检索结果-内蒙古大学图书馆

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

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

Smart outrigger damper system for response reduction of tall buildings subjected to wind and seismic excitations

引用

INTERNATIONAL JOURNAL OF STEEL STRUCTURES 2017年第4期17卷 1263-1272页

作者： Kim, Hyun-Su Kang, Joo-Won Sunmoon Univ Div Architecture Architectural & Civil Engrgineer Asan South Korea Yeungnam Univ Sch Architecture Gyongsan South Korea

The outrigger damper system has recently been proposed to reduce the dynamic response of tall buildings subjected to lateral loads. Previous studies have shown that the outrigger damper system could effectively increase the response reduction capacity of tall buildings. The outrigger damper system was used not only for a response reduction of tall buildings, but also for adjusting the differential column shortening. When an outrigger damper system is designed optimally for wind or earthquake loads, it shows good control performance against each target excitation. On the other hand, the outrigger damper system designed for the wind load cannot effectively control the seismic responses and vice versa. This study examined the control performance of a smart outrigger damper system for reducing both the wind and seismic responses. The smart outrigger damper system was comprised of magnetorheological dampers. A fuzzy logic control algorithm, which was optimized by a multi-objective genetic algorithm, was used to control the smart outrigger damper system. Numerical analysis showed that the smart outrigger damper system could provide superior control performance for the reduction of both wind and earthquake responses compared to the general outrigger system and passive outrigger damper system.

关键词： smart outrigger damper system wind-induced response reduction seismic response control MR damper fuzzy logic controller multi-objective genetic algorithm tall buildings

来源：评论

学校读者我要写书评

暂无评论

Performance enhancement of a small-scale organic Rankine cycle radial-inflow turbine through multi-objective optimization algorithm

引用

ENERGY 2017年 131卷 297-311页

作者： Al Jubori, Ayad M. Al-Dadah, Raya Mahmoud, Saad Univ Birmingham Sch Engn Birmingham B15 2TT W Midlands England Univ Technol Baghdad Baghdad Iraq

An effective methodology that encompasses a mean-line design, three-dimensional CFD analysis and optimization and ORC system modelling of the small-scale ORC radial-inflow turbine is presented. Three-dimensional CFD analysis and a multi-objective optimization algorithm were achieved using ANSYS (R)(17) CFX and Design Exploration based on 3D RANS with a k-omega SST turbulence model. The 3D optimization technique combines a design of the experiment, a response surface method and multi-objective method. The optimization of the blade geometry was performed using 20 design points for both nozzle and rotor blades, based on the B-splines' technique to represent the blade angles and thickness distribution. The number of blades and rotor tip clearance were included as design parameters. The isentropic,efficiency and power output were introduced as an optimization objective with two organic working fluids, namely isopentane and R245fa. The results of the optimized geometry with R245fa showed that the turbine's and cycle's thermal efficiencies were higher by 13.95% and 1738% respectively, compared with a base-line design with a maximum power output of 5.415 kW. Such methodology is proved to be effective as it allows the enhancing of the turbine's and the ORC's system performance throughout to find the optimum blade shape of the turbine stage. (C) 2017 Elsevier Ltd. All rights reserved.

关键词： Small-scale radial-inflow turbine Preliminary mean-line design ORC 3D CFD optimization multi-objective genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

An intelligent support system for automatic detection of cerebral vascular accidents from brain CT images

引用

COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2017年 146卷 109-123页

作者： Hajimani, Elmira Ruano, M. G. Ruano, A. E. Univ Algarve Fac Sci & Technol Faro Portugal Univ Coimbra CISUC Coimbra Portugal Univ Lisbon Inst Super Tecn IDMEC Lisbon Portugal

objective: This paper presents a Radial Basis Functions Neural Network (RBFNN) based detection system, for automatic identification of Cerebral Vascular Accidents (CVA) through analysis of Computed Tomographic (CT) images. Methods: For the design of a neural network classifier, a multi objective genetic algorithm (MOGA) framework is used to determine the architecture of the classifier, its corresponding parameters and input features by maximizing the classification precision, while ensuring generalization. This approach considers a large number of input features, comprising first and second order pixel intensity statistics, as well as symmetry/asymmetry information with respect to the ideal mid-sagittal line. Results: Values of specificity of 98% and sensitivity of 98% were obtained, at pixel level, by an ensemble of non-dominated models generated by MOGA, in a set of 150 CT slices (1,867,602 pixels), marked by a NeuroRadiologist. This approach also compares favorably at a lesion level with three other published solutions, in terms of specificity (86% compared with 84%), degree of coincidence of marked lesions (89% compared with 77%) and classification accuracy rate (96% compared with 88%). (C) 2017 Published by Elsevier Ireland Ltd.

关键词： Neural networks Symmetry features multi-objective genetic algorithm Intelligent support systems Cerebral vascular Accident

来源：评论

学校读者我要写书评

暂无评论

Uncertain multi-objective optimal model of oilfield development planning and its algorithm

引用

JOURNAL OF AMBIENT INTELLIGENCE AND HUMANIZED COMPUTING 2017年第5期8卷 769-779页

作者： Ji, Xiaoyu Yan, Sen Feng, Siyu Renmin Univ China Sch Business Beijing 100872 Peoples R China

In this paper, we discuss the formulation of the oilfield development plan in case of significant nondeterminacy in oilfield development. And the plan needs to ensure production and achieve minimum cost and maximum new recoverable reserves. The uncertain factors in oilfield development are analyzed in this paper, and we consider the uncertain nature of the stimulation effect of measures and new recoverable reserves per well and quantify them. On this basis, an uncertain multi-objective optimal model of oilfield development planning is constructed. The model aims to minimize the expectation of development cost and maximize the expectation of new recoverable reserves, and optimizes the workload of each measure under the constraints including the oil production and the resources limitation. Based on uncertainty theory, the model is transformed into a deterministic model. And a nondominated sorting genetic algorithm with elite strategy is developed to solve the model and get the Pareto solution set. Then the multi-attribute decision-making is applied to select the multiple development plans, which provides the basis for the decision-making of the oilfield development plan. Finally, a numerical example is given to verify the effectiveness of the model and algorithm, and their practical application values under the background of oilfield development planning.

关键词： Oilfield development planning Uncertain programming Uncertain multi-objective programming multi-objective genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

MODC: A Pareto-Optimal Optimization Approach for Network Traffic Classification Based on the Divide and Conquer Strategy

引用

INFORMATION 2018年第9期9卷 233-233页

作者： Nascimento, Zuleika Sadok, Djamel Univ Fed Pernambuco UFPE Informat Ctr BR-50740560 Recife PE Brazil

Network traffic classification aims to identify categories of traffic or applications of network packets or flows. It is an area that continues to gain attention by researchers due to the necessity of understanding the composition of network traffics, which changes over time, to ensure the network Quality of Service (QoS). Among the different methods of network traffic classification, the payload-based one (DPI) is the most accurate, but presents some drawbacks, such as the inability of classifying encrypted data, the concerns regarding the users' privacy, the high computational costs, and ambiguity when multiple signatures might match. For that reason, machine learning methods have been proposed to overcome these issues. This work proposes a multi-objective Divide and Conquer (MODC) model for network traffic classification, by combining, into a hybrid model, supervised and unsupervised machine learning algorithms, based on the divide and conquer strategy. Additionally, it is a flexible model since it allows network administrators to choose between a set of parameters (pareto-optimal solutions), led by a multi-objective optimization process, by prioritizing flow or byte accuracies. Our method achieved 94.14% of average flow accuracy for the analyzed dataset, outperforming the six DPI-based tools investigated, including two commercial ones, and other machine learning-based methods.

关键词： network traffic classification machine learning hybrid model multi-objective genetic algorithm extreme learning machine growing hierarchical self-organizing map

来源：评论

学校读者我要写书评

暂无评论

multi-objective multi-population biased random-key genetic algorithm for the 3-D container loading problem

引用

COMPUTERS & INDUSTRIAL ENGINEERING 2015年 89卷 80-87页

作者： Zheng, Jia-Nian Chien, Chen-Fu Gen, Mitsuo Natl Tsing Hua Univ Hsinchu 30013 Taiwan Fuzzy Log Syst Inst Iizuka Fukuoka 8200067 Japan

The container loading problem (CLP) has important industrial and commercial application for global logistics and supply chain. Many algorithms have been proposed for solving the 2D/3D container loading problem, yet most of them consider single objective optimization. In practice, container loading involves optimizing a number of objectives. This study aims to develop a multi-objective multi-population biased random-key genetic algorithm for the three-dimensional single container loading problem. In particular, the proposed genetic algorithm applied multi-population strategy and fuzzy logic controller (PLC) to improve efficiency and effectiveness. Indeed, the proposed approach maximizes the container space utilization and the value of total loaded boxes by employing Pareto approach and adaptive weights approach. Numerical experiments are designed to compare the results between the proposed approach and existing approaches in hard and weak heterogeneous cases to estimate the validity of this approach. The results have shown practical viability of this approach. This study concludes with discussions of contributions and future research directions. (C) 2014 Elsevier Ltd. All rights reserved.

关键词： Container loading genetic algorithm multi-objective genetic algorithm Fuzzy logic controller Cutting and packing

来源：评论

学校读者我要写书评

暂无评论

Joint Optimal Channel Allocation, Interface Assignment and Routing in multi-hop Wireless Networks 20

Joint Optimal Channel Allocation, Interface Assignment and R...

引用

20th International Conference on Advanced Communication Technology (ICACT)

作者： Wu, Jie Li, Hongchun Xu, Yi Tian, Jun Fujitsu Res & Dev Ctr Co Ltd Beijing Peoples R China

ISBN: (纸本)9791188428014

multi-hop wireless networks have advantages over the single-hop ones in terms of reliability and coverage range. Moreover, the capacity of multi-hop wireless network can be substantially increased via multiple radios tuned to non-overlapping channels. However, the channel allocation, network interface cards assignment and routing remain challenging due to the interference of the neighboring transmissions. These three problems have proved to be a NP-hard problem. Previous studies separating the routing from the channel allocation, instead of considering the three problems as a whole, cannot get the overall optimal solution. In this work, we employ an improved multi-objective genetic algorithm to optimize the channel allocation, interface assignment and the routing, so as to minimize the overall network interference. The proposed algorithm includes two parts: 1) dynamic genetic mutation based on diversity measure;and 2) elite preservation based on ideal points. In order to eliminate illegal solutions, a new individual encoding method is proposed. In addition, an interference model taking into account the effects of channel separation and the traffic of neighbor links is applied to evaluate the quality of the interference of the network. Finally, a fitness function is defined to obtain the best search results. Simulation results show that our improved multi-objective genetic algorithm can reduce the interference and cost of total network compared to the standard genetic algorithm.

关键词： multi-objective genetic algorithm channel allocation interface assignment routing multi-hop wireless network

来源：评论

学校读者我要写书评

暂无评论

A NSGA-Ⅱ based Peak Load Shifting Optimization Method for Customers with Distributed Generators Considering Time-of-use Price

A NSGA-Ⅱ based Peak Load Shifting Optimization Method for C...

引用

第37届中国控制会议

作者： Hao Zhou Min Ding Bo Hu Qingyi Wang Zhili Tan Danyun li School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex System State Grid Energy Research Institute Co. LTD.

With the extensive use of distributed generation, the traditional demand response analysis cannot meet the current *** paper proposes a NSGA-II based peak load shifting optimization method for customers with distributed generators considering time-of-use price. Firstly, a fuzzy classification method divides the daily power into three time segments,peak hours, flat hours and valley hours. Secondly, on the basis of the time-of-use price, a peak load shifting optimization model is built with constraints and the objectives of minimizing the peak load, maximizing the valley load, and minimizing the peakvalley difference. Then, a NSGA-II based optimization method solves the optimal model and obtains the optimal electricity prices of different time segments to shift the peak load and the valley load. Finally, the simulation results shows the effectiveness of the proposed method.

关键词： Distributed Generation Demand Respond Time-of-use Price multi-objective genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

multi-satellite Observation Scheduling for Large Area Disaster Emergency Response

Multi-satellite Observation Scheduling for Large Area Disast...

引用

The ISPRS Technical Commission III Midterm Symposium on "Developments, Technologies and Applications in Remote Sensing"

作者： X.N.Niu H.Tang L.X.Wu Key Laboratory of Environment Change and Natural Disaster Ministry of EducationBeijing Normal University Beijing Key Laboratory of Environmental Remote Sensing and Digital Cities Beijing Normal University School of Geosciences and Info-Physics Central South University

Timely acquiring remote sensing data is very important for rapid response to disasters. Satellite task scheduling aiming at making an optimal imaging plan, plays a key role in coordinating multiple satellites to monitor the disaster area. In the paper, to generate imaging plan dynamically according to the disaster relief, we propose a dynamic satellite task scheduling method for large area disaster response. First, an initial robust scheduling scheme is generated by a robust satellite scheduling model in which both the profit and the robustness of the schedule are simultaneously maximized. Then, we use a multi-objective optimization model to obtain a series of decomposing schemes. Based on the initial imaging plan, we propose a mixed optimizing algorithm named HASGA-II to allocate the decomposing results thus to obtain an adjusted imaging schedule. A real disaster scenario, i.e., 2008 Wenchuan earthquake, is revisited in terms of rapid response using satellite resources and used to evaluate the performance of the proposed method with state-of-the-art approaches. We conclude that our satellite scheduling model can optimize the usage of satellite resources so as to obtain images in disaster response in a more timely and efficient manner.

关键词： Disaster Emergency Response Area Tasks Decomposition multi-satellite Scheduling multi-objective genetic algorithm

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：