Physics-Informed Machine Learning for Intelligent Gas Turbine Digital Twins: A Review
Open Access
Abstract
This review surveys recent progress in hybrid artificial intelligence (AI) approaches for gas turbine intelligent digital twins, with an emphasis on models that integrate physics-based simulations and machine learning. The main contribution is the introduction of a structured classification of hybrid AI methods tailored to gas turbine applications, the development of a novel comparative maturity framework, and the proposal of a layered roadmap for integration. The classification organizes hybrid AI approaches into four categories: (1) artificial neural network (ANN)-augmented thermodynamic models, (2) physics-integrated operational architectures, (3) physics-constrained neural networks (PcNNs) with computational fluid dynamics (CFD) surrogates, and (4) generative and model discovery approaches. The maturity framework evaluates these categories across five criteria: data dependency, interpretability, deployment complexity, workflow integration, and real-time capability. Industrial case studies—including General Electric (GE) Vernova’s SmartSignal, Siemens’ Autonomous Turbine Operation and Maintenance (ATOM), and the Electric Power Research Institute (EPRI) turbine digital twin—illustrate applications in real-time diagnostics, predictive maintenance, and performance optimization. Together, the classification and maturity framework provide the means for systematic assessment of hybrid AI methods in gas turbine intelligent digital twins. The review concludes by identifying key challenges and outlining a roadmap for the future development of scalable, interpretable, and operationally robust intelligent digital twins for gas turbines.Keywords
All Related Versions
This publication has 64 references indexed in Scilit:
- Implicitly physics-informed multi-fidelity physical field data fusion method based on Taylor modal decompositionAdvanced Engineering Informatics, 2024
- Scientific Machine Learning Through Physics–Informed Neural Networks: Where we are and What’s NextJournal of Scientific Computing, 2022
- A holistic method of complex product development based on a neural network-aided technological evolution systemAdvanced Engineering Informatics, 2021
- The utility based non-linear fuzzy AHP optimization model for network selection in heterogeneous wireless networksApplied Soft Computing, 2018
- Performance-based health monitoring, diagnostics and prognostics for condition-based maintenance of gas turbines: A reviewApplied Energy, 2017
- Automatic modeling of a gas turbine using genetic programming: An experimental studyApplied Soft Computing, 2017
- An artificial neural network-based diagnostic methodology for gas turbine path analysis—part II: case studyEnergy, Ecology and Environment, 2016
- An artificial neural network approach to compressor performance predictionApplied Energy, 2009
- Prospects for aero gas-turbine diagnostics: a reviewApplied Energy, 2004
- Gas-turbine diagnostics using artificial neural-networks for a high bypass ratio military turbofan engineApplied Energy, 2004