摘要
针对钢铁件材质缺陷检测问题,介绍了基于初始幅值磁导率法的一种电磁无损检测方法。为了提高检测的效率和准确率,将RBF神经网络设计成为新的识别系统通过对钢铁件样本数据进行的仿真测试表明,RBF神经网络系统识别效率较高且可靠,为电磁无损检测提供了一个新的思路。
Aiming at the detection of steel and iron parts's crack, an electromagnetic nondestructive testing method based on the principle of initial increment permeability is introduced in this paper. To improve efficiency and accuracy of the detection, we use RBF neural network as a new recognizing system. It is shown by the numerical simulation of the data samples that the RBFNN system can identify the crack of steel and iron parts correctly, and also it has high efficiency. And this method presents a new feasible and effective way to research electromagnetic nondestructive testing system.
出处
《计算机与数字工程》
2009年第12期167-169,174,共4页
Computer & Digital Engineering
关键词
无损检测
RBF神经网络
钢铁缺陷检测
nondestructive testing, RBF neural network, crack testing of the steel materiall