Improved Damage Localization and Quantification of CFRP Using Lamb Waves and Convolution Neural Network
Improved Damage Localization and Quantification of CFRP Using Lamb Waves and Convolution Neural Network
复制标题
使用兰姆波和卷积神经网络改进 CFRP 的损伤定位和量化
DOI：
10.1109/jsen.2019.2908838
复制
发表时间：
2019-07-15
影响因子：
4.3
通讯作者：
Sui, Qingmei
中科院分区：
文献类型：
--
作者：
Su, Chenhui;Jiang, Mingshun;Sui, Qingmei
本文提出了一种利用兰姆波和卷积神经网络算法同时定位和量化复合材料板损伤的新方法。通过仿真研究了兰姆波与不同程度损伤的相互作用。兰姆波实验采用四块压电晶片组成的方形阵列进行。首先，传感器阵列采集兰姆波响应信号作为训练数据，然后采用小波变换的方法对其进行去噪。在此过程中，对复合材料造成的损伤可以通过质量块来实现。此外，应用傅里叶变换来提取信号所显示的特征。然后，将具有损伤特征的频谱和相应的损伤模式分别作为卷积神经网络的输入和输出，从而建立损伤识别模型。最终对192个样本中的191个样本进行了准确识别，正确识别率为99.5%，证明了卷积神经网络可以建立信号与损伤之间复杂的映射关系，进一步证明该方法具有较高的准确率，在复合板损伤的同时定位和定量识别方面具有巨大的潜力。
A novel method is proposed in this paper for simultaneously locating and quantifying damage in composite plates by employing Lamb waves and the algorithm of convolution neural network. The interaction between Lamb wave and damage of different degrees is also studied by simulation. The experiments on Lamb wave are carried out by employing a square array which is composed of four piezoelectric wafers. First of all, the sensor array collects response signals of Lamb wave as training data, and then de-noises them adopting the method of the wavelet transform. In the process, the damage caused to the composite can be realized through mass blocks. Besides, the Fourier transform is applied for the extraction of the characteristics shown by the signals. After that, the spectrum with the characteristics of damage and corresponding damage modes are employed as input and output of the convolutional neural network, respectively, and accordingly, the model of damage identification is established. Finally, 191 samples (from a total of 192) were identified accurately and the correct recognition rate achieved is 99.5%, which consequently demonstrates that the convolution neural network can be employed to establish the complex mapping relationship between signal and damage, and further proves that the proposed method performs well in high accuracy and great potential in simultaneous localization and quantitative identification of damage existing in composite plate.