collaborators

5 papers

cs.LG2026

Development and Validation of a Physics-Guided Machine Learning Extrapolation Framework Using a Classical Transient Diffusion Benchmark

Ashutosh Yadav, Alok Dubey, Prodyut Ranjan Chakraborty +1

Machine learning models used in engineering are typically trained within limited operating ranges, yet reliable predictions are often required beyond these domains. Consequently, t…

physics.flu-dyn2026

DD-RNO: A Domain-Decomposed Routed Neural Operator for Airfoil Flow Prediction

T. A. Mehta, P. S. Bhati, H. D. Akolekar

Deep learning surrogates for RANS flow prediction around airfoils face two persistent bottlenecks. A single neural architecture cannot simultaneously resolve sharp near-wall bounda…

physics.flu-dyn2026

Realizability-Constrained Machine Learning for Turbulence Closures in Wake Flows

Talib Ansari, Priyank H. Mehta, Harshal D. Akolekar

Computational fluid dynamics (CFD)-driven machine learning frameworks based on symbolic regression offer a promising pathway for turbulence model discovery, but are often hindered…

physics.flu-dyn2024

Enhancing Accuracy of Transition Models for Gas Turbine Applications Through Data-Driven Approaches

Harshal D. Akolekar

Separated flow transition is a very popular phenomenon in gas turbines, especially low-pressure turbines (LPT). Low-fidelity simulations are often used for gas turbine design. Howe…

physics.flu-dyn2024

Surface roughness effects in a transonic axial flow compressor operating at near-stall conditions

Prashant B. Godse, Harshal D. Akolekar, A. M. Pradeep

Surface roughness is a major contributor to performance degradation in gas turbine engines. The fan and the compressor, as the first components in the engine's air path, are especi…