Aerodynamic Shape Optimization of Rockets Based on a Multi-Fidelity Neural Network Surrogate Model Article Swipe

View

Li-Wei Chen , Qin Tong , Chuanqiang Gao , Han Zeng , Zhonghua Han ·

YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.1088/1742-6596/3109/1/012066

This study presents a complete workflow integrating parametric modeling of complex rocket geometries, multi-fidelity data fusion, deep neural network surrogate, and aerodynamic shape optimization. A CAD-based parametric approach was implemented to describe a “Von Kármán nose cone-boosterless-tailless rocket” configuration, with initial design samples generated via Latin Hypercube Sampling to support mesh generation and computational fluid dynamics (CFD) simulations. Aerodynamic datasets containing multiple performance parameters were constructed through CFD computations, subsequently enabling the training and validation of deep learning models. A multi-fidelity neural network architecture was developed to synergistically integrate low- and high-fidelity data, establishing a surrogate-assisted optimization framework that constitutes a variant of discrete adjoint optimization. For the operational condition of Mach 2 at a 6° angle of attack, the optimization strategy, which fixed the center of pressure while minimizing axial force, achieved a 30% reduction in axial force magnitude. These results systematically validate the computational robustness of the proposed algorithm and the practical efficacy of the optimization framework.

Related Topics

Ant Colony Optimization Algorithms

The Shape Of Water

Search Engine Optimization

Shape Of The Universe

Female Body Shape

Shape Of You

The Colour And The Shape

Particle Swarm Optimization

Shape Of My Heart (Sting Song)

Shape

Bent Out Of Shape

The Shape Of Things To Come

Concepts

No concepts available.

Metadata

Type: article
Landing Page: https://doi.org/10.1088/1742-6596/3109/1/012066
OA Status: diamond
References: 7
OpenAlex ID: https://openalex.org/W4415617412

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4415617412

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.1088/1742-6596/3109/1/012066

Digital Object Identifier
Title: Aerodynamic Shape Optimization of Rockets Based on a Multi-Fidelity Neural Network Surrogate Model

Work title
Type: article

OpenAlex work type
Publication year: 2025

Year of publication
Publication date: 2025-10-01

Full publication date if available
Authors: Li-Wei Chen, Qin Tong, Chuanqiang Gao, Han Zeng, Zhonghua Han

List of authors in order
Landing page: https://doi.org/10.1088/1742-6596/3109/1/012066

Publisher landing page
Open access: Yes

Whether a free full text is available
OA status: diamond

Open access status per OpenAlex
OA URL: https://doi.org/10.1088/1742-6596/3109/1/012066

Direct OA link when available
Cited by: 0

Total citation count in OpenAlex
References (count): 7

Number of works referenced by this work

Full payload

id	https://openalex.org/W4415617412
doi	https://doi.org/10.1088/1742-6596/3109/1/012066
ids.doi	https://doi.org/10.1088/1742-6596/3109/1/012066
ids.openalex	https://openalex.org/W4415617412
fwci
type	article
title	Aerodynamic Shape Optimization of Rockets Based on a Multi-Fidelity Neural Network Surrogate Model
biblio.issue	1
biblio.volume	3109
biblio.last_page	012066
biblio.first_page	012066
is_xpac	False
apc_list
apc_paid
language
locations[0].id	doi:10.1088/1742-6596/3109/1/012066
locations[0].is_oa	True
locations[0].source.id	https://openalex.org/S4210187594
locations[0].source.issn	1742-6588, 1742-6596
locations[0].source.type	journal
locations[0].source.is_oa	True
locations[0].source.issn_l	1742-6588
locations[0].source.is_core	True
locations[0].source.is_in_doaj	False
locations[0].source.display_name	Journal of Physics Conference Series
locations[0].source.host_organization	https://openalex.org/P4310320083
locations[0].source.host_organization_name	IOP Publishing
locations[0].source.host_organization_lineage	https://openalex.org/P4310320083, https://openalex.org/P4310311669
locations[0].source.host_organization_lineage_names	IOP Publishing, Institute of Physics
locations[0].license	cc-by
locations[0].pdf_url
locations[0].version	publishedVersion
locations[0].raw_type	journal-article
locations[0].license_id	https://openalex.org/licenses/cc-by
locations[0].is_accepted	True
locations[0].is_published	True
locations[0].raw_source_name	Journal of Physics: Conference Series
locations[0].landing_page_url	https://doi.org/10.1088/1742-6596/3109/1/012066
indexed_in	crossref
authorships[0].author.id	https://openalex.org/A5021688498
authorships[0].author.orcid	https://orcid.org/0000-0002-0309-2284
authorships[0].author.display_name	Li-Wei Chen
authorships[0].author_position	first
authorships[0].raw_author_name	Liwei Chen
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5103037749
authorships[1].author.orcid	https://orcid.org/0000-0002-7011-6514
authorships[1].author.display_name	Qin Tong
authorships[1].author_position	middle
authorships[1].raw_author_name	Tong Qin
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5101425641
authorships[2].author.orcid	https://orcid.org/0000-0002-8674-7759
authorships[2].author.display_name	Chuanqiang Gao
authorships[2].author_position	middle
authorships[2].raw_author_name	Wuhuan Gao
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5022689002
authorships[3].author.orcid	https://orcid.org/0000-0002-5992-8730
authorships[3].author.display_name	Han Zeng
authorships[3].author_position	middle
authorships[3].raw_author_name	Han Zeng
authorships[3].is_corresponding	False
authorships[4].author.id	https://openalex.org/A5103029659
authorships[4].author.orcid	https://orcid.org/0000-0001-7942-1091
authorships[4].author.display_name	Zhonghua Han
authorships[4].author_position	last
authorships[4].raw_author_name	Zhonghua Han
authorships[4].is_corresponding	False
has_content.pdf	False
has_content.grobid_xml	False
is_paratext	False
open_access.is_oa	True
open_access.oa_url	https://doi.org/10.1088/1742-6596/3109/1/012066
open_access.oa_status	diamond
open_access.any_repository_has_fulltext	False
created_date	2025-10-28T00:00:00
display_name	Aerodynamic Shape Optimization of Rockets Based on a Multi-Fidelity Neural Network Surrogate Model
has_fulltext	False
is_retracted	False
updated_date	2025-11-06T03:46:38.306776
primary_topic
cited_by_count	0
locations_count	1
best_oa_location.id	doi:10.1088/1742-6596/3109/1/012066
best_oa_location.is_oa	True
best_oa_location.source.id	https://openalex.org/S4210187594
best_oa_location.source.issn	1742-6588, 1742-6596
best_oa_location.source.type	journal
best_oa_location.source.is_oa	True
best_oa_location.source.issn_l	1742-6588
best_oa_location.source.is_core	True
best_oa_location.source.is_in_doaj	False
best_oa_location.source.display_name	Journal of Physics Conference Series
best_oa_location.source.host_organization	https://openalex.org/P4310320083
best_oa_location.source.host_organization_name	IOP Publishing
best_oa_location.source.host_organization_lineage	https://openalex.org/P4310320083, https://openalex.org/P4310311669
best_oa_location.source.host_organization_lineage_names	IOP Publishing, Institute of Physics
best_oa_location.license	cc-by
best_oa_location.pdf_url
best_oa_location.version	publishedVersion
best_oa_location.raw_type	journal-article
best_oa_location.license_id	https://openalex.org/licenses/cc-by
best_oa_location.is_accepted	True
best_oa_location.is_published	True
best_oa_location.raw_source_name	Journal of Physics: Conference Series
best_oa_location.landing_page_url	https://doi.org/10.1088/1742-6596/3109/1/012066
primary_location.id	doi:10.1088/1742-6596/3109/1/012066
primary_location.is_oa	True
primary_location.source.id	https://openalex.org/S4210187594
primary_location.source.issn	1742-6588, 1742-6596
primary_location.source.type	journal
primary_location.source.is_oa	True
primary_location.source.issn_l	1742-6588
primary_location.source.is_core	True
primary_location.source.is_in_doaj	False
primary_location.source.display_name	Journal of Physics Conference Series
primary_location.source.host_organization	https://openalex.org/P4310320083
primary_location.source.host_organization_name	IOP Publishing
primary_location.source.host_organization_lineage	https://openalex.org/P4310320083, https://openalex.org/P4310311669
primary_location.source.host_organization_lineage_names	IOP Publishing, Institute of Physics
primary_location.license	cc-by
primary_location.pdf_url
primary_location.version	publishedVersion
primary_location.raw_type	journal-article
primary_location.license_id	https://openalex.org/licenses/cc-by
primary_location.is_accepted	True
primary_location.is_published	True
primary_location.raw_source_name	Journal of Physics: Conference Series
primary_location.landing_page_url	https://doi.org/10.1088/1742-6596/3109/1/012066
publication_date	2025-10-01
publication_year	2025
referenced_works	https://openalex.org/W4400879633, https://openalex.org/W4391324983, https://openalex.org/W2054374813, https://openalex.org/W1984753492, https://openalex.org/W3090646395, https://openalex.org/W2132169421, https://openalex.org/W2919958648
referenced_works_count	7
abstract_inverted_index.2	113
abstract_inverted_index.A	25, 80
abstract_inverted_index.a	4, 33, 95, 101, 115, 134
abstract_inverted_index.at	114
abstract_inverted_index.in	137
abstract_inverted_index.of	10, 76, 103, 111, 118, 127, 148, 156
abstract_inverted_index.to	31, 49, 87
abstract_inverted_index.30%	135
abstract_inverted_index.6°	116
abstract_inverted_index.CFD	68
abstract_inverted_index.For	107
abstract_inverted_index.and	21, 53, 74, 91, 152
abstract_inverted_index.the	72, 108, 120, 125, 145, 149, 153, 157
abstract_inverted_index.via	45
abstract_inverted_index.was	29, 85
abstract_inverted_index.Mach	112
abstract_inverted_index.This	1
abstract_inverted_index.data	15
abstract_inverted_index.deep	17, 77
abstract_inverted_index.low-	90
abstract_inverted_index.mesh	51
abstract_inverted_index.nose	36
abstract_inverted_index.that	99
abstract_inverted_index.were	65
abstract_inverted_index.with	40
abstract_inverted_index.(CFD)	57
abstract_inverted_index.Latin	46
abstract_inverted_index.These	141
abstract_inverted_index.angle	117
abstract_inverted_index.axial	131, 138
abstract_inverted_index.data,	93
abstract_inverted_index.fixed	124
abstract_inverted_index.fluid	55
abstract_inverted_index.force	139
abstract_inverted_index.shape	23
abstract_inverted_index.study	2
abstract_inverted_index.which	123
abstract_inverted_index.while	129
abstract_inverted_index.center	126
abstract_inverted_index.design	42
abstract_inverted_index.force,	132
abstract_inverted_index.neural	18, 82
abstract_inverted_index.rocket	12
abstract_inverted_index.“Von	34
abstract_inverted_index.adjoint	105
abstract_inverted_index.attack,	119
abstract_inverted_index.complex	11
abstract_inverted_index.fusion,	16
abstract_inverted_index.initial	41
abstract_inverted_index.models.	79
abstract_inverted_index.network	19, 83
abstract_inverted_index.results	142
abstract_inverted_index.samples	43
abstract_inverted_index.support	50
abstract_inverted_index.through	67
abstract_inverted_index.variant	102
abstract_inverted_index.Abstract	0
abstract_inverted_index.Kármán	35
abstract_inverted_index.Sampling	48
abstract_inverted_index.achieved	133
abstract_inverted_index.approach	28
abstract_inverted_index.complete	5
abstract_inverted_index.datasets	60
abstract_inverted_index.describe	32
abstract_inverted_index.discrete	104
abstract_inverted_index.dynamics	56
abstract_inverted_index.efficacy	155
abstract_inverted_index.enabling	71
abstract_inverted_index.learning	78
abstract_inverted_index.modeling	9
abstract_inverted_index.multiple	62
abstract_inverted_index.presents	3
abstract_inverted_index.pressure	128
abstract_inverted_index.proposed	150
abstract_inverted_index.training	73
abstract_inverted_index.validate	144
abstract_inverted_index.workflow	6
abstract_inverted_index.CAD-based	26
abstract_inverted_index.Hypercube	47
abstract_inverted_index.algorithm	151
abstract_inverted_index.condition	110
abstract_inverted_index.developed	86
abstract_inverted_index.framework	98
abstract_inverted_index.generated	44
abstract_inverted_index.integrate	89
abstract_inverted_index.practical	154
abstract_inverted_index.reduction	136
abstract_inverted_index.rocket”	38
abstract_inverted_index.strategy,	122
abstract_inverted_index.containing	61
abstract_inverted_index.framework.	159
abstract_inverted_index.generation	52
abstract_inverted_index.magnitude.	140
abstract_inverted_index.minimizing	130
abstract_inverted_index.parameters	64
abstract_inverted_index.parametric	8, 27
abstract_inverted_index.robustness	147
abstract_inverted_index.surrogate,	20
abstract_inverted_index.validation	75
abstract_inverted_index.Aerodynamic	59
abstract_inverted_index.aerodynamic	22
abstract_inverted_index.constitutes	100
abstract_inverted_index.constructed	66
abstract_inverted_index.geometries,	13
abstract_inverted_index.implemented	30
abstract_inverted_index.integrating	7
abstract_inverted_index.operational	109
abstract_inverted_index.performance	63
abstract_inverted_index.architecture	84
abstract_inverted_index.establishing	94
abstract_inverted_index.optimization	97, 121, 158
abstract_inverted_index.simulations.	58
abstract_inverted_index.subsequently	70
abstract_inverted_index.computational	54, 146
abstract_inverted_index.computations,	69
abstract_inverted_index.high-fidelity	92
abstract_inverted_index.optimization.	24, 106
abstract_inverted_index.configuration,	39
abstract_inverted_index.multi-fidelity	14, 81
abstract_inverted_index.systematically	143
abstract_inverted_index.synergistically	88
abstract_inverted_index.surrogate-assisted	96
abstract_inverted_index.cone-boosterless-tailless	37
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	5
citation_normalized_percentile