A Transfer-Learning and Continuous Optimization-Based Framework for Predicting Heat Treatment-Dependent Mechanical Properties of DED-Processed Low-Alloy Steels

Compact and Interpretable Strength-Ductility Prediction of Heat-Treatable Aluminum Alloys Using Physics-Retained Explainable Multi-Target Machine Learning

Predicting yield strength (YS), ultimate tensile strength (UTS), and elongation (El) in heat-treatable aluminum alloys is challenging because composition and heat-treatment parameters interact nonlinearly. This study presents a physics-retained, explainable, and uncertainty-aware multi-target machine-learning framework for simultaneous strength–ductility prediction. A hybrid strategy combining statistical relevance, embedded importance, and metallurgical retention reduced the inputs from 17 to 12 while preserving solution treatment temperature, aging temperature, and aging time. A matched 17-feature comparator used the same outer-validation splits, inner tuning, model families, search space, and budget. Across 25 outer evaluations, the 12-feature pipeline achieved macro-averaged R², NRMSE, and NMAE values of 0.807±0.043, 0.424±0.047, and 0.293±0.033, respectively, compared with 0.800±0.047, 0.431±0.052, and 0.294±0.040 for the comparator. An exploratory post-selection comparison produced a mean macro-R² difference of 0.0068, a corrected 95% interval of [−0.0198, 0.0335], and p=0.602. Because k=12 was selected from the same outer-validation summaries, these results are descriptive rather than confirmatory. The selected pipeline therefore used 29.4% fewer descriptors with similar observed mean performance, although superiority or statistical equivalence was not established. On the row-wise held-out final-test partition, the locked 12-feature ExtraTrees model achieved R² values of 0.857, 0.842, and 0.826 for YS, UTS, and El, respectively. SHAP assigned the largest model attributions to Zn, Cu, and selected heat-treatment conditions, without implying causal metallurgical effects. At a nominal target-wise marginal coverage of 90%, ensemble-conformal coverage was 89.01%, 80.22%, and 91.21% for YS, UTS, and El, respectively; UTS therefore showed under-coverage, whereas YS and El were closer to nominal coverage. The intervals supported uncertainty-aware retrospective prioritization of row-wise held-out conditions. Because external and experimental validation were not performed and performance decreased under composition-group-disjoint validation, the framework should be regarded as an internally evaluated workflow rather than a validated alloy-design tool.

Machine-learning-enabled composition–process co-design of heat-resistant cast aluminum alloys with superior elevated-temperature strength

To address the reliance on trial-and-error methods and the prolonged development cycles inherent in the composition and process design of novel cast aluminum alloys, this study constructed a multi-source feature system integrating alloy composition, physicochemical properties of elements, testing conditions, and process parameters. Employing a three-step feature selection method, a prediction model for high-temperature ultimate tensile strength (UTS) was established with a test set the coefficient of determination of 0.881 and an mean absolute error of 22.639 MPa. Based on this model, a synergistic design of the alloy composition and heat treatment process was conducted by coupling the model with a genetic algorithm (GA), and four novel cast aluminum alloys were experimentally validated. The experimental results indicate that the designed alloys exhibit enhanced elevated-temperature strength compared with the commercial reference alloys. Notably, the ZL-2 alloy demonstrated optimal performance, achieving a UTS of 214.2 MPa when tested at 300 °C after holding at 300 °C for 1 h. Furthermore, SHapley Additive exPlanations (SHAP) analysis revealed significant nonlinear interactions among alloy composition, testing conditions, and process parameters in determining tensile strength. Multiscale microstructural characterization reveals that the exceptional elevated-temperature strength of ZL-2 stems from the synergistic effects of nanoscale Al20Cu2Mn3 and Al2CuMg precipitates, and micron-scale Al3Ti-containing intermetallics. This study demonstrates the application potential of data-driven methods in the composition-process synergistic design of heat-resistant cast aluminum alloys.

A hybrid experimental and machine learning framework for designing and predicting compressive strength of ultra-high-performance concrete

Ultra-high-performance concrete (UHPC) offers exceptional mechanical and durability properties but often relies on quartz powder, raising sustainability and occupational health concerns. This study introduces an integrated experimental-computational framework for predicting the compressive strength of UHPC and developing quartz-free mixtures. Experimentally, the effects of mixing sequence, sand characteristics, superplasticizer chemistry, and curing regime were investigated, leading to a quartz-free UHPC achieving 136 MPa at 28 days under heat-curing. A dataset of 550 UHPC compressive strength records was compiled, incorporating quantitative mix proportions and categorical variables (cement type, superplasticizer base, fiber type, and specimen geometry). Sixty-three machine learning models from tree-based, boosting, and support vector machine families were optimized using seven meta-heuristic algorithms. The Particle Swarm Optimization-tuned XGBoost model achieved the highest prediction accuracy (R2 = 0.897, RMSE = 7.63 MPa), followed by the Differential Evolution-optimized Random Forest (R2 = 0.867, RMSE = 8.70 MPa). SHapley Additive exPlanations (SHAP) analysis identified curing age as the most influential predictor after optimization. The proposed framework enables accurate and interpretable UHPC strength prediction and supports the design of safer and more sustainable quartz-free UHPC with reduced experimental effort.

Influence of Gas Infusion Casting Routes on the Hot Workability and Processing Maps of AZ91 Alloy: Experimentation, Constitutive Modeling, and Machine Learning

Two-Stage Machine Learning for Thermo-Mechanical Properties Optimization of Carbon-Filled Polyimide Composites

Highlights A two-stage ML framework decouples processing and formulation optimization. The two-stage strategy allows concurrent improvement of TS and TC. The CF/SA ratio serves as a composition-derived descriptor for interfacial effects. Feature construction enhances model reliability under small-data constraints. Abstract The rational design of high-performance carbon-filled polyimide (CF/PI) composites is challenged by complex interactions among processing parameters, composition, and interfacial effects. Here, we address thermo-mechanical co-optimization in CF/PI composites through two-stage processing and formulation design. An experimental dataset was employed to construct processing and composition datasets. A CatBoost model was developed to relate hot-pressing parameters to the tensile strength (TS) of pure PI, enabling inverse optimization of processing conditions, with quantitative experimental validation of the predicted processing windows (RMSE = 3.89 MPa). Within the optimized processing window, an XGBoost-based composition-property model was further established to perform high-throughput screening and multi-objective optimization of TS and thermal conductivity (TC). To quantitatively account for interfacial effects, the mass ratio of carbon-filled to sizing agent (CF/SA) was introduced as a composition-derived feature. Model interpretation reveals that CF and graphene positively contribute to TC but negatively affect TS. Notably, formulations with CF/SA > 2 tend to achieve a more favorable TS–TC balance. Experimental validation of model-selected composite formulations confirmed the predicted trends for both TS and TC. These findings suggest that interfacial regulation is a key lever for balancing mechanical strength and thermal transport in CF/PI composites.

Machine Learning-Based Prediction of Tensile Strength and Hardness in GTAW-Welded IS 2062 E250 Mild Steel Under Varying Heat Input

Gas Tungsten Arc Welding (GTAW) joints in structural mild steel exhibit a nonlinear, current-dominated relationship between tensile strength, hardness, and heat input that is difficult to capture using classical linear regression. A 16-run Taguchi L16 experimental design was conducted on IS 2062 Grade E250 mild steel (current: 120–150 A; voltage: 10–16 V), with heat input for each run (1.20–2.40 kJ/mm) calculated using the standard heat-input equation. Six regression algorithms Linear Regression, Decision Tree, Random Forest, Support Vector Regression (SVR), XGBoost, and Artificial Neural Network (ANN) were trained and evaluated using leave-one-out cross-validation (LOOCV), which is statistically appropriate for the limited sample size. XGBoost produced the most accurate tensile-strength predictions (R² = 0.953, RMSE = 19.71 MPa), while the ANN achieved the best hardness predictions (R² = 0.992, RMSE = 0.63 HB). In contrast, linear regression performed poorly for tensile strength (R² = −0.099) because the relationship peaked at 130 A rather than varying monotonically with current. ANOVA identified welding current as the statistically dominant factor influencing both responses (p < 0.001). The findings demonstrate that tree-based and neural-network models substantially outperform conventional linear regression for modelling nonlinear GTAW response surfaces, even with a limited dataset, providing a practical and cost-effective approach for pre-screening welding parameters prior to experimental validation, while highlighting the need for future validation using larger, replicated datasets.