NDT 4.0 – Automated Interpretation of Industrial X-ray Images

With digital X-ray detectors and highly automated inspection systems, manufacturers can significantly optimize their quality control and assurance processes. However, due to the higher throughput of parts, the evaluation and interpretation of X-ray images can become an expensive bottleneck.

Advanced technologies such as automated defect detection (ADR) and artificial intelligence (AI) have the potential to significantly reduce the cycle time required per component. Depending on the test standard and requirements, the algorithms can be implemented as an assistance system for the operator or fully automatically.

Machine learning as a supply for automatic defect recognition is important to the NDT sector because it is a data driven trend and the NDT sector supplies a lot of the data. To recreate the data and use it to improve processes and quality traditionally means putting the image on a screen, take some time, look at it and then make a decision. Now with the add of NDT 4.0 allows the making of even more semi-automatic decisions. It is a process to switch from manual to a system that automatically recognize the defect.

Under the umbrella of the fourth industrial revolution, also known as NDT 4.0, new technologies such as Artificial Intelligence (AI), cloud computing, IIOT, simulation and big data enable another significant increase in efficiency. The availability of low-maintenance and precise algorithms for automatic error detection (ADR) helps operators to make better decisions in less time. Digitization and intelligent data evaluation strategies have the potential to contribute to serious improvements in test processes.

Data-Driven Decisions – Allows creation of meaningful statistics on components defects. Gain knowledge about the distribution of defects (type, size, etc.) and create your own digital defect catalogs.

Automated Evaluation – Increases the efficiency of quality assurance by evaluating and interpreting industrial X-ray images using artificial intelligence.

Process Insights – Find out more about the performance and quality of your production processes and use this knowledge to optimize processes through a real-time feedback loop.

Quality of Inspection – An assistance system can support the operator in making decisions in order to increase the probability of detection and the general test reliability.

The availability of low-maintenance and precise algorithms for automatic error detection (ADR) can help operators make better decisions in less time. Digitization and intelligent data evaluation strategies have the potential to contribute to serious improvements in test processes.