Speaker
Description
The development of advanced composite materials requires a comprehensive understanding of the relationships between processing conditions, microstructural evolution, and resulting material properties. However, optimization of synthesis parameters remains challenging due to the complex and nonlinear interactions governing composite fabrication. This study presents an AI-driven computational framework that integrates machine learning and computer vision for process–structure modeling of sonochemically synthesized TiO2–cotton composites. Experimental datasets were generated by systematically varying key sonication parameters, including horn power, sonication time, sonication cycles, precursor concentration, and processing temperature. Computer vision techniques were employed to quantitatively characterize nanoparticle size, surface loading, and dispersion behavior from microscopic observations, while machine learning models were developed to establish predictive relationships between processing variables and composite characteristics. The developed models successfully captured the nonlinear dependencies between sonication parameters and material responses, enabling accurate prediction of composite morphology and nanoparticle distribution.
| Topic Area | Design Optimization, Additive Manufacturing Technologies & Applications |
|---|