一种基于卷积神经网络的电涡流金属辨识方法

为实现对主要金相组织同为铁素体和珠光体的3种碳素结构钢的辨识,提出一种基于卷积神经网络的金属辨识方法。卷积神经网络可以很好地处理环境信息复杂、推理规则不明确和样品本身有缺陷情况下的分类,利用涡流无损检测技术和卷积神经网络算法搭建了该金属辨识平台,首先在涡流传感器的工作频率范围内随机选取8个高频点,并通过该传感器分别采集各个频点下金属的信息;然后通过傅里叶变换、坐标变换等数据处理使得每种金属的信息图像化;最终通过卷积神经网络训练来获得辨识模型。结果表明,该方案对比传统方式可在不损伤金属的情况下识别金属;对比现有的BP神经网络算法(86.20%),对3种金属的正确识别率都达到了92.33%。

Metal type identification method based on convolutional neural network and eddy current

In order to identify three types of carbon structural steels whose metallographic structures are ferrite and pearlite. This paperproposes a metal identification method based on convolutional neural network. Convolutional neural networks can efficiently implementclassification with complex environmental information, ambiguous inference rules, and flawed samples. The metal identification platformwas built based on eddy current non-destructive testing technology and convolutional neural network. First, 8 high-frequency points arerandomly selected from the bandwidth of the eddy current sensor, and the metal information that under each frequency point is separatelycollected by this eddy current sensor. Then, this information is imaged through data processing such as Fourier transform and coordinatetransformation. Finally, the identification model is obtained by convolutional neural network. The results show that the proposed schemecan identify metals without damaging the metal compared to the traditional method. The accuracy of the CNN model for all three metalsincreased to 92. 33%, which is superior to the BP neural network (86. 20%).