Physics-Informed Machine Learning for Intelligent Gas Turbine Digital Twins: A Review

Gas turbine digital twins are increasingly critical for real-time diagnostics, predictive maintenance, and performance optimization under both baseload and flexible operations. Advances in hybrid modeling that integrate physics-based simulations with machine learning, offer tremendous opportunities to develop intelligent digital twins that are both physically consistent and computationally efficient. This review surveys current research and industrial practices in hybrid artificial intelligence (AI) models for gas turbines and introduces a classification of four distinct methodologies: (1) ANN-augmented thermodynamic models for enhanced component-level diagnostics; (2) physics-integrated operational architectures combining live sensor data, AI, and modular physics models for system-level optimization; (3) physics-constrained neural networks (PcNNs) and computational fluid dynamic (CFD) surrogates that embed governing equations into learning frameworks for consistent flow and thermal predictions; (4) generative and model-discovery approaches for synthetic data generation and interpretable equation extraction. A comparative maturity framework is presented to evaluate these approaches across five criteria: data dependency, interpretability, deployment complexity, integration with simulation and design workflows, and real-time capability. Industrial implementations by leading OEMs and independent research institutes are analyzed within this context. The review concludes by outlining key challenges and a roadmap toward scalable, interpretable, and operationally robust intelligent digital twin architectures for next generation gas turbines.