Artificial Intelligence-Based Prediction of Thermo-Elastic Behavior in Inconel 718 / Ti-6Al-4V Rotating Disks

This study presents a comprehensive numerical investigation of the thermo-elastic behavior of an Inconel 718 / Ti-6Al-4V bimetal rotating disk subjected to non-uniform thermal fields. The analysis focuses on the evaluation of radial and circumferential stress distributions as well as radial displacement responses under various temperature profiles, including constant, parabolic, linearly increasing, and linearly decreasing temperature variations along the radial direction. The governing thermo-elastic equations are formulated under plane stress assumptions and solved numerically by discretizing the disk geometry into finite radial segments. Material properties are assumed to remain constant within the investigated temperature range of 10 °C to 100 °C. The numerical results demonstrate that increasing temperature levels have a significant influence on both the magnitude and distribution of thermo-elastic stresses and radial displacements. Pronounced stress variations are observed near the material interface, highlighting the critical role of thermal expansion mismatch between Inconel 718 and Ti-6Al-4V. In particular, the maximum circumferential stress exhibits an increase of approximately 160% as the reference temperature rises from 10 °C to 100 °C. Additionally, radial displacement profiles show strong sensitivity to the imposed temperature modes, with steeper thermal gradients consistently leading to higher deformation levels and localized stress concentrations at the interface region. Beyond numerical analysis, the generated stress and displacement data constitute a structured and reliable dataset for artificial intelligence–based modeling. An AI-driven predictive framework is developed and validated using this dataset, achieving high predictive accuracy with mean squared error values below 0.012 and strong correlation with numerical benchmarks.