Artificial Neural Networks Framework for Detection of Defects in 3D-Printed Fiber Reinforcement Composites

One of the major challenges in applying tomography methods for detecting defects in composite materials is the large image datasets generated during imaging, which require significant effort for the detection of damage. Machine-learning (ML) methods require a large training dataset and can be efficient in processing tomography datasets for defect detection. Methods need to be developed for processing images to train the ML algorithms, which is the focus of the present work. An additive manufactured fiber reinforced composite material is imaged using a micro-CT scan to generate an image set for defect detection. The microstructures are processed using the binarized statistical image features (BSIF) method for compression without compromising the desired information about defects. The result shows that the convolutional neural network model has a mean square error of 0.001 in fiber orientation prediction, and a scheme has been developed for defect detection based on the predictions obtained from the ML models.

Automated summary

The study focuses on developing methods for processing images to train machine learning algorithms to handle tomography datasets for defect detection in composite materials. A micro-CT scan is used to image an additive manufactured fiber reinforced composite material, and the microstructures are processed using the BSIF method for compression. The study shows that the convolutional neural network model performs well in fiber orientation prediction.