Deep space and cislunar missions, including those associated with Artemis II mission, expose spacecraft structures to sustained thermal gradients and radiation environments that differ significantly from low Earth orbit conditions. Addressing these challenges requires material and design strategies capable of managing...
Reliable anomaly detection in precision milling is essential for maintaining dimensional accuracy, tool life, surface integrity and component reliability. Conventional data-driven approaches often average sensor signals over entire machining records and rely on black-box machine learning models, reducing physical i...
Aswin Karkadakattil· Journal of Intelligent Manuf...· 0 citations
Overall, SRAF provides an evidence-driven basis for developing engineering AI systems that are physically consistent, verifiable, uncertainty-aware, reproducible, computationally efficient, and suitable for industrial deployment.
Aswin Karkadakattil· Machine Learning for Computa...· 0 citations
A genetic algorithm (GA)-based meta-optimization framework is proposed to automate the selection of normalized loss weights in PINNs, enabling systematic and interpretable selection of normalized loss weights for reliable physics-informed surrogate modelling in manufacturing digital twin applications.
Aswin Karkadakattil· Journal of Intelligent Manuf...· 0 citations
The Reliability-Aware Physics-Guided Learning (RAPIL) framework provides an interpretable, reliability-aware framework for relative density prediction across heterogeneous LPBF datasets while highlighting the remaining challenges associated with machine-dependent variability and model transferability.
