Yiming Zhang

Metallographic image segmentation underpins automated metallographic analysis, yet pixel-level annotation is costly. Metallographic microstructures exhibit dramatic size differences, including cross-scale structures such as large-scale matrix phases, grain boundary cementite networks, and acicular Widmanstätten structures. Existing feature extraction modules cannot balance the semantic integrity of large regions and the fine details of microstructures, causing missed small microstructures and blurred segmentation boundaries. Current semi-supervised methods only impose consistency constraints on perturbed input images at the final prediction output, ignoring multi-scale semantic features from decoder upsampling stages. This leads to noisy supervision signals, low-quality pseudo-labels, and poor generalization. To address these issues, this paper proposes a semi-supervised metallographic image segmentation model, EISC, integrating MT cross-network scale feature extraction and decoder multi-scale consistency constraints. It adaptively fuses multi-receptive-field features and introduces a regularization term to maintain the semantic consistency of multi-scale decoder outputs, improving pseudo-label quality. Comparative and ablation experiments verify that EISC effectively enhances the segmentation accuracy and robustness of metallographic images.

Numerical simulation is a vital tool in the development of FeCrAl alloy cladding tubes, with its reliability closely tied to the predictive accuracy of the thermal deformation constitutive model used. In this study, hot compression tests on 0Cr23Al5 alloy were conducted using a Gleeble-3800 thermal compression testing machine (Dynamic Systems Inc., located in Albany, NY, USA), across a temperature range of 850–1050 °C and a strain rate range of 0.1–10 s⁻¹. Based on the data obtained, both the Arrhenius constitutive model and the artificial neural network (ANN) model were developed. The ANN model demonstrated significantly superior predictive accuracy, with an average absolute relative error (AARE) of only 0.70% and a root mean square error (RMSE) of 1.99 MPa, compared to the Arrhenius model (AARE of 4.30% and RMSE of 14.47 MPa). Further validation via the VUHARD user subroutine in ABAQUS revealed that the ANN model has good applicability and reliability in numerical simulations, with its predicted flow stress showing high consistency with the experimental data. The ANN model developed in this study can effectively predict the rheological stress of FeCrAl alloys during hot deformation. It provides methodological support for high-fidelity constitutive modeling of the flow stress of FeCrAl alloys and offers a reliable constitutive model for simulating the thermomechanical load response behavior of FeCrAl alloys.

MAX phases, a family of ternary layered carbide and nitride compounds characterized by their atomic-scale hybridization of metallic and covalent-ionic bonding, have emerged as potential materials for ...

Navigating materials performance databases efficiently is a persistent challenge in materials science and engineering, particularly in the selection of alloy materials. While recommendation systems ad-dress information overload, traditional approaches relying on historical user data face limitations such as data sparsity and cold-start issues. This study presents a novel recommendation model that integrates domain-specific knowledge graphs with large language models (LLMs) to enhance recommendation accuracy in alloy material selection. A knowledge graph for alloys is developed, encapsulating technical material data and relationships to improve retrieval and recommendation outcomes. LLMs are employed for label clustering and natural language-based instruction-following to craft user profiles and enhance data representation. Two graph enhancement strategies, integrated with attention mechanisms, effectively capture user preferences. Experimental results on a ferroalloy dataset demonstrate the model's superior performance compared to base-line methods, significantly addressing data sparsity while offering personalized, accurate recommendations. This research bridges the gap between knowledge graphs and LLMs in recommendation systems, contributing a flexible, intelligent solution to streamline material selection processes.

The high thermal conductivity of SiC single crystals makes them crucial in fields such as renewable energy and aerospace. Nevertheless, owing to the phonon scattering resulting from crystal boundary, the reported thermal conductivity of SiC ceramic is always well below the intrinsic value. For the SiC ceramic derived from β-SiC (3 C-SiC) starting powder, the β→α phase transformation (i.e. 3 C→4 H) happened imposes significant influences on its microstructure. Therefore, systematic studies of contributions from hetero-/homo- phase boundaries are necessary for understanding the thermal conductivities of resulting SiC ceramic, providing further guidance to the phase transformations control. In this work, the thermal conductivities of both β/β and α/α homophase boundary, as well as β/α heterophase boundary, are systematically investigated. Further, it is found that the highest thermal conductivity is reached at sintering temperature of around 2000 °C, where about 90% of SiC has been transformed from β to α content.

Silicon carbide ceramics are widely used within various applications, including mechanical, chemical, aerospace and military; where the fracture toughness plays a crucial role. From the processing perspectives, the fracture toughness is controlled by the combination of starting phases and sintering conditions (including additives, atmosphere, temperature and pressure). However, the interplay of these factors makes the forward predictions of fracture toughness untreatable neither through experimentation nor physical modeling; not mention to the reverse estimations of optimal processing parameters. In this work, a data-driven strategy was proposed that firstly to predict the fracture toughness from processing parameters; and then to explore certain parameters that have large impacts on the fracture toughness. From running four different machine learning (ML) algorithms on a well-established dataset of SiC sintering recipe, it was found that the eXtreme Gradient Boosting (XGBoost) model possess the best performance with accuracy up to 88%. Further, the feature importance scores revealed that the sintering temperature and the types of sintering additives show their significant influence on fracture toughness. It was found that the sintering temperature is the most critical factor affecting the obtained fracture toughness of SiC, where the optimum temperature range is of 1800 °C–2000 °C; and also, the sintering additives of Al and Al₂O₃ have great influences on the obtained fracture toughness, where the optimum range of their mass fraction within the whole additives is 3–8 wt%. Finally, the developed model shows its capability to propose sintering strategy for the preparation of SiC ceramics with target fracture toughness.