Industrial computed tomography data analysis is harnessing deep learning to both accelerate in-line inspection and build better products. This article includes a case history involving deep learning industrial CT scan data analysis.

This article summarizes the more common analytical techniques for studying ancient metal artifacts, illustrated by case histories. There are two main classifications: noninvasive and invasive techniques. This distinction is of prime importance because some heritage objects may be too rare or valuable for invasive sampling, or there may be ethical objections to certain types of examination. Noninvasive examination of ancient metal artifacts is important, yet it cannot provide the detailed information obtainable from invasive techniques. This is especially true when artifacts contain “hidden” damage and there is also a need for accurate quantitative analyses.

Fire risk in electric vehicle batteries can be reduced by detecting flaws through nondestructive visualization. Industrial computed tomography (CT scanning) combined with advanced software that makes sense of CT-generated images, allows users to measure voids and particle sizes within electrode active material during the research and development phase, detect delamination and contamination during cell manufacturing, analyze electrical connections and electrolyte fill levels, and provide many other quality-assurance functions that were once impractical or even impossible to perform.