Koh Young has declared to host an English webinar to shed light on the possibilities of using Artificial Intelligence (AI) in a surface mount electronics assembly line using the automated measurements systems as an example.
The webinar delivered by Axel Lindloff of Koh Young Europe is scheduled for 03 November 2021 beginning at 11:00 am CET (Central European Time).
AI has long surrounded us in all areas of life, but we no longer perceive it as such. Speech recognition, spelling check, search filters, and personalized ads are self-evident functions for us. In truth, they are AI examples. An AI simulates human behavior and decisions using a variety of strategies.
It is only logical to use these useful tools in the production environment and to turn the spell check into a process parameter check. In electronics production, the structures and components are becoming smaller, and the processes are more complex.
At the same time, manufacturers are striving for fully automated, unattended production. The goals have long been set and the roadmaps have been created. Soon, electronics production may be a deserted place.
Using AI, manufacturers can increase process requirements and complete automation. AI was conceived to simulate human behavior and decisions.
In the past, it required supercomputers, but today the available computing power and intelligent application strategies give us new possibilities to use AI in the manufacturing process. Whereas some people make quick decisions based on gut feelings and past experiences, the AI decision is based on hard facts and measured values.
AI can mimic the human decision process in seconds while considering large data piles. The webinar will explore the possible benefits and advantages of applying AI in an SMT line.
A self-sufficient AI analysis can collect measurement data and account for production parameters to independently execute process optimization.
AI algorithms can further help by differentiating between components and designs for faster program creation. It is even capable of self-learning defect detection.