检索结果-内蒙古大学图书馆

Process parameters optimization of sheet metal forming in drawing process based on multi-objective genetic algorithm

引用

Zhongguo Jixie Gongcheng/China Mechanical Engineering 2006年第SUPPL.期17卷 74-76页

作者： Pan, Jiangfeng Zhong, Yuexian Yuan, Chaolong Key Lab. for AMMPT Tsinghua University Beijing 100084 China

An optimization model was established with MOGA and numerical simulation, in which several process parameters (e. g. blank-holding force, friction coefficient) were optimization variables, and several forming problems (e.g. crinkling, cracking) were optimization objections. An ANN was built to connect process parameters and simulation results which improved the optimization efficiency. At last a model of the exhaust muffler was provided. The result shows that the forming problems can be avoided via numerical simulation. It indicates that the algorithm has good optimization effect.

关键词： Artificial neural network multi-objective genetic algorithm Sheet drawing

来源：评论

学校读者我要写书评

暂无评论

Fast multi-objective genetic algorithm based on clustering

引用

Jisuanji Yanjiu yu Fazhan/Computer Research and Development 2004年第7期41卷 1081-1087页

作者： Zheng, Jin-Hua Shi, Zhong-Zhi Xie, Yong Lab. of Intelligent Info. Proc. Inst. of Comp. Technol. Chinese Acad. of Sci. Beijing 100080 China Coll. of Info. Eng. Xiangtan Univ. Xiangtan 411105 China

multi-objective genetic algorithm based on Pareto optimum is much suitable for solving multi-objective optimization problems. The relations between individuals and some features about these relations are discussed. It is proved that the individuals of an evolutionary population can be classified by the idea of quick sort. At the same time, the approach to maintain diversity of solutions by clustering algorithms is discussed, and the clustering algorithm based on hierarchical aggregation is also discussed. Then by using the quick sort algorithm and the clustering procedure, an algorithm of constructing a new evolutionary population is proposed. It is shown by theoretic analysis and experimental results that the convergent speed of the algorithm discussed is more efficient than the other existing algorithms.

关键词： Clustering multi-objective genetic algorithm multi-objective optimization

来源：评论

学校读者我要写书评

暂无评论

An Interactive Evaluation Method of Decentralized Procurement Plan by multi-objective genetic algorithm

An Interactive Evaluation Method of Decentralized Procuremen...

引用

International Conference on Data Communication Networking

作者： Ryoji Kobayashi Masakatsu Mori Masaki Samejima Norihisa Komoda Graduate School of Information Science and Technology Osaka University Yokohama Research Laboratory Hitachi Ltd.

ISBN: (纸本)9789898565723

This paper addresses evaluation of a decentralized procurement plan for the support of the discussion among decision-makers with considering a catastrophic disaster. For the evaluation of the decentralized procurement plan, we have formulated the decentralized procurement planning problem as 3-objective optimization problem. However, multiple-objective genetic algorithms (MOGA) to solve the problem take several minutes and display many Pareto solutions. We propose the interactive evaluation method of the decentralized procurement plan that is an expanded interactive MOGA (iMOGA) with loss evaluation simulator and solution selection by characteristics of the decentralized procurement plan. Experimental results show that the proposed method can allow the decision-makers to find their preference solutions with 38% fewer interactions than the basic iMOGA can.

关键词： Supply Chain Decentralized Procurement Plan multi-objective genetic algorithm Interactive Evaluation

来源：评论

学校读者我要写书评

暂无评论

A growing complex network design method with an adaptive multi-objective genetic algorithm and an inner link restructuring method

A growing complex network design method with an adaptive Mul...

引用

Society of Instrument and Control Engineers Annual Conference

作者： Haruki Mizuno Takashi Okamoto Seiichi Koakutsu Hironori Hirata Graduate School of Engineering Chiba University

ISBN: (纸本)9781467322591

Many systems that can be modeled using network structures appear in various fields such as informatics, social science, economics, ecology, biology, and engineering. If these systems can be modeled as complex network systems, a complex network design method that finds a desired network structure can become one of strong tools in large-scale system designs. Conventional complex network design methods generally tackle static networks. On the other hand, a growing complex network design method has been proposed. In this method, the network is grown with determining the link structure of the newly-added node in order to obtain a desired network. In this design method, it is expected that characteristics of the optimization problem solved in the algorithm vary along with growth of the network. However, parameters of the optimization method are fixed;hence, its search process may be inefficient. In the design method, connection targets of a new node are only determined, and the structure of the existing network is not changed. Therefore, if the initial network has a large number of nodes, the desired network may not be obtained by using the design method. In this study, we propose to introduce an inner link restructuring method and an adaptive MOGA, that is, an adaptive SPEA2 into the growing complex network design method to deal with foregoing issues. Then, we confirm the effectiveness of the proposed method through numerical experiments.

关键词： Complex Network multi-objective Optimization Growing Network Network Design multi-objective genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

Modular Granular Neural Networks Optimization with multi-objective Hierarchical genetic algorithm for human recognition based on iris biometric

Modular Granular Neural Networks Optimization with Multi-Obj...

引用

IEEE Congress on Evolutionary Computation

作者： Daniela Sanchez Patricia Melin Oscar Castillo Fevrier Valdez Tijuana Institute of Technology

ISBN: (纸本)9781479904532

In this paper a new model of a multi-objective Hierarchical genetic algorithm (MOHGA) based on the Micro genetic algorithm (μGA) approach for Modular Neural Networks (MNNs) optimization is proposed. The proposed method can divide the data automatically into granules or sub modules, and chooses which data are for the training and which are for the testing phase. The proposed multi-objective genetic algorithm is responsible for determining the number of granules or sub modules and the percentage of data for training that can allow to have better results. The proposed method was applied to human recognition and its applicability with good results is shown, although the proposed method can be used in other applications such as time series prediction and classification.

关键词： Modular Neural Networks Hierarchical genetic algorithms multi-objective genetic algorithm Micro genetic algorithm Granular computing

来源：评论

学校读者我要写书评

暂无评论

Machine learning-based predictive modeling and optimization: Artificial neural network-genetic algorithm vs. response surface methodology for black soldier fly (Hermetia illucens) farm waste fermentation

引用

BIOCHEMICAL ENGINEERING JOURNAL 2025年 218卷

作者： Okoro, Oseweuba Valentine Hippolyte, D. E. Caevel Nie, Lei Karimi, Keikhosro Denayer, Joeri F. M. Shavandi, Armin Univ Libre Bruxelles ULB Ecole Polytech Bruxelles BioMatter Unit Ave FD Roosevelt 50CP 165-61 B-1050 Brussels Belgium Xinyang Normal Univ Coll Life Sci Xinyang 464000 Peoples R China Vrije Univ Brussel Dept Chem Engn B-1050 Brussels Belgium

Recognizing the complexity of non-linear and interdependent biological processes, this study compared the predictive performance of artificial neural network (ANN) models with response surface methodology regression based (RB) models. The research focused on the biological transformation of black soldier fly (Hermetia illucens) farm waste into chitin, facilitated by Lactobacillus paracasei. Key parameters of time (1-7 days), temperature (30-40 degrees C), substrate concentration (7.5-20 wt%), and inoculum concentration (5-15 v/v%), were evaluated for their impact on demineralization and deproteinization subprocesses and subsequently optimized. It was determined that the ANN models outperformed RB models, with R2 values of 0.950 and 0.959 for DP% and DD%, compared to 0.677 and 0.720 for RB models. While both models, optimized using a multi-objective genetic algorithm (MOGA) and a desirability function respectively, produced comparable optimal results, differences emerged in process variable analysis. Main effects plots (RB) and one way partial dependence plots (ANN) revealed conflicting parameter influences, highlighting the limitations of regression models in complex systems. This study highlights the superiority of ANN-MOGA in addressing biological complexity and recommends its use especially if RB models show suboptimal predictive capabilities.

关键词： Artificial neural network multi-objective genetic algorithm Chitin Black solder fly Response surface methodology Waste valorization

来源：评论

学校读者我要写书评

暂无评论

multi-objective genetic algorithms in the study of the genetic code's adaptability

引用

INFORMATION SCIENCES 2018年 425卷 48-61页

作者： de Oliveira, Lariza Laura Freitas, Alex A. Tinos, Renato Univ Sao Paulo Sch Med Ribeirao Preto Ctr Hlth Informat & Informat Ribeirao Preto Brazil Univ Sao Paulo Dept Comp & Math Ribeirao Preto Brazil Univ Kent Sch Comp Canterbury Kent England

Using a robustness measure based on values of the polar requirement of amino acids, Freeland and Hurst (1998) showed that less than one in one million random hypothetical codes are better than the standard genetic code. In this paper, instead of comparing the standard code with randomly generated codes, we use an optimisation algorithm to find the best hypothetical codes. This approach has been used before, but considering only one objective to be optimised. The robustness measure based on the polar requirement is considered the most effective objective to be optimised by the algorithm. We propose here that the polar requirement is not the only property to be considered when computing the robustness of the genetic code. We include the hydropathy index and molecular volume in the evaluation of the amino acids using three multi-objective approaches: the weighted formula, lexicographic and Pareto approaches. To our knowledge, this is the first work proposing multi -objective optimisation approaches with a non-restrictive encoding for studying the evolution of the genetic code. Our results indicate that multi -objective approaches considering the three amino acid properties obtain better results than those obtained by single objective approaches reported in the literature. The codes obtained by the multi -objective approach are more robust and structurally more similar to the standard code. (C) 2017 Elsevier Inc. All rights reserved.

关键词： genetic code genetic algorithms Lexicographic approach multi-objective genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

multi-objective optimization of stamping forming process of head using Pareto-based genetic algorithm

引用

Journal of Central South University 2015年第9期22卷 3287-3295页

作者：周杰卓芳黄磊罗艳 College of Material Science and Engineering Chongqing University

To obtain the optimal process parameters of stamping forming, finite element analysis and optimization technique were integrated via transforming multi-objective issue into a single-objective issue. A Pareto-based genetic algorithm was applied to optimizing the head stamping forming process. In the proposed optimal model, fracture, wrinkle and thickness varying are a function of several factors, such as fillet radius, draw-bead position, blank size and blank-holding force. Hence, it is necessary to investigate the relationship between the objective functions and the variables in order to make objective functions varying minimized simultaneously. Firstly, the central composite experimental(CCD) with four factors and five levels was applied, and the experimental data based on the central composite experimental were acquired. Then, the response surface model(RSM) was set up and the results of the analysis of variance(ANOVA) show that it is reliable to predict the fracture, wrinkle and thickness varying functions by the response surface model. Finally, a Pareto-based genetic algorithm was used to find out a set of Pareto front, which makes fracture, wrinkle and thickness varying minimized integrally. A head stamping case indicates that the present method has higher precision and practicability compared with the "trial and error" procedure.

关键词： stamping forming heads finite element analysis central composite experimental design response surface methodology multi-objective genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

multi-objective optimization of a non-uniform sinusoidal mini-channel heat sink by coupling genetic algorithm and CFD model

引用

APPLIED THERMAL ENGINEERING 2024年第PartA期257卷

作者： Ge, Ya Yin, Weixing Lin, Yousheng He, Kui He, Qing Huang, Si-Min Dongguan Univ Technol Engn Res Ctr Distributed Energy Syst Guangdong Prov Key Lab Distributed Energy Syst Dongguan 523808 Peoples R China

Wavy mini-channel heat sinks (MCHS) can disrupt the development of the thermal boundary layer, resulting in superior performance compared to straight MCHS. For complete utilization of the coolant, this study proposed and optimized a non-uniform sinusoidal MCHS with varying wavelength or varying amplitude along the flow direction. The optimization for five design variables was accomplished through a multi-objective genetic algorithm, where the thermal resistance B or the pressure drop gyp p were defined as two objectives. The computational fluid dynamics (CFD) software was employed to solve all direct problems encountered during the evolutionary process. Compared to the straight MCHS with different channel widths, the optimal designs achieved reductions of 27.74 % in B or 59.51 % in gy p . Simultaneously, all the optimal values of the wavelength ratio and amplitude ratio indicate that enhancing the heat transfer performance downstream is more efficient. It was observed that among the five design variables, the number of wave cycles is the most relevant parameter with a Spearman's correlation up to 0.983. Subsequently, a multiple-criteria decision-making approach was employed to ascertain the best compromise solution to balance the two objectives. Although the B of the best compromise solution could be higher by 38.57 % than that of the lowest B solution, the gyp p presents a more substantial reduction of 92.45 % after the trade-off. Compared to the straight MCHS with the same gy p , the best compromise solution with varying wavelength reduces the B and the standard temperature deviation by 26.20 % and 76.98 % respectively, while lowering the average base temperature by 3.07 K. Therefore, the optimal non-uniform wavy MCHS, along with the optimization approach presented, is meaningful for practical applications.

关键词： Heat sink Non-uniform wavy channel multi-objective genetic algorithm multi-criteria decision-making Heat transfer enhancement

来源：评论

学校读者我要写书评

暂无评论

multi-objective optimization of lithium-ion battery model using genetic algorithm approach

引用

JOURNAL OF POWER SOURCES 2014年 270卷 367-378页

作者： Zhang, Liqiang Wang, Lixin Hinds, Gareth Lyu, Chao Zheng, Jun Li, Junfu Harbin Inst Technol Sch Elect Engn & Automat Harbin 150001 Peoples R China Natl Phys Lab Teddington TW11 0LW Middx England

A multi-objective parameter identification method for modeling of Li-ion battery performance is presented. Terminal voltage and surface temperature curves at 15 degrees C and 30 degrees C are used as four identification objectives. The Pareto fronts of two types of Li-ion battery are obtained using the modified multi-objective genetic algorithm NSGA-II and the final identification results are selected using the multiple criteria decision making method TOPSIS. The simulated data using the final identification results are in good agreement with experimental data under a range of operating conditions. The validation results demonstrate that the modified NSGA-II and TOPSIS algorithms can be used as robust and reliable tools for identifying parameters of multi-physics models for many types of Li-ion batteries. (C) 2014 Elsevier B.V. All rights reserved.

关键词： Parameter identification multi-objective genetic algorithm multi-physics model Lithium-ion battery

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：