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