VisiConsult X-ray Systems & Solutions is developing an artificial intelligence (AI) platform to detect defects even more reliably and more automated than past devices.
Initial tests with available AI frameworks achieved detection rates of up to 90 per cent in a blind study compared to conventional procedures.
Since the digitisation period in the past ten years, digital detectors have been used much more heavily instead of analogue film.
With this digitisation step, the data is available in real time and can be evaluated by computers. This is highly relevant in high volume sectors such as the automotive sector.
For 20 years, VisiConsult has been delivering automated defect recognition systems, which detect errors automatically after a human does a component-specific parameterization.
In a fast moving age, production cycles are getting shorter and the market is calling for more speed.
The classic image processing methods of the X-ray specialists require a high positioning accuracy and an extensive component parameterization.
Specialists from VisiConsult predict this effort could be massively reduced by using AI.
But, authorised signatory at VisiConsult, Lennart Schulenburg, said the tests were still in their infancy.
“Since our systems are used to test safety-critical components, extensive tests and qualifications are necessary.”
VisiConsult concluded a research cooperation with the University of Lübeck in 2017.
“The university of Lübeck is a leader in medical imaging. Since they already investigated heavily in AI, this area is already far ahead of our industry. We are currently transferring this knowledge to our applications,” said Schulenburg.
Automatic defect recognition has historically been excluded from high-critical areas such as aviation.
Due to the increased quantities in these areas, there is a great interest in qualifying the procedures accordingly.
VisiConsult is working with a leading aviation group in a European aviation research project to establish automatic defect recognition as a test method.
Crucial for the success of an AI is the number and quality of the underlying image data.
“Data is the oil of Industry 4.0,” said Schulenburg.
VisiConsult has developed a cloud solution into which cooperation partners can upload evaluated image data.
These are anonymised and used to parameterize the AI.
The higher the quality of the data, the better the AI can become.
VisiConsults error database includes multivalued multi-user records with marked and classified errors.
VisiConsult has developed a patent for automatic robot positioning.
Through the combination of robotics, 3D sensors and image registration a high positioning repeatability can be achieved without additional components.
This system will now be combined with the new AI solutions, reducing the ramp-up process from several days to a few hours.
Components are then moved in mixed operation on a conveyor belt in the system and are automatically detected by the system.
The software would recognise which component is to be inspected and guides the robotics to the exact inspection-position.
This would eliminate set-up times completely and increase the throughput massively.
As a side effect, the pseudo-rejects are reduced and the detection probability is increased.
Both are requirements for an aerospace approval of the system.