MACHINE LEARNING–ASSISTED DESIGN OF SMART MATERIALS AND ADDITIVE MANUFACTURED COMPONENTS
Abstract
The integration of machine learning methods with additive manufacturing (AM) processes and the emerging class of smart materials promises to transform mechanical design and structural performance optimization. This work presents a comprehensive study that combines data-driven modeling, inverse design, and process-parameter optimization to produce additive manufactured components incorporating smart material fractions. We propose a methodological pipeline that spans dataset generation, feature engineering, supervised learning for property prediction, and optimization-driven design to minimize defects while maximizing mechanical performance. An experimental campaign is simulated to demonstrate the approach, producing model predictions and measured outcomes that highlight the potential and limitations of ML-assisted design in AM of smart-material-enabled components. Key outcomes show that machine learning models can predict tensile strength and defect trends with acceptable accuracy and that optimization of laser power, print speed, and smart material fraction yields measurable improvements in structural performance. The results are contextualized within contemporary literature, and practical recommendations for future experimental validation are provided.
Downloads
Published
Issue
Section
License

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.







