The use of neural network technologies in the design of printed circuit boards
A.V. Arkhipov, K.A. Muravyov, A.A. Solodnjakov, I.S. Potanin · Neurocomputers · 2024
Problem setting. The production process of any electronic device currently involves a large number of both software and hardware. In the manufacture of electronic products, elements are automatically installed on the board using robotic devices. Along with the installation of components, the quality of the PCB design is also of serious importance. Quality control at any stage of production is assigned to a person, which significantly reduces not only productivity, but also the quality of rejection. All this leads to the need to develop modern digital methods and technologies for automatic control of components of electronic products using artificial intelligence. Target. The purpose of this work is to study methods for identifying defective areas of a printed circuit board topology that arise during its production, as well as the possibility of adjusting production line control algorithms. Results. An analysis of modern literary and Internet sources was carried out, during which the advantages and disadvantages of using neural networks in the design of printed circuit boards were determined; an algorithm was also proposed for developing a technique for monitoring the topology of a printed circuit board; a program for applying the image analysis procedure was implemented and the software package was tested. As part of the work, it is proposed to monitor the line in real time, which makes it possible to adjust the indicators “online” by entering possible causes into the database, subsequent analysis and elimination. Practical significance. The proposed solution will primarily improve the quality and increase the speed of modern printed circuit board production. The main indicator that it can provide is a reduction in the defect rate.