Robust design of a re-entry unmanned space vehicle by multi-fidelity evolution control

Minisci, Edmondo; Vasile, Massimiliano

doi:10.1145/2001576.2001671

Cited by 2 publications

(4 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A suitably trained ANN may perform tasks such as pattern recognition, identification, classification, system control and function approximation (non-linear regression) [29]. In aerospace, ANNs have been used for the estimation of aerodynamic coefficients [30], space vehicle design and trajectory optimisation [31], [32], turbo-machinery blade optimisation [33], wing design [34], flow control, aeroelasticity, and interpolation of wind tunnel data [18].…”

Section: B Artificial Neural Networkmentioning

confidence: 99%

“…Leary [36] introduced the 'knowledgebased-neural-network' (KBNN) technique as a means of incorporating LF data into the training procedure of a limited set of HF samples via scaling/translation based parameter mapping. Minisci and Vasile [32] estimate aerodynamic coefficients using a MF ANN first trained on a global set of samples given by a simplified analytical model, then iteratively refined with CFD data scheduled via evolution control. LF samples are sequentially discarded should they fall outwith a predefined applicability region relative to new HF points.…”

Section: B Artificial Neural Networkmentioning

confidence: 99%

“…The geometric design vector d(l, w, n, θ) is defined via the variable bounds given in table I [32]. By parametrising in this manner, small variations in d can correspond to significant change in the resulting geometry [40].…”

Section: A Geometry Parametrizationmentioning

confidence: 99%

See 2 more Smart Citations

Multi-stage Multi-fidelity Information Correction for Artificial Neural Network Based Meta-modelling

Parsonage

Maddock

2020

2020 IEEE Symposium Series on Computational Intelligence (SSCI)

View full text Add to dashboard Cite

Multi-fidelity meta-modelling has become a popular means of efficiently distributing computational resource across various levels of simulation fidelity to obtain numerically accurate predictions of an expensive function. Such techniques have significant potential within an engineering design paradigm incorporating either many-query analyses or outer-loop applications.This paper presents a hybrid parametric/non-parametric information correction method incorporating the sequential application of several distinct stages within an artificial neural network based surrogate framework. The proposed methodology may be used to correct any domain encompassing set of low-fidelity input/output correspondence using a small subset of high-fidelity samples. A global surrogate can then be generated via a doubleloop ANN hyper-parameter selection and training procedure.To demonstrate the effectiveness of the proposed metamodelling approach, the aerodynamic response prediction of a parametrized waverider-based re-entry vehicle is examined. Results suggest that the incorporation of multiple corrective stages leveraging low-fidelity data can offer significant improvements in computational efficiency when modelling the expensive highfidelity function compared with single stage correction. The costs to achieve global accuracy are examined and compared across single/multi-stage variants, with consideration given to surrogate construction and evaluation. Results are compared both with the low-fidelity approximation and a surrogate of the 'true' response built using only the high-fidelity samples available to the corrective method.

show abstract

Section: B Artificial Neural Networkmentioning

confidence: 99%

Section: B Artificial Neural Networkmentioning

confidence: 99%

See 1 more Smart Citation

Multi-stage Multi-fidelity Information Correction for Artificial Neural Network Based Meta-modelling

Parsonage

Maddock

2020

2020 IEEE Symposium Series on Computational Intelligence (SSCI)

View full text Add to dashboard Cite

show abstract

“…Recently, multi-fidelity modelling, characterized by hierarchical training on different data sources, has gradually gained large attention. 36 Inspired by this mechanism, Zhang et al formally proposed the concept of multi-fidelity residual neural network (MR-NN) to model sand behaviours. 23 Further, He et al proposed a modelling framework based on multi-fidelity data to successfully capture the rate-dependent behaviour of soft clays, where the LF and HF model are trained based on theoretical values generated by the a phenomenological constitutive model and only 24 experimental data, respectively.…”

Section: Introductionmentioning

confidence: 99%

A multi‐fidelity residual neural network based surrogate model for mechanical behaviour of structured sand

Zhou,

Yin,

et al. 2024

Num Anal Meth Geomechanics

View full text Add to dashboard Cite

The structured sand presents significant interparticle bonding and anisotropy, resulting in significant differences in the physical and mechanical properties from the pure sand. This study proposes a new surrogate model based on the concept of multi‐fidelity residual neural network (MR‐NN) as an alternative to DEM simulation for predicting the mechanical behaviours of structured sand with different initial anisotropy and saving largely computational costs. The model is initially trained using low‐fidelity (LF) data to focus on capturing the main underpinning correlations between macroscopic mechanical parameters with inter‐particle properties and anisotropic state variables (i.e., microscopic fabric and tilting angle of sand), where the LF data are generated from previously proposed anisotropic macro‐micro quantitative correlation. Subsequent training on sparser high‐fidelity (HF) data is used to calibrate and refine the model with HF data generated from DEM simulations for anisotropic structured sand. Feedforward neural network (FNN) is adopted as the baseline algorithm for training models. The macroscopic anisotropic parameters of structured sand predicted by the surrogate model are compared with DEM simulations to examine its feasibility and generalization ability. Furthermore, the robustness of the surrogate model is examined by discussing the effect of LF data on the performance of MR‐NN. The superiority of the MR‐NN is further verified by comparing the performance of the trained MR‐NN with the one‐shot trained FNN based on the same HF data. All results demonstrate that the proposed surrogate model can provide a fast and accurate simulation of the anisotropic parameters of structured sand.

show abstract

Robust design of a re-entry unmanned space vehicle by multi-fidelity evolution control

Cited by 2 publications

References 26 publications

Multi-stage Multi-fidelity Information Correction for Artificial Neural Network Based Meta-modelling

Multi-stage Multi-fidelity Information Correction for Artificial Neural Network Based Meta-modelling

A multi‐fidelity residual neural network based surrogate model for mechanical behaviour of structured sand

Contact Info

Product

Resources

About