Artificial intelligence in NDE: Automatic error detection and higher data integrity
The range of applications includes the automatic recognition of components and the assignment to an inspection instruction: once stored, the software recognises which inspection part it is based on the images and automatically places a matching template over the image, which shows exactly at which locations measurements must be taken. The generated inspection data is fed back into the Inspection Management System. The advantage: it is ensured that the right measurements are taken on the right component with the right designations and fed back into the management software. Such automated inspections can also be carried out retroactively for inspections that have already been performed, for example for quality assurance purposes.
However, AI can also be used to automate the measurement itself. For example, the point with the thinnest wall thickness on a pipeline can be automatically detected and measured. Finally, the third application scenario is the automated detection of erosion, corrosion and deposits on the test images. Such detection simply takes place in the background, the inspector does not have to do anything for it.
PACS as a prerequisite for AI in NDE, NDT and inspection
The prerequisite for the use of such AI solutions is a qualified database. And this requires that the inspection workflow is digitized in such a way that inspection data and reports are available digitally and that there are no media breaks in the process. In short, the use of AI requires the use of a PACS, i.e., software for image data management with interfaces to the customer's leading IT systems. The DIMATE PACS fulfills these tasks, so it was only logical that we use our excellent database to provide our customers with further advantages through the use of AI.