Journal of Advanced Computational Engineering

This paper develops an empirically validated conceptual framework, which redefines construction inspection technology selection as a context-specific optimization problem. The framework models inspection performance as the generation of interactions between technological capabilities and environmental constraints, rather than universal technical superiority. 

Non-linear differential equations play a central role in modeling complex phenomena in physical, chemical, and biological sciences. Exact analytical solutions are rarely obtainable due to strong nonlinearities and complex boundary conditions.

The rapid advancement of Artificial Intelligence (AI) and intelligent digital systems has created significant opportunities to enhance clinical decision-making and data management within healthcare infrastructures.

This paper presents an enhanced Physics-Informed Neural Network (PINN) methodology for structural beam deflection analysis, introducing three methodological contributions that address computational challenges in mechanics: a penalty-based boundary condition enforcement framework, a time-decaying adaptive boundary loss weight, and a regularized representation of concentrated loads via Gaussian approximation.

The field of computational engineering is undergoing a profound transformation, driven by the rapid integration of artificial intelligence (AI) into traditional modelling and simulation paradigms [1].