Accurate identification and measurement of the precipitate area by two-stage deep neural networks in novel chromium-based alloys.

The performance of advanced materials for extreme environments is underpinned by their microstructure, such as the size and distribution of nano- to micro-sized reinforcing phase(s). Chromium-based superalloys are a recently proposed alternative to conventional face-centred-cubic superalloys for high-temperature applications, e.g., Concentrated Solar Power. Their development requires the determination of precipitate volume fraction and size distribution using Electron Microscopy (EM), as these properties are crucial for the thermal stability and mechanical properties of chromium superalloys. Traditional approaches to EM image processing utilise filtering with a fixed contrast threshold, leads to weak robustness to background noise and poor generalisability to different materials. It also requires an enormous amount of time for manual object measurements on large datasets. Efficient and accurate object detection and segmentation are therefore highly desired to accelerate the development of novel materials like chromium-based superalloys. To address these bottlenecks, based on YOLOv5 and SegFormer structures, this study proposes an end-to-end, two-stage deep learning scheme, DT-SegNet, to perform object detection and segmentation for EM images. The proposed approach can thus benefit from the training efficiency of CNNs at the detection stage (i.e., a small number of training images required) and the accuracy of the ViT at the segmentation stage. Extensive numerical experiments demonstrate that the proposed DT-SegNet significantly outperforms the state-of-the-art segmentation tools offered by Weka and ilastik regarding a large number of metrics, including accuracy, precision, recall and F1-score. This model forms a useful tool to aid alloy development microstructure examinations, and offers significant advantages to address the large datasets associated with high-throughput alloy development approaches.

Data on a new beta titanium alloy system reinforced with superlattice intermetallic precipitates.

The data presented in this article are related to the research article entitled "a new beta titanium alloy system reinforced with superlattice intermetallic precipitates" (Knowles et al., 2018) [1]. This includes data from the as-cast alloy obtained using scanning electron microscopy (SEM) and x-ray diffraction (XRD) as well as SEM data in the solution heat treated condition. Transmission electron microscopy (TEM) selected area diffraction patterns (SADPs) are included from the alloy in the solution heat treated condition, as well as the aged condition that contained < 100 nm B2 TiFe precipitates [1], the latter of which was found to exhibit double diffraction owing to the precipitate and matrix channels being of a similar width to the foil thickness (Williams and Carter, 2009) [2]. Further details are provided on the macroscopic compression testing of small scale cylinders. Of the micropillar deformation experiment performed in [1], SEM micrographs of focused ion beam (FIB) prepared 2 µm micropillars are presented alongside those obtained at the end of the in-situ SEM deformation as well as videos of the in-situ deformation. Further, a table is included that lists the Schmidt factors of all the possible slip systems given the crystal orientations and loading axis of the deformed micropillars in the solution heat treated and aged conditions.

Data on a Laves phase intermetallic matrix composite in situ toughened by ductile precipitates.

The data presented in this article are related to the research article entitled "Laves phase intermetallic matrix composite in situ toughened by ductile precipitates" (Knowles et al.) [1]. The composite comprised a Fe2(Mo, Ti) matrix with bcc (Mo, Ti) precipitated laths produced in situ by an aging heat treatment, which was shown to confer a toughening effect (Knowles et al.) [1]. Here, details are given on a focused ion beam (FIB) slice and view experiment performed on the composite so as to determine that the 3D morphology of the bcc (Mo, Ti) precipitates were laths rather than needles. Scanning transmission electron microscopy (S(TEM)) micrographs of the microstructure as well as energy dispersive X-ray spectroscopy (EDX) maps are presented that identify the elemental partitioning between the C14 Laves matrix and the bcc laths, with Mo rejected from the matrix into laths. A TEM selected area diffraction pattern (SADP) and key is provided that was used to validate the orientation relation between the matrix and laths identified in (Knowles et al.) [1] along with details of the transformation matrix determined.