Research on integrated design method of wide-range hypersonic vehicle/engine based on dynamic multi-objective optimization

IF 5 1区工程技术 Q1 ENGINEERING, AEROSPACE

Aerospace Science and Technology Pub Date : 2025-02-07 DOI:10.1016/j.ast.2025.110031

Zeyang Zhao , Yue Ma , Ye Tian , Zhijian Ding , Hua Zhang , Shuhong Tong

{"title":"Research on integrated design method of wide-range hypersonic vehicle/engine based on dynamic multi-objective optimization","authors":"Zeyang Zhao , Yue Ma , Ye Tian , Zhijian Ding , Hua Zhang , Shuhong Tong","doi":"10.1016/j.ast.2025.110031","DOIUrl":null,"url":null,"abstract":"<div><div>A hypersonic vehicle powered by an air-breathing engine enables efficient long-range delivery and high-speed flexible access to space. The key to achieving high-performance operation of hypersonic vehicles lies in high-efficiency and well-matched hypersonic vehicle/engine integration configuration design. While machine learning-assisted intelligent optimization has shown initial success in hypersonic vehicle/engine integration design, over-reliance on basic and simplistic intelligent methods has led to a significant dependency on sample size and a tendency to easily converge to local optima. This study addresses the need for wide-speed-range, small-sample, and multi-criteria hypersonic vehicle/engine integration design by developing a parametric model for the hypersonic vehicle/engine configuration. Leveraging computational fluid dynamics (CFD) technology, the study uses the Deep Active Subspace (DAS) model along with the Improved Multi-Objective Coati Optimization Algorithm (IMOCOA). This approach is applied to small-sample dynamic multi-point and multi-objective optimization design with the objective of achieving an optimal hypersonic vehicle/engine configuration design characterized by low drag, a high lift-drag ratio, and a high total pressure recovery coefficient across various operating conditions. The results indicate that the Mean Absolute Percentage Error (MAPE) for predicting hypersonic vehicle/engine integration performance using the DAS model is <2 %. Validation of the Pareto solution set from multi-objective optimization shows that dynamic multi-objective optimization enhances performance by >3 % compared to static multi-objective optimization. In comparison to the pre-optimization configuration, the optimized configuration demonstrates a 12.97 % reduction in total drag, with a 9.77 % improvement in lift-drag ratio and a 10.27 % enhancement in total pressure recovery coefficient, highlighting rapid and efficient hypersonic vehicle/engine integration configuration design and performance improvement.</div></div>","PeriodicalId":50955,"journal":{"name":"Aerospace Science and Technology","volume":"159 ","pages":"Article 110031"},"PeriodicalIF":5.0000,"publicationDate":"2025-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Aerospace Science and Technology","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1270963825001026","RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, AEROSPACE","Score":null,"Total":0}

引用次数: 0

Abstract

A hypersonic vehicle powered by an air-breathing engine enables efficient long-range delivery and high-speed flexible access to space. The key to achieving high-performance operation of hypersonic vehicles lies in high-efficiency and well-matched hypersonic vehicle/engine integration configuration design. While machine learning-assisted intelligent optimization has shown initial success in hypersonic vehicle/engine integration design, over-reliance on basic and simplistic intelligent methods has led to a significant dependency on sample size and a tendency to easily converge to local optima. This study addresses the need for wide-speed-range, small-sample, and multi-criteria hypersonic vehicle/engine integration design by developing a parametric model for the hypersonic vehicle/engine configuration. Leveraging computational fluid dynamics (CFD) technology, the study uses the Deep Active Subspace (DAS) model along with the Improved Multi-Objective Coati Optimization Algorithm (IMOCOA). This approach is applied to small-sample dynamic multi-point and multi-objective optimization design with the objective of achieving an optimal hypersonic vehicle/engine configuration design characterized by low drag, a high lift-drag ratio, and a high total pressure recovery coefficient across various operating conditions. The results indicate that the Mean Absolute Percentage Error (MAPE) for predicting hypersonic vehicle/engine integration performance using the DAS model is <2 %. Validation of the Pareto solution set from multi-objective optimization shows that dynamic multi-objective optimization enhances performance by >3 % compared to static multi-objective optimization. In comparison to the pre-optimization configuration, the optimized configuration demonstrates a 12.97 % reduction in total drag, with a 9.77 % improvement in lift-drag ratio and a 10.27 % enhancement in total pressure recovery coefficient, highlighting rapid and efficient hypersonic vehicle/engine integration configuration design and performance improvement.

查看原文本刊更多论文

求助全文

约1分钟内获得全文求助全文

来源期刊

Aerospace Science and Technology 工程技术-工程：宇航

CiteScore

10.30

自引率

28.60%

发文量

654

审稿时长

54 days

期刊介绍： Aerospace Science and Technology publishes articles of outstanding scientific quality. Each article is reviewed by two referees. The journal welcomes papers from a wide range of countries. This journal publishes original papers, review articles and short communications related to all fields of aerospace research, fundamental and applied, potential applications of which are clearly related to: • The design and the manufacture of aircraft, helicopters, missiles, launchers and satellites • The control of their environment • The study of various systems they are involved in, as supports or as targets. Authors are invited to submit papers on new advances in the following topics to aerospace applications: • Fluid dynamics • Energetics and propulsion • Materials and structures • Flight mechanics • Navigation, guidance and control • Acoustics • Optics • Electromagnetism and radar • Signal and image processing • Information processing • Data fusion • Decision aid • Human behaviour • Robotics and intelligent systems • Complex system engineering. Etc.