高超声速气动热实验数据的多层学习方法 | |
Alternative Title | A Multi-Level Learning Method for Aerodynamic Heating Experimental Data Analysis |
陈正 | |
Thesis Advisor | 罗长童 |
2021-05-17 | |
Degree Grantor | 中国科学院大学 |
Place of Conferral | 北京 |
Subtype | 硕士 |
Degree Discipline | 流体力学 |
Keyword | 气动热 实验数据 小样本 特征工程 多层学习 |
Abstract | 高超声速气动热是典型的多物理因素耦合的强非线性问题,受到激波、粘性、热化学反应、非定常效应等众多复杂因素的影响,这样的特性对传统的理论方法和仿真技术提出了巨大的挑战。数据驱动的研究方法向来是分析研究此类问题的重要途径。真实流动环境中采集的风洞实验数据在分析气动热问题中具有无可替代的价值,机器学习作为代表性的数据驱动研究方法,则是目前极具潜力的数据分析手段。依托实验数据,一方面可以建立快速可靠的气动热估算方法,这对高超声速飞行器的设计,尤其是初期设计阶段,具有重要的指导意义;另一方面,也是探索目前理论方法不足以准确描述和数值模拟无法准确复现的物理现象的重要手段。如今,人工智能技术的发展为开展数据驱动的研究提供了强有力的支撑,而其中的机器学习方法或将是推动气动热实验数据研究的关键。 |
Other Abstract | Aerodynamic heating is a complicated physical phenomenon that many factors affect it nonlinearly. The wind tunnel experimental data collected from real-world hypersonic flow is irreplaceable in the study of aerodynamic heating. Machine learning is regarded as the most promising approach to data modeling. As a critical problem in hypersonic flow, aerodynamic heating is influenced by shock-waves, viscosity, thermal-chemical reactions and so on, and those factors challenge both theoretical analysis and numerical simulation severely. Data-driven has always been an effective path to handle those problems. Modeling experimental data to predict aerodynamic heating rapidly and reliably plays an important role in hypersonic aircraft design, especially at the preliminary stage. Besides, it can also be applied to detect the physical mechanism when theoretical models or numerical simulations are not exact enough. Nowadays, the development of artificial intelligence provides a powerful data-driven technique, which is promising in the research on aerodynamic heating. |
Language | 中文 |
Document Type | 学位论文 |
Identifier | http://dspace.imech.ac.cn/handle/311007/86559 |
Collection | 高温气体动力学国家重点实验室 |
Recommended Citation GB/T 7714 | 陈正. 高超声速气动热实验数据的多层学习方法[D]. 北京. 中国科学院大学,2021. |
Files in This Item: | ||||||
File Name/Size | DocType | Version | Access | License | ||
86559.pdf(14953KB) | 学位论文 | 开放获取 | CC BY-NC-SA | Application Full Text |
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment