摘要
提出一种基于自适应共振理论（ＡｄａｐｔｉｖｅＲｅｓｏｎａｎｃｅＴｈｅｏｒｙ）神经网络的焊缝检测算法，其基本原理是把焊缝横截面方向上的灰度分布归结为若干种空间模式，并使之记忆在ＡＲＴ神经网络中的典型空间模式进行匹配程度检验，根据模式分布情况确定出焊缝位置。它是一种能够在强烈的噪声环境中正确地检测出焊缝位置的新的焊缝检测算法。本算法也为在强噪声环境中检测特定的空间模式提供了一条新思路。
This article introduces a welding seam detectig algorithm based on the ART(Adaptive Resonance Theory) artificial neural network.The basic principle of the algorithm is to sum up the grey level distributions on the transversal direction of the seam into several typical space patterns and then match them with the patterns memorized in the LTM(Long Time Memory) of the ART nenral network.The seam position can be determined according to the pattern distributions.It is a novel method for welding seam visual tracking which can inhibit strong noises and work correctly in a very noisy circumsumstance.
出处
《机械工程学报》
EI
CAS
CSCD
北大核心
1994年第2期93-98,共6页
Journal of Mechanical Engineering
关键词
焊缝跟踪
模式识别
人工神经网络
Welding seam tracking Pattern recognition Artificial neural network
