Artificial Neural Network for Technical Diagnostics of Control Systems by Thermography

The paper deals with the problem of testing and technical diagnostics of the control systems in electronic devices by means of infrared thermography. The methodology of technical state noncontact monitoring and failure analysis is presented. An algorithm for measuring the temperature field of the elements surface and supporting decision procedure on the operability implemented in the information-measuring system is described. The different mathematic models of electronic devices thermal performance are considered. It is shown that for microelectronic devices it is sufficient to use a two-dimensional mathematical model of the thermal field on the surface. To compare the calculated thermal fields and measured temperatures, it is suggested to use an artificial neural network that is trained in the process of functioning of the information-measuring system. The experiments were carried out on the recognition of defects and failures in microelectronic devices of control systems.