CN113779869B - 一种基于自动编码器反演的多层绝热材料优化方法 - Google Patents

一种基于自动编码器反演的多层绝热材料优化方法 Download PDF

Info

Publication number
CN113779869B
CN113779869B CN202110932572.3A CN202110932572A CN113779869B CN 113779869 B CN113779869 B CN 113779869B CN 202110932572 A CN202110932572 A CN 202110932572A CN 113779869 B CN113779869 B CN 113779869B
Authority
CN
China
Prior art keywords
mli
automatic encoder
layer
optimized
thickness
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202110932572.3A
Other languages
English (en)
Other versions
CN113779869A (zh
Inventor
谭宏博
吴昊
许张良
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Xian Jiaotong University
Original Assignee
Xian Jiaotong University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Xian Jiaotong University filed Critical Xian Jiaotong University
Priority to CN202110932572.3A priority Critical patent/CN113779869B/zh
Publication of CN113779869A publication Critical patent/CN113779869A/zh
Application granted granted Critical
Publication of CN113779869B publication Critical patent/CN113779869B/zh
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00Computer-aided design [CAD]
    • G06F30/20Design optimisation, verification or simulation
    • G06F30/27Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00Computer-aided design [CAD]
    • G06F30/10Geometric CAD
    • G06F30/15Vehicle, aircraft or watercraft design
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00Computer-aided design [CAD]
    • G06F30/10Geometric CAD
    • G06F30/17Mechanical parametric or variational design
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/04Architecture, e.g. interconnection topology
    • G06N3/045Combinations of networks
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/08Learning methods
    • G06N3/088Non-supervised learning, e.g. competitive learning
    • GPHYSICS
    • G16INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16CCOMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
    • G16C60/00Computational materials science, i.e. ICT specially adapted for investigating the physical or chemical properties of materials or phenomena associated with their design, synthesis, processing, characterisation or utilisation
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F2111/00Details relating to CAD techniques
    • G06F2111/06Multi-objective optimisation, e.g. Pareto optimisation using simulated annealing [SA], ant colony algorithms or genetic algorithms [GA]
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02TCLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T90/00Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Geometry (AREA)
  • General Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Computing Systems (AREA)
  • Computer Hardware Design (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Software Systems (AREA)
  • Computational Linguistics (AREA)
  • Computational Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Mathematical Physics (AREA)
  • Data Mining & Analysis (AREA)
  • Biophysics (AREA)
  • Health & Medical Sciences (AREA)
  • Pure & Applied Mathematics (AREA)
  • Biomedical Technology (AREA)
  • Molecular Biology (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Automation & Control Theory (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Medical Informatics (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Investigating Or Analyzing Materials Using Thermal Means (AREA)

Abstract

一种基于自动编码器反演的多层绝热材料优化方法,利用自动编码器模型能够良好预测反演的特点,将热流密度、厚度构成的优化目标与待优化设计参数所组成的样本集进行SVD分解,获得对应设计参数及优化目标的正交基;采用最小二乘法计算待优化目标所对应的正交基系数,从而快速预测待优化目标所对应的设计参数;本发明可以直接由一步计算获得设计厚度下热流密度的下边界,可获得所有反射屏上的温度分布。

Description

一种基于自动编码器反演的多层绝热材料优化方法
技术领域
本发明属于低温绝热技术领域,具体涉及到一种基于自动编码器反演的多层绝热材料优化方法。
背景技术
在航天低温系统中,由于被保温件往往处于狭窄空间之中,预留给保温材料的空间非常有限,在这样的工程限制条件下,对多层绝热材料的设计往往需要顾及到材料厚度及绝热性能两个指标,因此,变密度多层绝热材料(Variable-Density MultilayerInsulation,简称“VD-MLI”)被提出并广泛运用,变密度多层绝热材料是在常规多层绝热材料的基础上,将整个多层绝热材料设计成多个层密度(单位厚度内辐射屏的数量)区域的组合,由于不同温度区间内的辐射热流密度不同,可通过调节层密度使材料更好地反射辐射热流,因此变密度多层绝热材料的绝热性能较常规定密度多层绝热材料更优。
在变密度多层绝热的设计方法中,最为常用的方法即为NASA所提出的Lockheed模型及Layer-by-layer模型,Layer-by-layer模型通过逐层计算反射屏处的温度获得多层绝热材料的热物性,Lockheed模型则通过大量实验数据,将不同温度区间内用层密度拟合热流密度的一个半经验系数的表达式。
在对多层绝热材料的优化方法中,Lockheed模型通过推导表观导热系数对层密度的导数的表达式,来获得不同温度区域内的最优层密度,但在工程设计中,往往需要某个厚度下最优的多层绝热材料搭配方案,但由于某个定厚度往往可以有多种变密度的搭配方案,不同的变密度搭配方案却具备不同的热流密度,因此,Lockheed模型无法直接得到对应厚度下的最小热流密度搭配方案,一般需要不断尝试多种层密度搭配以确定最小热流密度。
Layer-by-layer模型中,所有的物理参数含义明确,可以获得不同反射屏处的温度分布,但是无法直接用于优化;Lockheed模型可直接用于优化,但是存在半经验系数,且无法获得所有反射屏处的温度分布。
发明内容
为了克服上述现有技术的缺点,本发明的目的在于提供了一种基于自动编码器反演的多层绝热材料优化方法,可以直接由一步计算获得设计厚度下的最小热流密度,同时可获得所有反射屏上的温度分布。
为了达到上述目的,本发明采取的技术方案为:
一种基于自动编码器反演的多层绝热材料优化方法,包括以下步骤:
第一步,参数化,MLI的设计参数表示为元数组的重复组合,元数组为1层铝箔与n层玻纤纸的搭配方案,[1,2]表示一层铝箔一层玻纤纸,[1,2,2]表示表示一层铝箔两层玻纤纸……,采用三个密度区的搭配方案,即给定元数组分别为:
elementpack1=[1,2]
elementpack2=[1,2,2]
elementpack3=[1,2,2,2]
则整个多层绝热材料的设计表示为:
MLI=[elementpack1,repmat(elementpack1,k1),
elementpack2,repmat(elementpack2,k2),
elementpack3,repmat(elementpack3,k3)]
其中k1,k2,k3分别为元数组的重复次数,即为待优化设计参数;
第二步,给定n组待优化设计参数组成MLI设计参数样本集MLIn,n为样本数,则MLI1=[k11,k21,k31],…,MLIn=[k1n,k2n,k3n],给定热端温度Th及冷端温度Tc,对MLIn进行仿真,得到n个对应样本的热流密度[q]=q1…qn及厚度[d]=d1…dn,将热流密度[q],厚度[d],[MLIn]组成整体样本集[Dataset],热流密度[q]、厚度[d]构成优化目标;
第三步,对整体样本集[Dataset]进行SVD分解,获得待优化设计参数的正交基[basis1]及优化目标的正交基[basis2];
第四步,计算正交基[basis2]的自相关矩阵[M];
第五步,给定优化目标数组[goal]=[d,q],求解优化目标数组[goal]与正交基[basis2]的相关矩阵Φ;
第六步,最小二乘法拟合优化目标数组[goal]的正交基系数;
第七步,计算优化目标的对应设计参数Dp
第八步,由Layer-by-layer模型对Dp进行仿真,得到待优化设计参数下MLI的热流密度qv、厚度dv、温度分布T和层密度N*
第九步,将第八步得到的热流密度、厚度的多层绝热材料用于低温容器或者航天低温绝热元件的低温绝热场合。
所述的一种基于自动编码器反演的多层绝热材料优化方法中采用SVD自动编码器方法能够用PCA、去噪自动编码器、稀疏自动编码器、变分自动编码器的自动编码器技术替换。
本发明的有益效果为:
本发明利用自动编码器模型能够良好预测反演的特点,将优化目标与待优化设计参数所组成的样本集进行SVD分解,获得对应设计参数及优化目标的正交基;采用最小二乘法计算待优化目标所对应的正交基系数,从而快速预测待优化目标所对应的设计参数,经验证,若给定的MLI厚度下能够达到所需要的热流密度,则直接得到设计参数,若无法达到所需的热流密度,只要所给定的目标热流密度小于最小热流密度,则验证所获得的热流密度即为该厚度下的最小热流密度。
相较于Lockheed多次调整层密度以获得最小热流密度的方式,本发明可以直接由一步计算获得设计厚度下的最小热流密度,采用Layer-by-layer模型仿真进行验证,即可获得所有反射屏上的温度分布,改善了Lockheed模型反复调整层密度的优化方法及无法得到所有反射屏处温度分布的缺点。
附图说明
图1为本发明实施例的示意图。
图2为实施例30mm厚度下最优热流密度的MLI温度分布。
具体实施方式
下面结合实施例和附图对本发明做进一步详细描述,实施例设计一个77K温区30mm厚的变密度多层绝热材料,获得在该30mm厚度下所能达到的最小热流密度的MLI搭配方案。
参照图1,一种基于自动编码器反演的多层绝热材料优化方法,在MATLAB程序中,包括以下步骤:
第一步,参数化,MLI的设计参数表示为元数组的重复组合,元数组为1层铝箔与n层玻纤纸的搭配方案,[1,2]表示一层铝箔一层玻纤纸,[1,2,2]表示表示一层铝箔两层玻纤纸……,为了在工程上便于实施,采用三个密度区的搭配方案,即给定元数组分别为:
elementpack1=[1,2]
elementpack2=[1,2,2]
elementpack3=[1,2,2,2]
则整个多层绝热材料的设计表示为:
MLI=[elementpack1,repmat(elementpack1,k1),
elementpack2,repmat(elementpack2,k2),
elementpack3,repmat(elementpack3,k3)]
其中k1,k2,k3分别为元数组的重复次数,即为待优化设计参数;
本实施例由采样方法生成n组待优化设计参数MLIn=[k1i,k2i,k3i],其中i=1,2,3…,n,k1,k2,k3分别为元数组elementpack1=[1,2],elementpack2=[1,2,2],elementpack3=[1,2,2,2]的循环次数;
第二步,给定n组待优化设计参数组成MLI设计参数样本集MLIn,n为样本数,则MLI1=[k11,k21,k31],…,MLIn=[k1n,k2n,k3n],给定热端温度Th及冷端温度Tc,对MLIn进行仿真,得到n个对应样本的热流密度[q]=q1…qn及厚度[d]=d1…dn,将热流密度[q],厚度[d],[MLIn]组成整体样本集[Dataset],热流密度[q]、厚度[d]构成优化目标;
第三步,对整体样本集[Dataset]进行SVD分解,获得待优化设计参数的正交基[basis1]及优化目标的正交基[basis2];
第四步,编码,计算正交基[basis2]的自相关矩阵[M];
第五步,编码,给定优化目标数组[goal]=[d,q],求解优化目标数组[goal]与正交基[basis2]的相关矩阵Φ;
第六步,拟合优化目标数组[goal]的正交基系数,b=[M]\ΦT
第七步,解码,获得优化目标的对应设计参数Dp=[b]*[basis1];
第八步,验证,采用Layer-by-layer模型对Dp进行仿真,得到待优化设计参数的MLI热流密度qv、厚度dv、温度分布T和层密度分布N*,实施例30mm厚度下最优热流密度的MLI温度分布如图2所示;
第九步,将第八步得到的热流密度、厚度的多层绝热材料用于低温容器或者航天低温绝热元件等低温绝热场合。
表1实施例中的具体参数值
Figure BDA0003211654970000061
Figure BDA0003211654970000071
表1为实施例中的具体参数值,由表1可知,在30mm厚度下,给出一个极小的热流密度为0.20W/m2(已知该厚度下的最小热流密度为0.3892W/m2)时,该自动编码器反演算法给出了30mm厚度下所能达到的最小热流密度qv=0.3872W/m2,与0.3892W/m2的验证值偏差为0.55%,验证厚度dv=29.79mm,与30mm厚度误差为0.7%,验证了本发明方法良好的反演及寻优性能。

Claims (2)

1.一种基于自动编码器反演的多层绝热材料优化方法,其特征在于,包括以下步骤:
第一步,参数化,MLI的设计参数表示为元数组的重复组合,元数组为1层铝箔与n层玻纤纸的搭配方案,[1,2]表示一层铝箔一层玻纤纸,[1,2,2]表示表示一层铝箔两层玻纤纸……,采用三个密度区的搭配方案,即给定元数组分别为:
elementpack1=[1,2]
elementpack2=[1,2,2]
elementpack3=[1,2,2,2]
则整个多层绝热材料的设计表示为:
MLI=[elementpack1,repmat(elementpack1,k1),
elementpack2,repmat(elementpack2,k2),
elementpack3,repmat(elementpack3,k3)]
其中k1,k2,k3分别为元数组的重复次数,即为待优化设计参数;
第二步,给定n组待优化设计参数组成MLI设计参数样本集MLIn,n为样本数,则MLI1=[k11,k21,k31],…,MLIn=[k1n,k2n,k3n],给定热端温度Th及冷端温度Tc,对MLIn进行仿真,得到n个对应样本的热流密度q1…qn及厚度d1…dn,将热流密度[q],厚度[d],[MLIn]组成整体样本集[Dataset],热流密度[q]、厚度[d]构成优化目标;
第三步,对整体样本集[Dataset]进行SVD分解,获得待优化设计参数的正交基[basis1]及优化目标的正交基[basis2];
第四步,计算正交基[basis2]的自相关矩阵[M];
第五步,给定优化目标数组[goal]=[d,q],求解优化目标数组[goal]与正交基[basis2]的相关矩阵Φ;
第六步,最小二乘法计算优化目标数组[goal]的正交基系数;
第七步,计算优化目标的对应设计参数Dp
第八步,由Layer-by-layer模型对Dp进行仿真,得到待优化设计参数下MLI的热流密度qv、厚度dv、温度分布T和层密度N*
第九步,将第八步得到的热流密度、厚度的多层绝热材料用于低温容器或者航天低温绝热元件的低温绝热场合。
2.根据权利要求1所述的一种基于自动编码器反演的多层绝热材料优化方法,其特征在于:所述的一种基于自动编码器反演的多层绝热材料优化方法中采用SVD自动编码器方法能够用PCA、去噪自动编码器、稀疏自动编码器、变分自动编码器的自动编码器技术替换。
CN202110932572.3A 2021-08-13 2021-08-13 一种基于自动编码器反演的多层绝热材料优化方法 Active CN113779869B (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110932572.3A CN113779869B (zh) 2021-08-13 2021-08-13 一种基于自动编码器反演的多层绝热材料优化方法

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110932572.3A CN113779869B (zh) 2021-08-13 2021-08-13 一种基于自动编码器反演的多层绝热材料优化方法

Publications (2)

Publication Number Publication Date
CN113779869A CN113779869A (zh) 2021-12-10
CN113779869B true CN113779869B (zh) 2022-12-09

Family

ID=78837940

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110932572.3A Active CN113779869B (zh) 2021-08-13 2021-08-13 一种基于自动编码器反演的多层绝热材料优化方法

Country Status (1)

Country Link
CN (1) CN113779869B (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114647950B (zh) * 2022-04-02 2024-02-20 西安交通大学 一种基于代理模型的变密度高真空多层绝热结构优化方法

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111898237A (zh) * 2020-06-01 2020-11-06 哈尔滨工业大学 材料多热物性参数反演测量用并行模拟退火快速优化方法
CN112856208A (zh) * 2020-12-29 2021-05-28 西南石油大学 一种液氦储罐复合变密度多层绝热结构变密度优化方法

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111898237A (zh) * 2020-06-01 2020-11-06 哈尔滨工业大学 材料多热物性参数反演测量用并行模拟退火快速优化方法
CN112856208A (zh) * 2020-12-29 2021-05-28 西南石油大学 一种液氦储罐复合变密度多层绝热结构变密度优化方法

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
基于瞬态热传导反问题反演材料随温度变化的导热系数;崔苗等;《中国电机工程学报》;20120515(第14期);全文 *
航天器多层隔热材料边缘漏热分析与设计;戴勇超等;《宇航学报》;20140130(第01期);全文 *

Also Published As

Publication number Publication date
CN113779869A (zh) 2021-12-10

Similar Documents

Publication Publication Date Title
Baldinelli et al. Windows thermal resistance: Infrared thermography aided comparative analysis among finite volumes simulations and experimental methods
Davie et al. Coupled heat and moisture transport in concrete at elevated temperatures—effects of capillary pressure and adsorbed water
CN113779869B (zh) 一种基于自动编码器反演的多层绝热材料优化方法
Asdrubali et al. Influence of cavities geometric and emissivity properties on the overall thermal performance of aluminum frames for windows
Shemelin et al. Detailed modeling of flat plate solar collector with vacuum glazing
Ismail et al. A comparative study of naturally ventilated and gas filled windows for hot climates
CN113688475B (zh) 一种基于梯度信息的多层绝热材料仿真设计方法
Fang et al. Effect of glass thickness on the thermal performance of evacuated glazing
Hart Numerical and experimental validation for the thermal transmittance of windows with cellular shades
Karatasou et al. Detection of low-dimensional chaos in buildings energy consumption time series
Memon Thermal Conductivity Measurement of Vacuum Tight Dual-Edge Seal for the Thermal Performance Analysis of Triple Vacuum Glazing
Naylor et al. Evaluation of an approximate method for predicting the U value of a window with a between-panes blind
Ciampi et al. On the optimization of building envelope thermal performance: Multi-layered wall design to minimize heating and Cooling plant intervention in the case of time varying external temperature fields
Alongi et al. Measuring the thermal resistance of double and triple layer pneumatic cushions for textile architectures
Sharda et al. Heat transfer through glazing systems with inter-pane shading devices: a review
Gustavsen et al. Natural convection effects in three-dimensional window frames with internal cavities
Sambou et al. Theoretical and experimental study of heat transfer through a vertical partitioned enclosure: application to the optimization of the thermal resistance
Griffiths et al. Experimental characterization and detailed performance prediction of a vacuum glazing system fabricated with a low temperature metal edge seal, using a validated computer model
Xamán et al. Effect of Heat Conduction of SnS-Cu x S Solar Control Coated Semitransparent Wall on Turbulent Natural Convection in a Square Cavity
Sharda et al. Statistical evaluation of U-value of a window with inter-pane blinds
CN114647950B (zh) 一种基于代理模型的变密度高真空多层绝热结构优化方法
Zhao Investigation of heat transfer performance in fenestration system based on finite element methods
Rakotomahefa et al. Zonal network solution of temperature profiles in a ventilated wall module
Saber et al. Evaluation and use of airspaces for thermal resistance in buildings
Gustavsen et al. Two-dimensional CFD and conduction simulations of heat transfer in horizontal window frames with internal cavities

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant