Anjidani & Partners Co. CN. 1444283
omanmedica.comomanmedica.comomanmedica.com
96892735515
SA to TH 8:00 To 20:00
Muscat, 18 Nov ST, No 432
omanmedica.comomanmedica.comomanmedica.com

Real-Time Surface Inspection

Real-Time Surface Inspection

This project combines computational materials science and Big Data analysis to generate a comprehensive digital twin of the aluminum strip casting process, aligned with the fourth wave of industry.

Current technologies in the production of continuous aluminum sheets and sheets face two major challenges:

Any change in alloy chemistry, strip thickness or casting speed requires adjustment of process parameters. This adjustment is normally achieved by intelligent trial and error. The success rate depends a lot on the experience and knowledge of the production team.
It is necessary to meet the important requirements of the optical properties for the sheets. In next-generation strip casting facilities, the production speed can reach tens of meters per minute. Detecting defects at such production speeds is nearly impossible with conventional visual quality control.
Schematic structure of the caster complex geometry

At AI-innovate we have developed an aluminium strip casting assistive computational package that employs integrated computational materials engineering (ICME) and deep learning (DL) algorithms to integrate the simulation data and production line data to address these challenges.

The software package is able to:

Modeling process progress (this module addresses challenge 1)
Automatic detection/classification of defects in real time (this module addresses challenge 2)
process optimization through feedback to operational equipment (this module empowers the factory to operate in optimal conditions and equips it with a predictive model to determine the probability of defective production)
defects in real time

The nature of this project corresponds to the needs of Industry 4.0 and offers the next level of efficiency and productivity in molten aluminum strip-to-coil casting lines, beyond the technologies used today. The use of artificial intelligence and machine learning algorithms to accurately and rapidly optimize the casting process is informed by data generated from three independent sources:

telemetry data from embedded sensors
optical and thermal images generated from the inspected surface
a simulation module that models the casting process.

The proposed setup can be applied to any high-speed continuous production line, including polymer sheets, fabrics, coatings, paints, and many others.

telemetry data from embedded sensors
X