PCB Testing Using Infrared Thermal Signatures

Abstract

A printed circuit board (PCB) testing method using infrared thermal signatures is presented. The concept of thermal signature for PCBs is introduced. Based on this concept, the testing method is able to classify the integrated circuits (ICs) on a PCB into a number of classes (e.g. functional - fault free, non-functional - faulty and less reliable - functional circuits with high current consumption). According with thermal signature of each IC on the PCB, the PCBs can be also classified in the same number of classes. The classification system is a feed-forward neural network that learns and classifies the information achieved from the infrared image