Physics-Informed Artificial Intelligence for Engineering Applications

Éditeurs invités

• Jiangbei Hu, Dalian University of Technology
• Ben Fei, The Chinese University of Hong Kong
• Yajun Cao, Hangzhou Dianzi University

Synthèse

This special issue addresses the integration of physical laws and mathematical structures into AI models for engineering systems. The challenge of creating accurate and generalizable AI systems in complex operating conditions motivates the inclusion of domain knowledge directly into learning architectures, combining data-driven approaches with established engineering principles.

Thèmes proposés

• Physics-informed neural networks (PINNs)
• Constrained learning
• Hybrid physics–AI models
• Differentiable simulation
• Neural operators
• Differential equations and conservation laws
• Approximation and convergence analysis
• Uncertainty quantification and robustness
• Industrial inspection and fault diagnosis
• Intelligent manufacturing and digital twins
• Energy and power systems
• Structural health monitoring
• Civil infrastructure and materials engineering
• Transportation and aerospace applications
• Robotics and autonomous systems
• Benchmarking and deployment