The aviation supplier PFW Aerospace, a subsidiary of the French company Hutchinson, is testing the use of Artificial Intelligence (AI) to ensure high quality standards in non-destructive material testing. An optimized economic efficiency in quality assessment tasks is targeted. As part of a pilot program, VisiConsult, the world market leader for customer-specific X-ray systems, is evaluating whether the evaluation of image data can be automated using AI. The core is the qualification of Artificial Intelligence according to demanding aviation test standards.

Convinced by reliability

PFW Aerospace has many years of experience with VisiConsult as a manufacturer of X-ray systems. "Thanks to the many systems, as well as the reliable service, we have been able to experience the special use of VisiConsult again and again in recent years," says Markus Gutensohn, Head of R&D at PFW Aerospace. "When VisiConsult announced that it now wants to establish artificial intelligence for evaluating image data and they offered a pilot program for this purpose, it was clear to us: We have to take part. "

Selected for a unique program

PFW Aerospace was selected as a pilot customer and will receive an AI prototype including test operation and a statistical qualification report. The application is for X-rays of longitudinally welded seams on titanium tubes. The test parts are subject to very high-quality standards because they are installed in aircraft. PFW will collect X-ray images over a defined period of time, which VisiConsult will then use as a basis for training AI networks. This is being brought to a secure industrial platform in collaboration with the AI pioneer FUJITSU.

Qualification by testing

In order to qualify this new technology according to the demanding test standards, sufficient statistical data about the accuracy of the algorithms must be available. Therefore, there is a permanent comparison of the AI results with the evaluations by experienced X-ray testers. With the help of this input, the neural networks are also regularly trained. Only when a sufficiently good detection probability (POD) has been proven the system can be qualified and used in production.

More quality through more intelligence

PFW Aerospace sees artificial intelligence for error interpretation as a future-oriented tool for its quality department: "This will save our employees a lot of time interpreting errors, and this time is ultimately available for other important tasks." The use of AI is expected to significantly increase the efficiency of non-destructive testing. It sorts out components with detected deviations and only forwards the necessary X-ray scans to the materials tester for final approval by humans. The information on the components with deviations can also be sent to the development team in order to optimise design data. Gutensohn assures: "The final approval will continue to be given by our highly qualified test colleagues." The motto here is: Safety First!

Digital revolution as the igniter for AI

For Lennart Schulenburg, Managing Director at VisiConsult, the fact that Artificial Intelligence is the next step in quality assurance is a logical consequence of the digital revolution: "Our inspection systems generate a mass of digital images and data that have to be evaluated and processed into information. This amount of data is hardly manageable for humans, but it can be processed with high precision by AI systems. "

Further pilot projects from other industries

VisiConsult is planning further pilot programs, also from other industries such as oil & gas and automotive. Companies that are interested in the program and would like to apply can find all the information at visiconsult.de/smart-inspection - there interested companies can apply for the waiting list of the pilot program or request a free initial analysis.