Search

This article presents a classification of Acoustic Emission (AE) signals from AlSi10Mg specimens produced via Selective Laser Melting (SLM). Tensile tests characterized the mechanical properties of specimens printed in different orientations (X, Y, Z, 45°). Initially, a study quantified damage modes based on the stress-strain curve and cumulative AE energy. AE signals for each specimen (X, Y, 45°, Z), across deformation stages (elastic and plastic), and damage modes were analyzed using continuous wavelet transform to extract time-frequency features. A novel convolutional neural network, based on artificial bee colonies and fuzzy C-means, was developed for scalogram classification. Data augmentation with Gaussian white noise enhanced the approach. Cross-validation ensured robustness against overfitting and suboptimal local maxima. Evaluation metrics, including the confusion matrix, precision-recall curve, and F1 score, demonstrated the algorithm's high accuracy of 92.6%, precision-recall curve of 92.5%, and F1 score of 92.5% for AE signals based on printing direction (X, Y, 45°, Z). The study highlighted the potential for improving AE signal classification related to elastic and plastic deformation stages with 100% accuracy. For damage modes, the algorithm achieved a confusion matrix accuracy of 90.6%, a precision-recall curve of 90.4%, and an F1 score of 90.5%. This approach demonstrates high accuracy in classifying AE signals across different printing orientations, deformation stages, and damage modes of AlSi10Mg specimens manufactured through SLM. [ABSTRACT FROM AUTHOR]

A multiparameter approach is preferred while utilizing Acoustic Emission (AE) technique for mechanical characterization of composite materials. It is essential to utilize a statistical parameter, which is independent of the sensor characteristics, for this purpose. Thus, a new information–theoretics parameter, Lempel–Ziv (LZ) complexity, is used in this research work for mechanical characterization of Carbon Fibre Reinforced Plastic (CFRP) composites. CFRP specimens in plain weave fabric configurations were tested and the acoustic activity during the loading was recorded. The AE signals were classified based on their peak amplitudes, counts, and LZ complexity indices using k-means++ data clustering algorithm. The clustered data were compared with the mechanical results of the tensile tests on CFRP specimens. The results show that the clustered data are capable of identifying critical regions of failure. The LZ complexity indices of the AE signal can be used as an AE descriptor for mechanical characterization. This is validated by studying the clustered signals in their time–frequency domain using wavelet transform. Finally, a neural network framework based on SqueezeNet was trained using the wavelet scalograms for a quantitative validation of the data clustering approach proposed in this research work. The results show that the proposed method functions at an efficiency of more than 85% for three out of four clustered data. This validates the application of LZ complexity as an AE descriptor for AE signal data analysis. [ABSTRACT FROM AUTHOR]

In this research paper, the acoustic emission technique and a deep learning framework based on two types of pre-trained CNN models (alexNet and squeezeNet) and a new model are proposed to characterize and classify the mechanical behavior of AlSi10Mg components. Specimens are built in a Selective Laser Melting machine with different bed orientations along X, Y, Z, and 45 degrees. Tensile tests are performed, and AE signals are recorded from these tests. To characterize the elastic and plastic deformation stages, a time-frequency domain analysis was performed using CWT-based spectrograms. Three different categories of damage classification strategies were implemented, and CNN models were trained for each strategy. CNN models including AlexNet, SqueezeNet, and the new model were used. Several training modes were performed to determine the CNN model that can accurately classify AE data. Understanding the minimum set of AE signals needed to train the CNN while having 100% accuracy and understanding the parameters affecting the accuracy of a CNN and the training time for the efficient classification of AE signals are the main objectives of this work. The results obtained demonstrated that the new simplified CNN model proposed can accurately classify the AE signals in a short time compared to AlexNet and SqueezeNet. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

In this research work, a deep Convolutional Neural Network (CNN) was trained for image-based Acoustic Emission (AE) waveform classification. AE waveforms from different damage modes of Carbon Fibre Reinforced Polymer (CFRP) composites were used to train the CNN for online damage monitoring. Spectrograms of AE Waveforms from four different damage modes, matrix cracking, delamination, debonding, and fibre breakage, were obtained in their Mel scale and used as the training data and test data for the CNN. The overall prediction accuracy of the CNN is 97.9%, while the fibre breakage and delamination events were able to be predicted with 100% accuracy. Then this pre-trained CNN is used for online damage monitoring of mode I delamination test of CFRP specimens. AE waveforms generated during the mode I test are classified using the trained CNN and the results are analysed in terms of the classified AE descriptors. The classified AE descriptors proved to identify the occurrences of different damage modes, thereby validating the damage classification accuracy of the CNN. [ABSTRACT FROM AUTHOR]