Barile Claudia, Casavola Caterina, Pappalettera Giovanni, Kannan Vimalathithan Paramsamy
Dipartimento di Meccanica, Matematica e Management, Politecnico di Bari, Via E. Orabona 4, 70125 Bari, Italy.
Materials (Basel). 2022 Jun 23;15(13):4428. doi: 10.3390/ma15134428.
In this study, the damage evolution stages in testing AlSi10Mg specimens manufactured using Selective Laser Melting (SLM) process are identified using Acoustic Emission (AE) technique and Convolutional Neural Network (CNN). AE signals generated during the testing of AlSi10Mg specimens are recorded and analysed to identify their time-frequency features in three different damage evolution stages: elastic stage, plastic stage, and fracture stage. Continuous Wavelet Transform (CWT) spectrograms are used for the processing of the AE signals. The AE signals from each of these stages are then used for training a CNN based on SqueezeNet. Moreover, k-fold cross validation is implemented while training the modified SqueezeNet to improve the classification efficiency of the network. The trained network shows promising results in classifying the AE signals from different damage evolution stages.
在本研究中，采用声发射（AE）技术和卷积神经网络（CNN）识别了使用选择性激光熔化（SLM）工艺制造的AlSi10Mg试样在测试过程中的损伤演化阶段。记录并分析了AlSi10Mg试样测试过程中产生的AE信号，以识别其在三个不同损伤演化阶段的时频特征：弹性阶段、塑性阶段和断裂阶段。连续小波变换（CWT）频谱图用于处理AE信号。然后，将这些阶段中每个阶段的AE信号用于基于SqueezeNet训练CNN。此外，在训练改进的SqueezeNet时实施k折交叉验证，以提高网络的分类效率。训练后的网络在对来自不同损伤演化阶段的AE信号进行分类方面显示出有前景的结果。
