High-Entropy Alloys (HEAs), characterized by their multi-element compositions and exceptional mechanical properties, have emerged as a promising class of materials for advanced applications. The stacking fault energy (SFE), a critical thermodynamic parameter, governs the activation of deformation mechanisms such as Transformation-Induced Plasticity (TRIP) and Twinning-Induced Plasticity (TWIP). In HEAs, understanding and predicting SFE is essential for optimizing their phase stability and mechanical performance. This project explores the role of SFE in determining deformation behaviors and employs machine learning models to accurately predict SFE based on alloy compositions and thermodynamic parameters.
The TRIP mechanism involves stress-induced phase transformations, typically from an FCC (γ) structure to an HCP (ε) or BCC (α′) phase, driven by low SFE values (<16 mJ/m²). This transformation enhances ductility and toughness by dissipating energy through phase boundary movements. In contrast, the TWIP mechanism, activated at moderate SFE values (20-50 mJ/m²), involves mechanical twinning within the stable FCC phase, improving strain hardening and maintaining structural integrity. The interplay between SFE, temperature, and alloying elements controls whether TRIP or TWIP dominates, directly affecting the material’s work-hardening rate and plastic deformation behavior.
This project leverages machine learning algorithms, such as Gaussian Process Regression (GPR) and Artificial Neural Networks (ANNs), to predict SFE efficiently, enabling rapid design of HEAs with tailored properties. By combining experimental data and computational modeling, the study demonstrates how SFE influences deformation modes, phase transformations, and mechanical responses in HEAs. The findings provide a foundation for designing advanced HEAs with optimized TRIP and TWIP behaviors for high-performance applications.
