In many instances, the electronic state of an electronic circuit card contains insufficient information for correct fault diagnosis. Infrared thermal images, captured during the initial warmup of an electronic circuit card, are employed to enhance the available information and to assist the technician in performing the fault diagnosis. This system has proven beneficial for radar and microwave technologies where probing changes the electronic response of the circuit and signal levels can be extremely small. The development of this system has required the integration of technologies from a diversity of fields including image capture, image compression, image enhancement, neural networks, genetic algorithms, thermodynamics, and automatic test equipment (ATE) software. These technologies and preliminary system performance are discussed.<<ETX>>
[1]
P. Werbos,et al.
Beyond Regression : "New Tools for Prediction and Analysis in the Behavioral Sciences
,
1974
.
[2]
D. E. Goldberg,et al.
Genetic Algorithms in Search
,
1989
.
[3]
D. F. Specht,et al.
Probabilistic neural networks for classification, mapping, or associative memory
,
1988,
IEEE 1988 International Conference on Neural Networks.
[4]
E. Patrick,et al.
Fundamentals of Pattern Recognition
,
1973
.
[5]
David E. Goldberg,et al.
Genetic Algorithms in Search Optimization and Machine Learning
,
1988
.
[6]
Chi Hau Chen,et al.
Statistical Pattern Recognition.
,
1973
.