Thermal signature for solder defect detection using a neural network approach Conference Paper

abstract

• This paper describes a neural network approach to detecting solder defects on printed circuit boards when using thermal signature. Solder defects such as open and insufficient solder was investigated. A multi-layer neural network with multiple inputs and a single output was utilized. A back-propagation algorithm was utilized within the network. Computer mouse printed circuit boards with known introduced solder defects and amounts of solder were used for experiments. Thermal images were acquired as the boards were powered up. A Visual Basic program was written to retrieve temperature data from an encoded image file format. Afterwards, MATLAB neural network routines were applied to analyze the data. The neural network was able to diagnose solder defects on two of five resistors with 91.1% accuracy, and on three of five resistors with 61.1% accuracy.

name of conference

• Thermosense XXIII

authors

• Hsieh, Sheng-Jen

published proceedings

• THERMOSENSE XXIII

author list (cited authors)

• Hsieh, S., & Calderon, A.

citation count

• 3

complete list of authors

• Hsieh, SJT||Calderon, A

editor list (cited editors)

• Rozlosnik, A. E., & Dinwiddie, R. B.

publication date

• March 2001

publisher

• SPIE, the international society for optics and photonics  Publisher

published in

• Proceedings of SPIE  Journal

keywords

• Neural Network
• Printed Circuit Board
• Solder Defect
• Thermal Signature

Digital Object Identifier (DOI)

• 10.1117/12.421049

International Standard Book Number (ISBN) 10

• 0-8194-4055-8

start page

• 636

end page

• 643

volume

• 4360

URL

• http://dx.doi.org/10.1117/12.421049