Submission Deadline: 31 July 2027 View: 143 Submit to Special Issue
Prof. Ki Yong Oh
Email: kiyongoh@hanyang.ac.kr
Affiliation: School of Mechanical Engineering, Hanyang University, Seoul, South Korea
Research Interests: prognostics and health management, physcal AIs, AI transformation, battery informatics
Assoc. Prof. Joon Ha Jung
Email: joonha@ajou.ac.kr
Affiliation: School of Mechanical Engineering, Hanyang University, Seoul, South Korea
Research Interests: fault diagnosis, artificial intelligence, agentic AI
Assist. Prof. Jong Moon Ha
Email: jmha@ajou.ac.kr
Affiliation: Department of Mechanical Engineering, Ajou University, Suwon, Republic of Korea
Research Interests: AI-driven prognostics and health management (PHM), agentic AI
Modern engineering systems are becoming increasingly complex, creating a critical demand for real-time monitoring, state estimation, and predictive maintenance to ensure operational safety and efficiency. However, physical sensing often faces limitations due to harsh environments, space constraints, and high implementation costs. Scientific Machine Learning (SciML) and Physics-Informed Neural Networks (PINNs) have emerged as powerful paradigms bridging data-driven machine learning with fundamental domain physics, overcoming traditional data sparsity and physical inconsistency issues.
This Special Issue aims to highlight recent advances, innovative methodologies, and practical engineering applications of SciML and PINNs for Virtual Sensing and overall AI Transformation (AX) in engineering domain. By integrating governing physical laws (e.g., fluid dynamics, solid mechanics, thermodynamics, and electrochemical processes) into neural network architectures, researchers can construct robust virtual sensors capable of estimating unmeasurable physical quantities in real time.
Suggested themes and topics include, but are not limited to:
- Novel architectures and optimization strategies for Physics-Informed Neural Networks (PINNs)
- Virtual sensing and digital twin frameworks for physical and structural systems
- Scientific Machine Learning (SciML) for multiscale and multiphysics modeling
- Physics-guided data-driven methods for Prognostics and Health Management (PHM)
- AI Transformation (AX) in mechanical, aerospace, civil, and energy engineering applications
- Real-time state estimation and physics-constrained surrogate modeling
Login
Register
Submit a Paper
Propose a Special lssue