检索结果-内蒙古大学图书馆

Fast Solutions Enhancing using a Copula-based EDA and SVM for many-objective problems

IFAC-PapersOnLine 2016年第12期49卷 781-786页

作者： Cheriet, Abdelhakim Cherif, Foudil Taleb-Ahmed, Abdelmalik LESIA Laboraroty University of Biskra Algeria LAMIH Electrical Engineering Department Valenciennes United States

In this paper we propose a new Copula-based Estimation of Distribution Algorithm, to solve Many-objective optimization problem and to get new optimal solutions in very court time. Our algorithm uses the proprieties of Copula and exploits their statistical properties to make new solutions using the founded optimal solutions through the estimation of their distribution. The first step of the proposed Copula-based Estimation of Distribution Algorithm (CEDA-SVM) is taking initial solutions offered by any MOEA (multi objective evolutionary Algorithm), and then creates Copulas to estimate their distribution, and we use Support Vector Machine (SVM) to learn the Pareto solutions model; those Copulas will be used to generate new solutions and SVM to avoid the expensive function evaluations. The idea of using the estimated distribution of the optimal solutions helps CEDA-SVM to avoid running the optimizer ( MOEA ) every time we need new alternatives solutions when the founded ones are not satisfactory. We tested CEDA-SVM on a set of many-objective benchmark problems traditionally used by the community, namely DTLZ (1, 2, 3, and 4) with different dimensions (3, 5, 8, 10, and 15). We used CEDA along with MOEA/D-Schy and MOEA/D-BI as two examples of MOEA thus resulting in two variants CEDA-MOAE/D-Scy and CEDA-MOEA/D-BI and compare them with MOEA/D-Schy and MOEA/D-BI. The results of our experiments show that, with both variants of CEDA-SVM, new solutions can be obtained in a very small time compared to the other algorithms. © 2016

关键词： evolutionary algorithms Distribution functions multiobjective optimization Optimal systems Support vector machines Bench mark problems Copula Estimation of distribution algorithms Initial solution Many objective optimizations multi objective evolutionary algorithms Optimal solutions Statistical properties

来源：评论

学校读者我要写书评

暂无评论

multi-criteria multi-constrained Aerodynamic Optimization of Civil Tiltrotor Empennage Surfaces

Multi-criteria Multi-constrained Aerodynamic Optimization of...

引用

AIAA Aviation Forum and Exposition

作者： Battiston, A. Ponza, R. Benini, E. Bernini, G. Pecoraro, M. HIT09 Srl I-35127 Padua Italy Univ Padua Dept Ind Engn I-35131 Padua Italy Leonardo SpA Helicopter Div I-21017 Cascina Costa Di Samarat Italy

ISBN: (数字)9781624106101

ISBN: (纸本)9781624106101

The present work describes the overall optimization strategy that has been adopted for the enhancement of the aerodynamic performance of a civil tiltrotor empennage surfaces. The optimization process has been designed around GeDEA-II, a multi-objective evolutionary Algorithm developed at University of Padua. The optimization algorithm has been used in two different cases: a two-dimensional optimization of the empennage airfoil and a threedimensional optimization of the empennage winglets, patented by Leonardo Helicopters under the name of finlets. Results demonstrate the effectiveness of the optimization strategies for both the cases. A parametric study of the empennage planform has also been conducted with the aid of an artificial neural network, in order to assess the variations in aerodynamic performance for different geometries.

关键词： Tiltrotor Airframes Aerodynamic Performance Symmetric Airfoil Artificial Neural Network Optimization Algorithm multi objective evolutionary algorithms Leonardo Helicopters Aerodynamic Coefficients Aspect Ratio

来源：评论

学校读者我要写书评

暂无评论

Interactive Explanation of Entry, Descent, and Landing Simulations

Interactive Explanation of Entry, Descent, and Landing Simul...

引用

AIAA Science and Technology Forum and Exposition (AIAA SciTech)

作者： De Leon, Samalis Santini Selva, Daniel Way, David W. Texas AM Univ Dept Aerosp Engn Aerosp Engn College Stn TX 77843 USA NASA Langley Res Ctr Hampton VA 23666 USA

ISBN: (数字)9781624105951

ISBN: (纸本)9781624105951

Entry, Descent, and Landing (EDL) architecture analysis relies on uncertainty quantification methods, such as Monte Carlo dispersion analysis, to assess system performance, and identify areas of risk. These simulations are critical throughout the entire mission lifecycle due to the inherent limitations of system verification and validation on Earth. As a mission lifecycle progresses, fidelity and complexity of these simulations increase, leading to large datasets that have to be manually examined by subject matter experts to identify correlations between parameters and calculate figures of merit. Motivated by the high cognitive load imposed by this process, this paper discusses the use of a cognitive assistant to provide a platform for interactive and collaborative explanation of EDL architecture analysis. The paper starts by describing the process of architecture analysis of EDL systems, identifying some of the main challenges leading to high cognitive workload and motivating the use of cognitive assistants. We then present a short survey of the techniques used to explain complex engineering simulations. The general architecture of the Daphne/EDL cognitive assistant is then described, focusing on the use case of explaining the results of a set of EDL simulations. Three functions are described in detail, namely 1) summarizing the statistics of large datasets (summarization), 2) identifying the input variables that appear to be driving the output variables (sensitivity analysis), and 3) identifying features and behaviors that appear to be common among failing cases or some other region of interest of the design space (association rule mining).

关键词： Sensitivity Analysis Planets Cumulative Distribution Function Black Box Monte Carlo Simulation Convolutional Neural Network Data Mining Techniques Analysis of Variance multi objective evolutionary algorithms Flight Path Angle

来源：评论

学校读者我要写书评

暂无评论

A Mixed Integer Efficient Global Optimization Algorithm with multiple Infill Strategy - Applied to a Wing Topology Optimization Problem

A Mixed Integer Efficient Global Optimization Algorithm with...

引用

AIAA Science and Technology (SciTech) Forum and Exposition

作者： Roy, Satadru Crossley, William A. Stanford, Bret K. Moore, Kenneth T. Gray, Justin S. Purdue Univ Aeronaut & Astronaut 701 W Stadium Ave W Lafayette IN 47907 USA NASA Langley Res Ctr Aeroelastic Branch 218 Dodd Blvd Hampton VA 23681 USA DB Consulting Grp Inc Cleveland OH 44135 USA NASA Glenn Res Ctr Cleveland OH 44135 USA

ISBN: (数字)9781624105784

ISBN: (纸本)9781624105784

With the advancement in high performance computing and numerical optimization techniques, engineering design optimization problems are becoming more complex, larger scale, higher fidelity, and computationally more demanding, requiring longer run times than ever before. There exists methodologies and techniques that can address some of these challenges but very few can address all, and most are limited in the extent that these concerns can be addressed. With the goal of addressing such challenging engineering problems, we developed a new optimization algorithm, named AMIEGO, that combines concepts from surrogate-based optimization approaches, gradient-based numerical methods, Partial Least Squares, evolutionary algorithms, and Branch-and-Bound, providing newer capabilities that were not previously perceived. The effort here builds upon this previously developed optimization algorithm to include multiple infill sampling capability that combines the concept of generalized expected improvement function, unsupervised learning, and multi-objective evolutionary technique. To demonstrate, AMIEGO with the multiple infill capability (called AMIEGO-MIMOS) solves a series of increasingly difficult engineering design optimization problems. The results reveal the performance of the new approach is problem dependent. When applied to a ten-bar truss problem, the newly proposed multiple infill strategy consistently leads to a better design solutions when compared to the existing CPTV method (implemented with the context of the AMIEGO algorithm). On the other hand, when applied to a mixed-integer high fidelity wing topology optimization problem - MIMOS, despite showing a steeper convergence at the start, eventually leads to an inferior solution as compared to CPTV approach. These results also reveal that a small number of starting points, in general, are sufficient to lead to a good overall solution.

关键词： Optimization Algorithm Numerical Optimization Trusses multi objective evolutionary algorithms High Performance Computing Surrogate Model Wingbox Kernel Functions Parallel Computing Aspect Ratio

来源：评论

学校读者我要写书评

暂无评论

Effectiveness of Surrogate-Based Optimization algorithms for System Architecture Optimization

Effectiveness of Surrogate-Based Optimization Algorithms for...

引用

AIAA Aviation Forum and Exposition

作者： Bussemaker, Jasper H. Barton, Nathalie Lefebvre, Thierry Ciampa, Pier D. Nagel, Bjoern DLR German Aerosp Ctr Inst Syst Architectures Aeronaut Aircraft Design & Syst Integrat Hamburg Germany Univ Toulouse DTIS ONERA Informat Proc & Syst Dept Toulouse France DLR German Aerosp Ctr Inst Syst Architectures Aeronaut Hamburg Germany

ISBN: (数字)9781624106101

ISBN: (纸本)9781624106101

The design of complex system architectures brings with it a number of challenging issues, among others large combinatorial design spaces. Optimization can be applied to explore the design space, however gradient-based optimization algorithms cannot be applied due to the mixed-discrete nature of the design variables. It is investigated how effective surrogate-based optimization algorithms are for solving the black-box, hierarchical, mixed-discrete, multiobjective system architecture optimization problems. Performance is compared to the NSGAII multi-objective evolutionary algorithm. An analytical benchmark problem that exhibits most important characteristics of architecture optimization is defined. First, an investigation into algorithm effectiveness is performed by measuring how accurately a known Pareto-front can be approximated for a fixed number of function evaluations. Then, algorithm efficiency is investigated by applying various multi-objective convergence criteria to the algorithms and establishing the possible trade-off between result quality and function evaluations needed. Finally, the impact of hidden constraints on algorithm performance is investigated. The code used for this paper has been published.

关键词： Optimization Algorithm multi objective evolutionary algorithms Black Box algorithms Convergence Surrogate Model Gaussian Process Design of Experiments Computational Fluid Dynamics Systems Engineering Genetic Algorithm

来源：评论

学校读者我要写书评

暂无评论

Linguistic Summarization of Time Series Data using Genetic algorithms

Linguistic Summarization of Time Series Data using Genetic A...

引用

7th Biannual Conference of the European-Society-for-Fuzzy-Logic-and-Technology (EUSFLAT)/17th Annual LFA Meeting

作者： Castillo-Ortega, Rita Marin, Nicolas Sanchez, Daniel Tettamanzi, Andrea G. B. Univ Granada Granada Spain European Ctr Soft Comp Mieres Asturias Spain Univ Milan Crema CR Italy

ISBN: (纸本)9789078677000

In this paper, the use of an evolutionary approach when obtaining linguistic summaries from time series data is proposed. We assume the availability of a hierarchical partition of the time dimension in the time series. The use of natural language allows the human users to understand the resulting summaries in an easy way. The number of possible final summaries and the different ways of measuring their quality has taken us to adopt the use of a multi objective evolutionary algorithm. We compare the results of the new approach with our previous greedy algorithms.

关键词： Linguistic Summarization multi objective evolutionary algorithms Time Series Dimensional Data Model Fuzzy Logic

来源：评论

学校读者我要写书评

暂无评论

From Design Assistants to Design Peers: Turning Daphne into an AI Companion for Mission Designers

From Design Assistants to Design Peers: Turning Daphne into ...

引用

AIAA Science and Technology (SciTech) Forum and Exposition

作者： Viros, Antoni Selvat, Daniel Texas A&M Univ College Stn TX 77843 USA

ISBN: (数字)9781624105784

ISBN: (纸本)9781624105784

This paper describes the changes done to Daphne, a virtual assistant for architecting earth observing satellite systems, to turn it from a reactive assistant that only acts when asked by the user into a proactive assistant that can perform actions without not directly linked to a user request, taking its own initiative. Specifically, the paper describes a new way for Daphne to communicate with the user with Websockets that allows for a broader range of interactivity. The new features enabled by this new communication system are: (1) an agent that searches over the space of designs and shows interesting designs to the user;(2) an agent that tries to encourage the user to diversify their search of the tradespace;and (3) a live recommender system that acts when the user is modifying a certain design by suggesting changes that are likely to improve cost and/or performance. The paper also describes changes in the existing sub-systems as well as the interface to accommodate the new systems and interactivity. Finally, the paper has a short discussion on how a common user case scenario would unfold with all these new features.

关键词： Satellite Constellations Earth Communication System Scatter Plot Integrated Development Environments Genetic Algorithm Mobile Computing RADAR Human Robot Interaction multi objective evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

Design Optimization of multi-Stage Axial-Flow Compressor Using Machine Learning Models

Design Optimization of Multi-Stage Axial-Flow Compressor Usi...

引用

AIAA SciTech Forum

作者： Zhang, Xiawen Nichols, Andrew Thomos Zhang, Chuhua Liu, Feng Univ Calif Irvine Dept Mech & Aerosp Engn Irvine CA 92697 USA Xi An Jiao Tong Univ Sch Energy & Power Engn Xian 710049 Shaanxi Peoples R China

ISBN: (数字)9781624107115

ISBN: (纸本)9781624107115

A rapid and accurate mean-line design optimization method for multi-stage axial-flow compressor is established and implemented on a 3.5-stage subsonic compressor. The accuracy of performance prediction using both empirical models and metamodels is compared. The aerodynamic matching of intra- and inter-stage compressor is investigated. The design variables are optimized for overall multi-stage performance improvement. The results show that the metamodels for loss coefficient, deviation angle and aerodynamic blockage exhibit better accuracy compared to the empirical models. For the investigated compressor, the design variables of stage 3 have dominant effects on the adiabatic efficiency. The pressure ratio on stage 3 should be less than the averaged distribution for higher efficiency. The stage inlet axial Mach number and flow angle have similar influence on the adiabatic efficiency. Increase of these two design variables results in increase of loading on stator 3 while increase of inter-stage hub radius results in increase of loading on rotor 3. After the optimization, higher adiabatic efficiency at design point and wider stall margin have been achieved.

关键词： Design Optimization multi Stage Compressors Machine Learning Aerodynamic Design Aerodynamic Performance Inlet Flow CFD simulation Aspect Ratio multi objective evolutionary algorithms Mass Flow Rate

来源：评论

学校读者我要写书评

暂无评论

Integrated Shape and Trajectory Optimisation of Hypersonic Waveriders

Integrated Shape and Trajectory Optimisation of Hypersonic W...

引用

AIAA SciTech Forum

作者： Carvalho, Jose Mooij, Erwin Delft Univ Technol Fac Aerosp Engn Astrodynam & Space Miss Delft Netherlands GNC Engn GMV Lisbon Portugal

ISBN: (数字)9781624107115

ISBN: (纸本)9781624107115

This research performs a surrogate-assisted shape optimisation of hypersonic waveriders, where the trajectories of each shape are optimised with a multi-objective evolutionary algorithm for heat-load and cross-range. A study on the best evolutionary algorithm, node control strategy for angle of attack and bank angle profiles, and population size to use in the trajectory optimisation phase, are identified. The aerodynamics of the waveriders is computed with a new local surface inclination method blending the modified Newtonian and tangent wedge solutions, while the convective heat flux is computed for the leading edges using the Newton-Kays engineering model. Shape variability is introduced according to the layout of central composite designs, and analysis of variance is applied to identify the shape features driving the two objectives. Shock angle, leading edge radius and overall vehicle dimensions are the strongest drivers, while details on the planform shape are less relevant and should be left for posterior studies. The surrogates are a good approximation of the true fitness functions, so they were optimised in a single-objective framework, producing two optimal waverider designs.

关键词： Trajectory Optimization Lift Force Coefficient Leading Edge Bluntness Heat Flux Aerodynamic Performance Central Composite Designs multi objective evolutionary algorithms Waverider Design Pressure Coefficient Hypersonic Flight

来源：评论

学校读者我要写书评

暂无评论

A Cognitive Approach to Load Balancing for Green Houses

A Cognitive Approach to Load Balancing for Green Houses

引用

General Meeting of the IEEE-Power-and-Energy-Society (PES)

作者： Lugo-Cordero, Hector M. Fuentes-Rivera, Abigail Guha, Ratan K. Ortiz-Rivera, Eduardo I. Univ Cent Florida Dept Elect Engn & Comp Sci Orlando FL 32816 USA Univ Puerto Rico Dept Elect & Comp Engn Mayaguez PR 00681 USA

ISBN: (纸本)9781457710018

In this paper the case study of a smart home powered by solar and wind energy is presented. The benefits of having a smart home that can control the amount of power needed, according to the context of the usage, are also shown. Simulation shows that with a good control of the load it might be possible to reduce the installation costs of the Green Energy System. Furthermore, to support the results, a load balancing algorithm is created based on the Knapsack problem. An economic analysis of the approach is also shown to demonstrate the viability of the project, and how can the intelligence in the home lower the cost.

关键词： Smart Home Context Reasoning Green Energy multi objective evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：