capabilities, limitations, and potential gaps in feature selection, data selection, and model optimization. The need for quantifying and validating the performance of machine learning methods for ultrasonic NDE, including the need for common data sets, is identified.