A survey of Bayesian calibration and physics-informed neural networks in scientific modeling
FAC Viana, AK Subramaniyan - Archives of Computational Methods in …, 2021 - Springer
Computer simulations are used to model of complex physical systems. Often, these models
represent the solutions (or at least approximations) to partial differential equations that are …
represent the solutions (or at least approximations) to partial differential equations that are …
Propagation of friction parameter uncertainties in the nonlinear dynamic response of turbine blades with underplatform dampers
Underplatform dampers are widely used in turbomachinery to mitigate structural vibrations
by means of friction dissipation at the interfaces. The modelling of such friction dissipation is …
by means of friction dissipation at the interfaces. The modelling of such friction dissipation is …
Learning and optimization under epistemic uncertainty with Bayesian hybrid models
Abstract Hybrid (ie, grey-box) models are a powerful and flexible paradigm for predictive
science and engineering. Grey-box models use data-driven constructs to incorporate …
science and engineering. Grey-box models use data-driven constructs to incorporate …
Aerodynamic optimization of a transonic fan rotor by blade sweeping using adaptive Gaussian process
J Luo, Z Fu, Y Zhang, W Fu, J Chen - Aerospace Science and Technology, 2023 - Elsevier
Due to its easy implementation and comprehensive applicability, surrogate model has been
widely used in the aerodynamic design optimization (ADO) of turbomachinery blades …
widely used in the aerodynamic design optimization (ADO) of turbomachinery blades …
Data-driven predictive modeling of FeCrAl oxidation
FeCrAl alloys are among the most promising candidates for accident-tolerant fuel cladding
material in light water nuclear reactors. Despite their high-temperature oxidation resistance …
material in light water nuclear reactors. Despite their high-temperature oxidation resistance …
Application of deep transfer learning and uncertainty quantification for process identification in powder bed fusion
Accurate identification and modeling of process maps in additive manufacturing remains a
pertinent challenge. To ensure high quality and reliability of the finished product …
pertinent challenge. To ensure high quality and reliability of the finished product …
Inverse aerodynamic design of gas turbine blades using probabilistic machine learning
S Ghosh… - Journal of …, 2022 - asmedigitalcollection.asme.org
One of the critical components in industrial gas turbines (IGT) is the turbine blade. The
design of turbine blades needs to consider multiple aspects like aerodynamic efficiency …
design of turbine blades needs to consider multiple aspects like aerodynamic efficiency …
Bayesian learning of orthogonal embeddings for multi-fidelity Gaussian Processes
Uncertainty propagation in complex engineering systems often poses significant
computational challenges related to modeling and quantifying probability distributions of …
computational challenges related to modeling and quantifying probability distributions of …
Guided probabilistic reinforcement learning for sampling-efficient maintenance scheduling of multi-component system
In recent years, multi-agent deep reinforcement learning has progressed rapidly as reflected
by its increasing adoptions in industrial applications. This paper proposes a Guided …
by its increasing adoptions in industrial applications. This paper proposes a Guided …
Shock wave prediction in transonic flow fields using domain-informed probabilistic deep learning
Transonic flow fields are marked by shock waves of varying strength and location and are
crucial for the aerodynamic design and optimization of high-speed transport aircraft. While …
crucial for the aerodynamic design and optimization of high-speed transport aircraft. While …