Thermal energy emission diagnostics enhancement to the advanced power supply test system

The Advanced Power Supply Test Station (APSTS) is a system used for automated power supply testing. The capabilities of this system have been enhanced by the development and integration of a Thermal Diagnostic Instrument to provide thermal energy emission diagnostics. Thermal images of a power supply circuit board are acquired at intervals during initial power-on. A projective mapping technique based on geometric image warping is used to locate individual components in these images given arbitrary alignment between the board and the imager. A unique energy ratio calculation is used to normalize the effects of emissivity in the measured thermal values for each component. A fuzzy logic expert system and an artificial neural network are used to compute likelihood of failure estimates from these energy ratio values. Fuzzy logic membership functions are based on experimental data from normal and failed circuit boards, and rules are based on the knowledge of the board circuits.

[1]  Michel Defrise,et al.  Symmetric Phase-Only Matched Filtering of Fourier-Mellin Transforms for Image Registration and Recognition , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  L. G. Allred,et al.  Thermal imaging is the sole basis for repairing circuit cards in the F-16 flight control panel , 1996, Conference Record. AUTOTESTCON '96.

[3]  G. E. Kelly,et al.  A system for fault diagnosis in electronic circuits using thermal imaging , 1992, Conference Record AUTOTESTCON '92: The IEEE Systems Readiness Technology Conference.

[4]  J. Lopez,et al.  An artificial neural network printed circuit board diagnostic system based on infrared energy emissions , 1991, Conference Record AUTOTESTCON '91 IEEE Systems Readiness Technology Conference Improving Systems Effectiveness in the Changing Environment of the '90s.

[5]  R. C. Berkan,et al.  Fuzzy systems design principles - building fuzzy IF-THEN rule bases , 1997 .