View Video Presentation: https://doi.org/10.2514/6.2022-1424.vid This work discusses new methodologies for identifying the grain boundaries in color imagesof metallic microstructures and the quantification of their grain topology. Grain boundarieshave a large impact on the macro-scale material properties. Particularly, this work employs theexperimental microstructure data of Titanium-Aluminum alloys, which can be used for variousaerospace components owing to their outstanding mechanical performance in elevated temper-atures. The grain topology of these metallic microstructures is quantified using the concept ofshape moment invariants. In order to capture the grains using the shape moment invariants,it is necessary to identify the grain boundaries and separate them from their respective grains.We present two methodologies to detect the grain boundaries. The first method is the tolerance-based neighbor analysis. The second method focuses on creating three-dimensional space ofpixel intensity values based on the three color channels and measuring the Euclidean distanceto separate different grains. Additionally, since the grain boundaries may not possess the samematerial properties as the grain itself, this work investigates the effect of including the grainboundaries when determining the homogenized material properties of the given microstruc-ture. To generate adequate statistical information, microstructures are reconstructed fromthe experimental data using the Markov Random Field (MRF) method. Upon separating thegrains, we use the shape moment invariants to quantify the shapes of different grains. Using theshape moment invariants and the experimental material property values, three neural networkfunctions are developed to investigate the effects of grain boundaries on material propertypredictions

Thermal barrier coating, a widely used advanced manufacturing technique in various industries, provides thermal insulation and surface protection to a substrate by spraying melted coating materials on to the surface of the substrate. As the melted coating materials solidify, it creates microstructures that affect the coating quality. An important coating quality assessment metric that determines its effectiveness is porosity, the quantity of microstructures within the coating. In this article, we aim to build a novel algorithm to determine the microstructures in a thermal barrier coating, which is used to calculate porosity. The hybrid approach combines the efficiency of thresholding-based techniques and the accuracy of convolutional neural network (CNN) based techniques to perform a binary semantic segmentation. We evaluate the performance of the proposed hybrid approach on coating images generated from two different types of coating powders. These images exhibit various texture features. The experimental results show that the proposed hybrid approach outperforms the thresholding-based approach and the CNN-based approach in terms of accuracy on both types of images. In addition, the time complexity of the hybrid approach is also greatly optimized compared to the CNN-based approach.

This work trained convolutional neural networks (CNNs) to identify microstructure characteristics and then provide a measurement of porosity in the topcoat layer (TCL) of thermal barrier coatings using digital images captured by an inverted optical microscope. Porosity in a coating is related to thermal compensation and the longevity of the parts protected by the coating. The approach employs pixel-wise classification and transfer learning accompanied by data augmentation to expedite the training process and increase classification accuracy. The authors evaluate CNN-based models globally on the entire TCL of 159 high resolution raw images of three types (Type A, B, C) that are generated from three different types of powders and exhibit different physical and visual properties. The experimental results show that the CNN-based models outperform adaptive local thresholding-based porosity measurement (ALTPM) approach that this paper proposed in the previous work by 7.76%, 10.82%, and 12.10% respectively for Type A, Type B, and Type C images in terms of the average classification accuracy.