Multi-fidelity Kriging-assisted structural optimization of whole engine models employing medial meshes

Abstract

Finite element models of whole gas turbine engines, also known as whole engine models (WEMs), which consist of threedimensional solid elements are not commonly used in design optimization studies due to the high computational cost of solving them for many designs. WEMs consisting of two-dimensional shell elements can be a suitable replacement for high-fidelity solid WEMs as they approximate the responses well while being significantly quicker to solve. However, in a surrogate-assisted optimization study, the accumulation of errors in the shell WEM evaluations can result in the construction of a surrogate model that can be somewhat misleading compared to the solid WEM response surface. Such a surrogate model could return promising designs that, when validated using solid WEMs, turn out to be suboptimal or infeasible. A novel approach which combines medial meshing and multi-fidelity surrogate modelling techniques is proposed to increase the feasibility of conducting whole engine optimization studies. We demonstrate the workflow for generating medial meshes on an engine intercasing geometry. The accuracy of medial mesh simulations with respect to solid mesh simulations is evaluated and discussed in the context of their suitability as a source of low-fidelity structural information for multi-fidelity surrogate models. The impact of this combination of techniques is subsequently illustrated using two case studies. The first case study is the optimization of an intermediate compressor casing for minimum mass with constraints on the casing stiffness. The results show that the multi-fidelity approach is able to find optimum designs that are equivalent to the expensive singlefidelity approach of using only solid mesh evaluations but at a significantly lower computational cost. The second case study is the optimization of a whole engine geometry. This case study serves to demonstrate the effectiveness of the multi-fidelity approach for solving realistic design problems.

Machine learning-based inverse design methods considering data characteristics and design space size in materials design and manufacturing: a review

“…110,111 Yong et al (2019) distinguished high-fidelity models (3D elements) and lowfidelity models (2D elements) by using different mesh types for gas turbine engines. 112 Moreover, Liu et al (2020) developed a low-fidelity model of mesostructure using homogenized effective dynamic properties. 113 In light of these examples, high-and low-fidelity models can be differentiated based on experiments/simulations, simulations/analytical functions, or non-linear solvers/linear solvers, among others, depending on the situation.…”

A multi-fidelity RBF surrogate-based optimization framework for computationally expensive multi-modal problems with application to capacity planning of manufacturing systems

“…To fill this gap, the multi-fidelity optimization (MFO) methods have received much attention in recent years and have been applied to various fields (Liu et al 2016;Kandasamy et al 2016;Bonfiglio et al 2018;Habib et al 2019;Liu et al 2019;Yi et al 2019;Zhang et al 2019a;Yong et al 2019;Zhang et al 2018;Ding and Kareem 2018;Tao and Sun 2019). Instead of only building a single-fidelity surrogate-based on the HF model, MFO methods also utilize a LF model, which is less accurate but much cheaper and easier to compute.…”

MUMBO: MUlti-task Max-value Bayesian Optimization

“…Therefore, MT BO has so far been restricted to considering simple structures at a large computational cost. Despite this restriction, MT optimization has wide-spread use across physical experiments [6,7,8], environmental modeling [9], and operational research [10,11,12].…”