Search Results (2)

This work describes a novel methodology for the quality assessment of a Fused Filament Fabrication (FFF) 3D printing object during the printing process through AI-based Computer Vision. Specifically, Neural Networks are developed for identifying 3D printing defects during the printing process by analyzing video captured from the process. Defects are likely to occur in 3D printed objects during the printing process, with one of them being stringing; they are mostly correlated to one of the printing parameters or the object’s geometries. The defect stringing can be on a large scale and is usually located in visible parts of the object by a capturing camera. In this case, an AI model (Deep Convolutional Neural Network) was trained on images where the stringing issue is clearly displayed and deployed in a live environment to make detections and predictions on a video camera feed. In this work, we present a methodology for developing and deploying deep neural networks for the recognition of stringing. The trained model can be successfully deployed (with appropriate assembly of required hardware such as microprocessors and a camera) on a live environment. Stringing can be then recognized in line with fast speed and classification accuracy. Furthermore, this approach can be further developed in order to make adjustments to the printing process. Via this, the proposed approach can either terminate the printing process or correct parameters which are related to the identified defect. Full article

In the present study, data generated from nanoindentation were used in order to reconstruct the surface constituent phases of mortar grids through machine learning algorithms. Specifically, the K-Means algorithm (unsupervised learning) was applied to two 49 measurement (7 × 7) datasets with information about the modulus (E) and hardness (H) in order to discover the underlying structure of the data. The resulting clusters from K-Means were then evaluated and values range assigned so as to signify the various constituent phases of the mortar. Furthermore, another dataset from nanoindentation containing information about E, H, and the surface colour of the measured area (obtained from an optical microscope) was used as the training set in order to develop a random forests model (supervised learning), which predicts the surface colour from the E and H values. Colour predictions on the two 7 × 7 mortar grids were made and then possible correlations between the clusters, signifying constituent phases, and the predicted colours were examined. The groupings of data in the clusters (phases) corresponded to a unique surface colour. Finally, the constituent phases of the mortar grids were reconstructed in contour plots by assigning the corresponding cluster of the K-Means algorithm to each measurement (position in the grid). Full article