SKILLS

Deep learning

Our platform - machine learning for industrial use

MABRI.VISION has developed the DEEP.MV software platform for the application of modern deep learning and AI technologies in the industrial environment. The platform combines all the necessary components and enables use at the plant level.

Deep learning platform, machine learning application, deep learning

Possible uses

Our deep learning platform is ideal for applications where rule-based approaches are challenging or fail. This applies above all to test applications with a wide range of variants and error characteristics, such as varying surface and structural properties. The MABRI.VISION platform can be used optimally where, due to the complexity, primarily manual and manual checks are carried out using error catalogs.

Classification | Detection and classification of objects and errors

The classification forms the basis for many quality assurance tasks. In the application, there is no need for time-consuming labeling of data - it is sufficient to categorize images.

Error detection in flushing tabs

Dish-tab scratches

Scratch

Spueltab-opened

started

Flush tab-nio

not ok

Web error

OK

Deep learning platform, machine learning application, deep learning

Web error

Deep learning platform, machine learning application, deep learning

hole

Object recognition | Examples: completeness check, presence check, counting, pick & place and much more.

Completeness check

Board completeness

Position check

Lid position check

Attendance control

Defect detection | Surface defects, incomplete components, structural defects, color and shape defects and much more.

Injection molding defect

MABRI.VISION injection molding Short shot, short fill

Scratch

Microfluidic scratches

Pores and grooves

Machine vision methods, testing, structures, surfaces, chip detection, pores
Segmentation | Detection of structures and image areas, surface defects, incomplete components, structural defects, color and shape defects and much more.

Segmentation is always important when objects, structures or errors have to be identified and delimited very precisely. This information can be used, for example, for process optimization

Chip detection

Machine vision methods, testing, structures, surfaces, chip detection, pores

textiles

Machine vision methods, testing, structures, surfaces, chip detection, pores

Dish tabs

Incorrect sorting

foreign body

Anomaly detection | Defects on packaging, printed image control, weaving defects and much more.

Circuit boards

With our approach of combining 2D and 3D sensors, we can check a very large number of features for patinas. To monitor solder joints, we offer solutions with high-resolution 3D cameras.

Microstructures

Microstructure microfluidics lab-on-a-chip anomaly detection

Surfaces ex. Glue residue

OCR | Text recognition

DOT code on tires

Tires, reading bridge, DOT-TIN codes, testing, specifications, testing facility

Handwriting recognition

MABRI.VISION cavity number Machine Vision

Your advantages

MABRI.VISION provides you with everything you need for your application. In this way, you avoid using partial and isolated solutions that do not interlock and are therefore difficult to maintain. In addition to the software application, we primarily supply the necessary sensor systems, test platforms and services for your production process.

By using our lean AI platform, challenging applications in the industrial environment can also be solved cost-effectively. Manual and time-consuming test steps can thus be omitted.

The deep learning technology can solve applications that are very challenging or cannot be solved satisfactorily with classic image processing. This opens up completely new possibilities in quality assurance.

As a universal solution provider for optical production metrology, we take a close look at your application. We only use our deep learning technologies when and to the extent that it makes sense for the application. In this way you avoid incorrect results and excessive development costs. In addition, we map all other essential components in quality assurance, including calibration and traceability.

One challenge of the current development trends in the industry is modular production with ever shorter production cycles. Machine learning processes keep you flexible and allow you to adapt your production adaptively and independently.

The development in the field of deep learning is progressing very quickly. Our AI platform is therefore constantly being expanded and relies on established standards in research and development. This continuous development enables you to always use the latest technologies in the future.

Practical example: error detection on socks

Machine learning processes can be used wherever rule-based approaches are difficult to implement.

Deep learning platform, machine learning application, deep learning

Web error

Deep learning platform, machine learning application, deep learning

hole

Deep learning platform, machine learning application, deep learning

Practical example: Defect detection on metal pipes

Deep learning platform, machine learning application, deep learning

Chip

Deep learning platform, machine learning application, deep learning

Weld seam defect

Pictorial representation of a weld seam inspection with a laser beam.

Process flow

Deep learning methods are based on artificial neural networks.
These networks are inspired by the (biological) neural networks, i.e. part of a nervous system. Artificial neural networks are built in layers. A layer or level consists of several artificial neurons. There are several hidden levels between an entrance and exit level. The name "deep" neural network gets the structure because of exactly these hidden levels.

Deep learning platform, machine learning application, deep learning