钢铁材质无损检测中神经网络聚类方法的应用

Application of Clustering Neural Network Method in Nondestructive Testing of Quality of Material for Steel and Iron

针对钢铁材质质量的检测问题,依据电磁无损检测原理,结合聚类分析技术,利用神经网络聚类学习方法,通过实验研究,提出了一种新的自适应模式识别技术。试验结果表明,该技术比传统的电磁无损检测准确度高,误判率低。

This paper uses a clustering neural network learning method to resolve the problem of testing on the quality of steel and iron, with the theory of electromagnetic nondestructive testing, integrating the technique of clustering. Experimental studies show that this method used as an adapting mode of pattern recognition technique has a better mode classification capability as compared to conventional nondestructive testing method.