Search
Realizations

Blispect for pharmaceutical producer – BIOFARM

BIOFARM is a Polish pharmaceutical manufacturer with a long tradition.

The client expected full integration of the machine vision system with the blistering machine while maintaining the existing functions of the blistering machine.
At KSM Vision, thanks to the smart construction and customized hardware of the Blispect system we managed to meet these requirements – integrating the Blispect vision system with the CAM and IMA blistering machines while maintaining operations at full efficiency.

The BLISPECT system implemented at BIOFARM offers:

– inspection of tablets and capsules packed in blisters
– two-color capsules and capsules with prints

The solution prepared for BIOFARM meets GAMP-5 & Audit Trail requirements.

  • Solution BLISPECT
  • Client BIOFARM
  • In our opinion, the application of neural networks and the classification function for detected defects distinguishes KSM Vision's solution from competitive alternatives, and the system's achieved efficiency ensures quality control on the level of leading manufacturers' systems.
    MLEKOVITA, listed on the FORBES 100 ranking of the largest private Polish companies (2022).
    mgr. inż. Dariusz Sapiński,
    President of the Board
  • During the design process, KSM Vision demonstrated great flexibility in adapting the system to the expectations of BIOFARM's Production Department. (...) Since the implementation of the BLISPECT vision technology on BIOFARM's first production line nearly two years ago, KSM Vision's Service Department has been and remains available to BIOFARM employees with a good response time.
    BIOFARM Jarosław Pieczuro,
    President of the Board
  • KSM Vision Sp. z o.o. developed a system for quality control of glass vials for tablets. (...) A major advantage of the system is the use of machine learning algorithms, which allows for easy and quick system adjustment.
    ADAMED Group Dariusz Stępień,
    Director of Infrastructure and Media

Project scope

The BLISPECT system integration at BIOFARM service included:

– designing a solution to maintain the functionality and efficiency of the existing blistering machine
– using an proprietary image visioning solution base on the neural network architecture – thanks to that training the system for new formats takes a minute
– use of feature extraction based on neural networks for the analysis of two-color capsules and printed capsules
– detection of defects in size as small as 15% of the tablet/capsule surface
– controlling the sensitivity of the system using only one parameter “tolerance”, which sets the threshold between good capsules/tablets and defective ones
– minimizing line changeover time while maintaining the accuracy of data analysis
– very easy to use system which translates both to faster introduction/training of new operators, and production downtime reduction
– integration of rejection stations for defective products

 

Our R&D on the solutions with the use of neural network potential are backed by our renowned partners: