Building Data Fusion Surrogate Models for Spacecraft Aerodynamic Problems with Incomplete Factorial Design of Experiments

Abstract

This work concerns a construction of surrogate models for a specific aerodynamic data base. This data base is generally available from wind tunnel testing or from CFD aerodynamic simulations and contains aerodynamic coefficients for different flight conditions and configurations (such as Mach number, angle-of-attack, vehicle configuration angle) encountered over different space vehicles mission. The main peculiarity of aerodynamic data base is a specific design of experiment which is a union of grids of low and high fidelity data with considerably different sizes. Universal algorithms can’t approximate accurately such significantly non-uniform data. In this work a fast and accurate algorithm was developed which takes into account different fidelity of the data and special design of experiments.

Driving digital rock towards machine learning: Predicting permeability with gradient boosting and deep neural networks

“…These are examined in [30,31,32]. Successful applications of such a technique include an application in aerodynamics, examined in [33] Another approach worth considering is to apply adaptive design of experiments, devised for industrial engineering problems, to both increase the efficiency of sensitivity analysis and improve utilization of the computational budget when generating a training sample [34,35].…”

GTApprox: Surrogate modeling for industrial design

“…We briefly describe several industrial applications of GTApprox [21][22][23][24] to illustrate how special features of GTApprox can help in solving real world problems.…”

“…In this application GTApprox was used to obtain surrogate models for aerodynamic response functions of 3-dimensional flight configurations [23]. The training data were obtained either by Euler/RANS CFD simulations or by wind tunnel tests; in either case experiments were costly and/or timeconsuming, so a surrogate model was required to cover the whole domain of interest.…”

“…At the same time, widely popular decision-tree-based methods such as random forests [19] and gradient boosting [20] produce discontinuous piece-wise constant surrogate models, completely inappropriate for, say, gradient-based optimization. This example is rather obvious and the issue can be solved by simply ignoring decision-tree-based methods, but, based on our experience of surrogate modeling at industrial enterprises [21][22][23][24][25], we can identify several more subtle elements of this engineering bias that require significant changes in the software architecture, in particular: Data anisotropy. Training data can be very anisotropic with respect to different groups of variables.…”

Gradient boosting to boost the efficiency of hydraulic fracturing

“…In many cases machine learning allow handling the forecasting problems for cases when the accuracy of physics-driven or empirical models is limited by uncertainties of their input parameters and can provide a fast approximation, or the so-called surrogate models, to estimate selected properties based on the results of real measurements (for details, see [4]). Surrogate models are a wellknown way of solving various industrial engineering problems including oil industry [2,3,9,13,17,18,20].…”