Answers are grounded in this paper and cite their sources.
Demonstrates improved performance in SiC-reinforced Ti-6Al-4 V composites, suggesting a reliable optimization method.
Ti-6Al-4 V metal matrix composites (MMCs) have gained significant relevance in advanced automotive systems due to their exceptional strength-to-weight ratio, thermal stability, and wear resistance. Existing studies on MMCs, including stir-casting and data-driven models like KNN, ANN, SVM, and DNN, exhibit limited generalization, weak process–structure–property coupling, and lack mechanistic validation, thereby hindering reliable optimization. The present study introduces a hybrid Mechanistic Physics-Embedded Neural Operator (MPeNO) combined with Physics-Guided Adaptive Differential Evolution (PG-ADE) to enable accurate prediction and multi-objective optimization of SiC-reinforced Ti-6Al-4 V MMCs. The framework aims to establish a physics-consistent predictive–optimization pipeline, with objectives focused on maximizing tensile strength, yield strength, hardness, and wear stability while minimizing density and processing energy. The novelty of this work lies in embedding Hall–Petch grain-size strengthening, Orowan looping, load transfer, α/β phase kinetics, and thermal-softening equations directly into the neural-operator loss terms, enabling predictions that adhere to metallurgical laws. PG-ADE further integrates physics-constrained mutation, feasibility-based selection, and Pareto filtering. The implementation uses Python, PyTorch, and SciPy. Results demonstrate substantial improvement over existing models: tensile strength prediction error reduces to 2.8%, yield strength error to 3.1%, and hardness prediction to 2.4%. Optimized composite configurations achieve UTS of 1150–1180 MPa, YTS of 1040–1070 MPa, hardness of 380–410 HV, and a 15–18% reduction in wear rate, outperforming baseline experimental and computational approaches. Compared with existing ML/DL approaches such as KNN, ANN, SVM, and conventional DNNs, the proposed framework achieves higher accuracy, stronger physical alignment, and faster convergence. Overall, the framework provides a physics-grounded, computationally efficient pathway for designing high-performance SiC-reinforced Ti-6Al-4 V composites for automotive applications.
No takes yet. Share an insight, caveat, or question.
Lakshmaiya et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: