Menu
Menu
Using a Trained Neural Network, the AI Tools for surface defects detection recognize a characteristic or defect that cannot be detected with traditional techniques.
PERFORMANT
Quick training
Fewer false rejects
than with traditional tools
READY TO
IMPROVEMENTS
Fastest Hardware
Upgradable software
EASY TO USE
User-friendly set-up
for surface controls
AI tools algorithm can be combined with the following control stations installed on Dimac MCV inspection machines.
For the control of raised or recessed elements on flat surfaces. SFS technology allows you to reconstruct the three-dimensional surface of a flat surface, highlighting raised and recessed elements. The control is not influenced by stains, non-homogeneity in the color of the piece, type, or appearance of the surface coating.
The most interesting applications are washers, flat heads of screws, coins, upper and lower surfaces of nuts, and fine blanking plates.
The combined analysis of the images of multiple cameras is arranged to see the entire external lateral surface of the piece to detect threads dents, scratches on smooth surfaces, open cracks, presence of radial holes.
The linear camera, combined with an encoded 360° rotation station, allows you to reconstruct the complete image of the lateral development of pieces with cylindrical or similar geometry.
The analysis of the development of the lateral surface of the piece can provide pieces of information of superficial and dimensional type: the presence of surface inhomogeneities (lines, scratches), the dimensional control of the correct phase between two asymmetric elements of the piece (for example two radial holes), the presence of open cracks (like the image above).
AI Tools for Surface defects detection differ from traditional vision software by not relying on preset rules. Instead, the AI algorithm calculates variables, forming a neural network that assesses image similarity for categories like compliant and non-compliant parts. This network determines the likeness percentage of a new image to specific categories.
AI goes beyond analytical image interpretation, autonomously generating search criteria with logic not directly understandable by humans. While highly versatile and powerful, its results aren’t entirely predictable beforehand, necessitating careful field validation.
Arriving at effective and computationally efficient solutions is crucial. The AI process demands substantial calculation time for the training and validation phases. To avoid prolonged non-productive periods of the sorting equipment, the training is not carried out on the sorting machine.
For user convenience, Dimac provides remote neural network training services.
The machine software incorporates a straightforward procedure to assist operators in capturing sufficient images of compliant and defective samples.
Ensuring safe 100% control of the character’s logo marked on the head of the rivet poses a challenge that cannot be solved with traditional techniques. Alongside human visual inspection, AI is currently the sole viable solution. The human eye remains essential in defining and optimizing the AI workflow today and possibly in the future.
