Paper:
Views over last 60 days: 460
Inspection System of Soldering Joint on Printed Circuit Board by Using Neural Network
Shunichiro Oe*, Kennichi Kaida**, Daisuke Nagai**,
Mituo Nakamura**, Tomohiro Kimura** and Koichi Kameyama**
*Faculty of Engineering, University of Tokushima, 2-1 Minamijosanjima, Tokushima, 770 Japan
**Matsushita Kotobuki Electronic Ind. Co., Ltd., Kawauchi-cho, Onsen-gun, Ehime, 791-03 Japan
Received:February 3, 1995Accepted:February 17, 1995Published:June 20, 1995
Keywords:Inspection system, Printed circuit board, Soldering joint, Feature extraction, Neural network
Abstract
This paper deals with a new inspection system of soldering joint on printed circuit board by using neural network. A sensor unit of this system consists of a semiconductor laser unit, four PSDs, and a pin photo-diode. We can obtain four types of images which are called height image, PSD brightness image, vertical image and vector image, by using four sensor units. We extract the features which show the state of soldering joint from these images and develop an inspection system using the neural networks constructed for the features and the state of soldering joint.
Cite this article as:S. Oe, K. Kaida, D. Nagai, M. Nakamura, T. Kimura, and K. Kameyama, “Inspection System of Soldering Joint on Printed Circuit Board by Using Neural Network,” J. Robot. Mechatron., Vol.7 No.3, pp. 225-229, 1995.Data files:
