Surrogate modeling: tricks that endured the test of time and some recent developments

FAC Viana, C Gogu, T Goel - Structural and Multidisciplinary Optimization, 2021‏ - Springer
Tasks such as analysis, design optimization, and uncertainty quantification can be
computationally expensive. Surrogate modeling is often the tool of choice for reducing the …

Compressor airfoil optimization method driven by data-mechanism integration based on evolutionary multi-tasking algorithm

J Cheng, Y Zhang, J Chen, H Ma, B Liu - Aerospace Science and …, 2024‏ - Elsevier
To address the challenge of the" curse of dimensionality" in aerodynamic design
optimization of compressors, this study introduces an innovative optimization technique …

Advances in bayesian probabilistic modeling for industrial applications

S Ghosh, P Pandita, S Atkinson… - … -ASME Journal of …, 2020‏ - asmedigitalcollection.asme.org
Industrial applications frequently pose a notorious challenge for state-of-the-art methods in
the contexts of optimization, designing experiments and modeling unknown physical …

On Uncertainty Quantification in Materials Modeling and Discovery: Applications of GE's BHM and IDACE

SK Ravi, A Bhaduri, A Amer, S Ghosh, L Wang… - AIAA SCITECH 2023 …, 2023‏ - arc.aiaa.org
View Video Presentation: https://doi. org/10.2514/6.2023-0528. vid The coupling of artificial
intelligence and materials characterizations has been a center piece of almost all materials …

Application of deep transfer learning and uncertainty quantification for process identification in powder bed fusion

P Pandita, S Ghosh, VK Gupta… - … -ASME Journal of …, 2022‏ - asmedigitalcollection.asme.org
Accurate identification and modeling of process maps in additive manufacturing remains a
pertinent challenge. To ensure high quality and reliability of the finished product …

Pro-ml ideas: A probabilistic framework for explicit inverse design using invertible neural network

S Ghosh, GA Padmanabha, C Peng… - AIAA Scitech 2021 …, 2021‏ - arc.aiaa.org
View Video Presentation: https://doi. org/10.2514/6.2021-0465. vid An inverse design
process has the potential to positively impact the difficulties of the traditional iterative …

Reinforcement learning-based sequential batch-sampling for bayesian optimal experimental design

Y Ashenafi, P Pandita, S Ghosh - Journal of …, 2022‏ - asmedigitalcollection.asme.org
Engineering problems that are modeled using sophisticated mathematical methods or are
characterized by expensive-to-conduct tests or experiments are encumbered with limited …

A federated, multimodal digital thread platform for enabling digital twins

VS Kumar, KS Aggour, P Cuddihy… - Naval Engineers …, 2020‏ - ingentaconnect.com
The “digital twin” is emerging as a dominant paradigm aimed at improving outcomes
associated with physical counterparts within several industrial sectors. Recently, the …

Bayesian Optimization for Multi-Objective High-Dimensional Turbine Aero Design

Y Zhang, S Ghosh… - … Expo: Power for …, 2021‏ - asmedigitalcollection.asme.org
Industrial design fundamentally relies on high-dimensional multi-objective optimization.
Bayesian Optimization (BO) based on Gaussian Processes (GPs) has been shown to be …

A Physics-informed Data-driven Approach to Additive Manufacturing Parameter Optimization

LC Dial, S Ghosh… - AM&P Technical …, 2019‏ - dl.asminternational.org
A novel framework including experimental and model-based techniques saves time and
enables the introduction of new alloys for additive manufacturing. This article describes the …