Increase of the Automotive Power Transistor Modules Manufacture Reliability Using Ai Detecting System for Soldering Splashes

This study discusses the automated visual inspection of electronic boards used in mass production power electronics equipment. Soldering splashes, produced during necessary manufacturing stages, can affect hybrid semiconductor modules' quality, specifications and lifespan. Splashes from soldering may appear some areas when they cause decreasing quality these need to be removed. Image analysis algorithms are search for such areas. The is based on neural network YOLO. images boards, acquired by authors SEMIKRON Slovakia company, were as training, testing validation dataset YOLO network. custom recording system was designed acquire those images. implementation this method increase object success then thereby overall module production.