检索结果-内蒙古大学图书馆

A robust optimization for damage detection using multiobjective genetic algorithm, neural network and fuzzy decision making

引用

INVERSE PROBLEMS IN SCIENCE AND ENGINEERING 2020年第1期28卷 21-46页

作者： Lopes Alexandrino, Patricia da Silva Gomes, Guilherme Ferreira Cunha, Sebastiao Simoes, Jr. Univ Fed Itajuba Mech Engn Inst Itajuba MG Brazil

An inverse problem of damage identification and localization in a structure is modelled as a robust optimization problem. In the robust optimization problem, the optimum value and small variations around this optimum value are considered. The structural health monitoring damage detection problem is solved using a multiobjective genetic algorithm. So, the robust optimum value is obtained by solving a multiobjective problem where a functional and a variance function of this functional are used. This variance function is obtained by a Design of Experiment with regression and also through a relation between functional variance and damage parameters found by artificial neural network. As a multiobjective genetic algorithm obtains multiple solutions, a fuzzy decision making technique finds the better tradeoff solution for the problem. Boundary element method is utilized to obtain the distribution of stress to elastostatic problem. Numerical results clearly show that the proposed strategy and the use an optimized fuzzy decision making results in accurate damage identification and represents a powerful tool for structural health monitoring. Based on the analysis and numerical results, suggestions to potential researchers have also been provided for future scopes.

关键词： Damage detection fuzzy decision making multiobjective genetic algorithm artificial neural network boundary element method

来源：评论

学校读者我要写书评

暂无评论

Lifetime maximisation of disjoint wireless sensor networks using multiobjective genetic algorithm

引用

IET WIRELESS SENSOR SYSTEMS 2018年第5期8卷 200-207页

作者： El-Sherif, Mohamed Fahmy, Yasmine Kamal, Hanan Cairo Univ Fac Engn Elect & Commun Dept Giza Egypt

One of the lifetime maximisation methods for wireless sensor network (WSN) depends on organising the dense sensors into groups which can work in a cooperative sequential manner. Each group contains a subset of sensors that cover all the monitored area and is called a complete cover or simply a cover. Increasing the number of organised covers and maximising the covers lifetime enable longer network lifetime. Here, the authors investigate the WSN lifetime problem as a two-objective optimisation problem. The first objective is to find the maximum number of covers. The second objective considers the problem of wasted energy. Minimising the wasted energy in the critical sensors is achieved by defining a difference factor (DF). The DF is an indication of the difference between the critical sensor lifetime and the cover lifetime. This second objective is compared with other choices in the literature such as minimising the overlapping and minimising the variance. This optimisation problem is addressed using non-dominated sorting genetic algorithm-II (NSGA-II). Simulation results are conducted for the network lifetime when using one-objective and different two-objective optimisation problem. The choice of DF as the second objective is proved to overcome drawbacks of other second objectives choices.

关键词： wireless sensor networks genetic algorithms telecommunication network reliability energy measurement minimisation DF two-objective optimisation problem multiobjective genetic algorithm lifetime maximisation methods wireless sensor network WSN lifetime problem nondominated sorting genetic algorithm-II difference factor NSGA-II

来源：评论

学校读者我要写书评

暂无评论

Inserting Co-evolution Information from Contact Maps into a multiobjective genetic algorithm for Protein Structure Prediction

Inserting Co-evolution Information from Contact Maps into a ...

引用

IEEE Congress on Evolutionary Computation (IEEE CEC) as part of the IEEE World Congress on Computational Intelligence (IEEE WCCI)

作者： Rocha, Gregorio K. dos Santos, Karina B. Angelo, Jaqueline S. Custodio, Fabio L. Barbosa, Helio J. C. Dardenne, Laurent E. MCTIC LNCC Petropolis RJ Brazil Univ Fed Juiz De Fora Juiz De Fora MG Brazil

ISBN: (纸本)9781509060177

Protein structure prediction (PSP) can be described as a multiobjective optimization (MO) problem since the energy function involves potentially conflicting terms to be simultaneously optimized. During the last three CASP editions (10th, 11th, and 12th), promising results were achieved with the introduction of co-evolution information, in the form of residues contact maps, in methodologies for PSP. In this paper, a residue-residue contact map potential is introduced into the evaluation function of the GAPF program, and it is optimized using a MO strategy. The Aggregation Tree (AT) method is applied to group in separated objectives the energetic potentials that compose the GAPF's evaluation function. The results are compared with those obtained from two consolidated PSP methods, QUARK and MEAMT.

关键词： Protein Structure Prediction multiobjective genetic algorithm Residue-Residue Contact Maps Aggregation Tree

来源：评论

学校读者我要写书评

暂无评论

Analysis of outrigger numbers and locations in outrigger braced structures using a multiobjective genetic algorithm

引用

STRUCTURAL DESIGN OF TALL AND SPECIAL BUILDINGS 2018年第1期27卷 1-1页

作者： Chen, Yue Zhang, Zhenya Ningbo Univ Technol Sch Civil & Transportat Engn Ningbo 315106 Zhejiang Peoples R China

Due to its advantages, the outrigger braced system has been employed in high-rise structures for the last 3 decades. It is evident that the numbers and locations of outriggers in this system have a crucial impact on the performance of high-rise buildings. In this paper, a multiobjective genetic algorithm (MGA) is applied to an existing mathematical model of outrigger braced structures and a practical project to achieve Pareto optimal solutions, which treat the top drift and core base moment of a high-rise building as 2 trade-off objective functions. MATLAB was employed to explore a multiobjective automatic optimization procedure for the optimal design of outrigger numbers and locations under wind load. In this research, various schemes for the preliminary stages of design can be obtained using MGA. This allows designers and clients easily to compare the performance of structural systems with different numbers of outriggers in different locations. In addition, design results based on MGA offer many other benefits, such as diversity, flexible options for designers, and active client participation.

关键词： high-rise building multiobjective genetic algorithm optimum design outrigger braced system Pareto optimal solution wind load

来源：评论

学校读者我要写书评

暂无评论

Application of a multiobjective genetic algorithm to Reduce Wet Weather Sanitary Sewer Overflows and Surcharge

引用

JOURNAL OF SUSTAINABLE WATER IN THE BUILT ENVIRONMENT 2017年第3期3卷

作者： Itaquy, Bruno Ogidan, Olufunso Giacomoni, Marcio H. Merrick & Co 401 East Sonterra BlvdSuit 250 San Antonio TX 78258 USA Univ Texas San Antonio Dept Civil & Environm Engn One UTSA Circle San Antonio TX 78249 USA

Sanitary sewer overflow (SSO) is the discharge of wastewater from the collection network into the environment. SSOs are significant environmental and public health hazards. The EPA estimates that up to 75,000 SSO events occur in the United States each year. One of the main causes of SSOs is excessive rainfall derived inflow and infiltration into the sanitary sewer network. This study applies a multiobjective genetic algorithm (MOGA) to identify near-optimal solutions to maximize the reduction of the number of SSOs, volume of SSOs, and surcharge, while minimizing costs for sewer rehabilitation. Three approaches are investigated: (1) enhancing the flow capacity of the collection and conveyance system by pipe diameter increase, (2) peak flow reduction using decentralized inline storage tanks, and (3) combining pipe capacity enhancement with inline storages. The approach is tested in a 15.3-square-kilometer sewer network located west of downtown San Antonio, Texas. The results show that the Combination strategy outperforms both the pipe capacity enhancement and the inline storage strategies. Reduction of surcharge lowers the pressure in the entire network and also provides substantial reduction of SSOs volumes. (C) 2017 American Society of Civil Engineers.

关键词： Sanitary sewer overflow multiobjective genetic algorithm Sanitary sewer systems Surcharge

来源：评论

学校读者我要写书评

暂无评论

Optimal design of plasmonic waveguide using multiobjective genetic algorithm

引用

OPTICAL ENGINEERING 2016年第1期55卷 017103-017103页

作者： Jung, Jaehoon Dankook Univ Dept Elect & Elect Engn 152 Jukjeon Ro Yongin 16890 Gyeonggi Do South Korea

An approach for multiobjective optimal design of a plasmonic waveguide is presented. We use a multiobjective extension of a genetic algorithm to find the Pareto-optimal geometries. The design variables are the geometrical parameters of the waveguide. The objective functions are chosen as the figure of merit defined as the ratio between the propagation distance and effective mode size and the normalized coupling length between adjacent waveguides at the telecom wavelength of 1550 nm. (C) 2016 Society of Photo-Optical Instrumentation Engineers (SPIE)

关键词： surface plasmons guided waves waveguides multiobjective genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

Sit-to-Stand Motion Analysis Using multiobjective genetic algorithm Based on Musculoskeletal Model Simulation

引用

IEEJ JOURNAL OF INDUSTRY APPLICATIONS 2016年第3期5卷 236-244页

作者： Yokota, Hiroki Ohshima, Shigemichi Mizuno, Naoki Nagoya Inst Technol Shouwa Ku Gokiso Cho Nagoya Aichi 4668555 Japan Meijo Univ Tempaku Ku 1-501 Shiogamaguchi Nagoya Aichi 4688502 Japan

One of the most vital skills of daily life is the ability to stand from a sitting position. This study aims to use musculoskeletal model simulation to create an optimal sit-to-stand motion without causing stress to the knee joints while activating the weak muscles. Numerical optimization was performed using the musculoskeletal model by applying the multiobjective genetic algorithm. The numerical optimization results indicate that by placing the feet under the chair prior to standing (not bending the upper body visibly forward) during the sit-to-stand movement, it is possible to reduce stress on the knee joints and muscles. To validate this optimized sit-to-stand motion, we performed two experiments. First, we calculated a correlation value between simulation and experimental results relative to muscle activity, and verified that there is a significant correlation. Next, two types of sit-to-stand movements performed by five healthy male subjects were analyzed: spontaneous sitting-to-standing and imitated sitting-to-standing using the optimized motion. The experimental results confirm that the imitated movement reduces the knee joint's maximum torque.

关键词： sit-to-stand motion optimization musculoskeletal model simulation multiobjective genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

A multiobjective Hybrid genetic algorithm for TFT-LCD Module Assembly Scheduling

引用

IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING 2014年第3期11卷 692-705页

作者： Chou, Che-Wei Chien, Chen-Fu Gen, Mitsuo Natl Tsing Hua Univ Dept Ind Engn & Engn Management Hsinchu 30013 Taiwan Fuzzy Log Syst Inst Fukuoka 8200067 Japan

The thin-film transistor-liquid crystal display (TFT-LCD) module assembly production is a flexible job-shop scheduling problem that is critical to satisfy the customer demands on time. On the module assembly shop floor, each workstation has identical and non-identical parallel machines that access the jobs at various processing velocities depending on the product families. To satisfy the various jobs, the machines need to be set up as the numerous tools to conduct consecutive products. This study aims to propose a novel approach to address the TFT-LCD module assembly scheduling problem by simultaneously considering the following multiple and often conflicting objectives such as the makespan, the weighted number of tardy jobs, and the total machine setup time, subject to the constraints of product families, non-identical parallel machines, and sequence-dependent setup times. In particular, we developed a multiobjective hybrid genetic algorithm (MO-HGA) that hybridizes with the variable neighborhood descent (VND) algorithm as a local search and TOPSIS evaluation technique to derive the best compromised solution. To estimate the validity of the proposed MO-HGA, experiments based on empirical data were conducted to compare the results with conventional approaches. The results have shown the validity of this approach. This study concludes with a discussion of future research directions. Note to Practitioners-Because of short product lifecycles, cycle time reduction and on-time delivery are crucial in high-tech industries such as the TFT-LCD and semiconductor manufacturing. To address these needs in real settings, a novel multiobjective hybrid genetic algorithm (MO-HGA) was developed, hybridizing with a variable neighborhood descent (VND) algorithm as a local search and TOPSIS technique to select the best compromised solution for the TFT-LCD module assembly scheduling problem. Experiments have shown practical viability of this approach. Future studies can be done to exten

关键词： multiobjective genetic algorithm scheduling thin-film transistor-liquid crystal display (TFT-LCD) TOPSIS variable neighborhood descent

来源：评论

学校读者我要写书评

暂无评论

Design-space adaptation method for multiobjective and multidisciplinary optimization

引用

Chinese Journal of Aeronautics 2024年第8期37卷 166-189页

作者： Jongho JUNG Kwanjung YEE Shinkyu JEONG Department of Aerospace Engineering Seoul National UniversitySeoul 08826Republic of Korea Department of Mechanical Engineering Kyunghee UniversityYoungin 17104Republic of Korea

This paper developed a new method that adaptively adjusts a design space by considering the actual solution distribution of a problem to overcome the conventional design-space adaptation method that assumes the solutions distribution to be a normal distribution because the distributions of solutions are rarely normal distributions for real-world *** developed method was applied to nineteen multiobjective test functions that are widely used to evaluate the characteristics and performance of optimization *** results showed that this method adapted the design space to an appropriate design space where the solution existence probability was *** optimization performance achieved using the developed method was higher than that of the conventional ***,the developed method was applied to the conceptual design of an unmanned spacecraft to confirm its validity in real-world design and multidisciplinaryoptimization *** results showed that the Pareto solutions of the developed method were superior to those of conventional ***,the optimization efficiency with the developed method was improved by more than 1.4 times over that of the conventional *** this regard,the developed method has the potential to be applied to complicated real-world optimization problems to achieve better performance and efficiency.

关键词： multiobjective optimization multiobjective genetic algorithm Design-space adaptation Multidisciplinary optimization Hypersonic vehicle

来源：评论

学校读者我要写书评

暂无评论

ARS-Flow 2.0: An enhanced design space exploration flow for accelerator-rich system based on active learning

引用

INTEGRATION-THE VLSI JOURNAL 2025年 101卷

作者： Huang, Shuaibo Ye, Yuyang Yan, Hao Shi, Longxing Southeast Univ Natl ASIC Syst Engn Technol Res Ctr Nanjing Peoples R China

Surrogate model-based design space exploration (DSE) is the mainstream method to search for optimal microarchitecture designs. However, building accurate models for accelerator-rich systems within limited samples is challenging due to their high dimensionality. Additionally, these models often fall into local optima or have difficulty converging. To address these issues, we propose a DSE flow based on active learning, called ARS-Flow. This method features particle-swarm-optimized Gaussian process regression modeling (PSOGPR), a multiobjective genetic algorithm with self-adaptive hyperparameter control (SAMOGA), and a Pareto-regionoriented stochastic resampling method (PRSRS). Using the gem5-SALAM system for evaluation, the proposed method can build more accurate models and find better microarchitecture designs with acceptable runtime costs.

关键词： Design space exploration Accelerator-rich system Active learning Gaussian process regression multiobjective genetic algorithm Pareto region stochastic resampling

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：