检索结果-内蒙古大学图书馆

Evolutionary-modified fuzzy nearest-neighbor rule for pattern classification

EXPERT SYSTEMS WITH APPLICATIONS 2017年 88卷 258-269页

作者： Kassani, Peyman Hosseinzadeh Teoh, Andrew Beng Jin Kim, Euntai Yonsei Univ Sch Elect & Elect Engn Seoul 120749 South Korea

This paper presents an improved version of the well-established k nearest neighbor (k-NN) and fuzzy NN (FNN), termed the multi-objective genetic-algorithm-modified FNN (MOGA-MFNN). The MFNN design problem is converted into a multi-modal objective maximization problem constrained by four objective functions. Thereafter, the associated parameter set of the MFNN and the feature attributes can be determined optimally and automatically via the non-dominated sorting genetic algorithm II. We introduce two new objective functions termed the Margin-I and Margin-II, which are used to improve the generalization capability of the MFNN for the unknown data, along with two existing performance functions: the geometric mean and the area under the receiver-operated characteristic curve for the training accuracy. Moreover, we proposed a novel data-dependent weight-assignment technique for local class membership functions of the MFNN. The technique enables the MFNN to determine its local neighbors adaptively through the MOGA algorithm. To expedite the classification, the MOGA-MFNN is implemented on a graphical processing unit (GPU), which significantly increases the computation speed. Furthermore, the local class-membership function of the MFNN can be computed in advance, rather than delaying it to the classification stage. This again can improve the classification speed. The MOGA-MFNN is evaluated on 20 datasets obtained from the repository of the University of California, Irvine (UCI). The experiments with rigorous statistical significance tests demonstrate that the proposed method performs competitively with the existing methods. (C) 2017 Elsevier Ltd. All rights reserved.

关键词： Pattern classification Fuzzy nearest-neighbor rule multi-objective genetic algorithm Graphical-processing unit

来源：评论

学校读者我要写书评

暂无评论

Vibration control of smart TMD for retractable-roof spatial structure considering closed and open roof condition

引用

INTERNATIONAL JOURNAL OF STEEL STRUCTURES 2017年第4期17卷 1537-1548页

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

A retractable-roof system is frequently adapted to the spatial structure of stadiums and sports halls. The geometric shape and mass location are varied by opening or closing the roof, resulting in a change in the dynamic characteristics of the retractable-roof spatial structure. A passive tuned mass damper (TMD) shows good vibration control performance of the spatial structures when it is tuned properly. Because the closed or open roof condition of a retractable spatial structure causes off-tuning, multiple smart tuned mass dampers (STMD) were developed in this study to increase the control performance in the case of off-tuning. Initially, the dynamic characteristics variations of the opened or closed roof conditions were investigated using an example retractable spatial structure. The control performances of a passive TMD and smart TMD were evaluated under off-tuning conditions. For this purpose, artificial ground motion was generated based on the Korean Building Code (KBC) 2016. multiple smart TMDs were comprised of magnetorheological (MR) dampers. A fuzzy logic control algorithm (FLC) was used to generate the command voltages sent to the MR dampers and the FLC was optimized by a multi-objective genetic algorithm. Numerical analyses showed that the smart TMD had better control performance than the passive TMD. In the case of the off-tuning condition, the difference in control performance between passive and smart TMDs increased.

关键词： retractable roof system spatial structure smart control system tuned mass damper MR damper seismic response control fuzzy logic controller multi-objective genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

Smart Platform for Microvibration Control of High-Tech Industry Facilities

引用

INTERNATIONAL JOURNAL OF STEEL STRUCTURES 2017年第1期17卷 155-164页

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

Recently, the microvibrations of high technology facilities resulting from nearby traffic loads have attracted significant attention. Considerable research aimed at protecting high-tech equipment due to nearby road and rail traffic has focused on vibration isolation systems. These isolation systems include passive-base isolation systems, smart base isolation systems, passive mounts, and active tables that are used mainly to isolate a small quantity of high-tech equipment. In this study, a smart platform was developed to control the microvibrations of high-technology facilities. Train-induced ground acceleration was generated as a nearby traffic load and a magnetorheological damper was used to compose a smart isolation platform. A fuzzy logic controller was used as a control algorithm that was optimized using a multi-objective genetic algorithm. The microvibration control performance of a smart isolation platform was compared with that of a conventional passive isolation platform. A series of parametric studies were performed to optimize the design of a passive isolation platform. Numerical analysis showed that a smart isolation platform can effectively control the microvibrations of a high-technology facility subject to train-induced excitation.

关键词： smart platform train-induced ground motion microvibration semi-active control MR damper fuzzy logic controller multi-objective genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

An experimental approach to reduce the parametric dimensionality for rainfall-runoff models

引用

HYDROLOGY RESEARCH 2017年第1期48卷 48-65页

作者： Chen, Jie Arsenault, Richard Brissette, Francois P. Wuhan Univ State Key Lab Water Resources & Hydropower Engn S Wuhan 430072 Peoples R China Univ Quebec Ecole Technol Super 1100 Rue Notre Dame Ouest Montreal PQ H3C 1K3 Canada

Sobol' sensitivity analysis has been used successfully in the past to reduce the parametric dimensionality for hydrological models. However, the effects of its limitation, in that it assumes an independence of parameters, need to be investigated. This study proposes an experimental approach to assess the commonly used Sobol' analysis for reducing the parameter dimensionality of hydrological models. In this approach, the number of model parameters is directly pitted against an efficiency criterion within a multi-objective genetic algorithm (MOGA), thus allowing both the identification of key model parameters and the optimal number of parameters to be used within the same analysis. The proposed approach was tested and compared with the Sobol' method based on a conceptual lumped hydrological model (HSAMI) with 23 free parameters. The results show that both methods performed very similarly, and allowed 11 out of 23 HSAMI parameters to be reduced with little loss in model performance. Based on this comparison, Sobol' appears to be an effective and robust method despite its limitations. On the other hand, the MOGA algorithm outperformed Sobol' analysis for further reduction of the parametric space and found optimal solutions with as few as eight parameters with minimal performance loss in validation.

关键词： hydrological model multi-objective genetic algorithm parameter reduction Sobol' sensitivity analysis

来源：评论

学校读者我要写书评

暂无评论

Seismic retrofit of MRF buildings using decentralized semi-active control for multi-target performances

引用

EARTHQUAKE ENGINEERING & STRUCTURAL DYNAMICS 2017年第3期46卷 409-424页

作者： Cha, Young-Jin Agrawal, Anil K. Univ Manitoba Dept Civil Engn Winnipeg MB R3T 5V6 Canada CUNY City Coll Dept Civil Engn New York NY 10034 USA

Numerous structures have been designed and built without taking earthquake ground motions or outdated seismic design codes into account. In order to improve the seismic performance of existing structures, many retrofit approaches based on performance-based design have been developed. However, some of these approaches are inapplicable due to structural limitations or because they were developed with the assumption of single-degree-of-freedom, which does not take higher modes into account. To overcome the limitations of these traditional methods, a multi-performance-based control design (MPBCD) methodology has been proposed by integrating a decentralized semi-active control algorithm, magnetorheological dampers, and an advanced multi-objective optimization method to provide various sets of retrofit control designs to satisfy multiple target performances under multiple seismic intensities without changing structural cross-section sizes or material properties. This MPBCD method provides engineers with numerous sets of control designs (i.e., control device layouts with control design parameters) to help them select proper control designs to retrofit existing building structures and improve seismic performance. Copyright (C) 2016 John Wiley & Sons, Ltd.

关键词： multi-target performances semi-active control magnetorheological damper multi-objective genetic algorithm nonlinear model nonlinear time-history analysis

来源：评论

学校读者我要写书评

暂无评论

Three dimensional optimization of small-scale axial turbine for low temperature heat source driven organic Rankine cycle

引用

ENERGY CONVERSION AND MANAGEMENT 2017年 133卷 411-426页

作者： Al Jubori, Ayad Al-Dadah, Raya K. Mahmoud, Saad Ennil, A. S. Bahr Rahbar, Kiyarash Univ Birmingham Sch Engn Dept Mech Engn Birmingham B15 2TT W Midlands England Univ Technol Baghdad Baghdad Iraq

Advances in optimization techniques can be used to enhance the performance of turbines in various applications. However, limited work has been reported on using such optimization techniques to develop small-scale turbines for organic Rankine cycles. This paper investigates the use of multi-objective genetic algorithm to optimize the stage geometry of a small-axial subsonic turbine. This optimization is integrated with organic Rankine cycle analysis using wide range of high density organic working fluids like R123, R134a, R141b, R152a, R245fa and isobutane suitable for low temperature heat sources <100 degrees C such as solar energy to achieve the best turbine design and highest organic Rankine cycle efficiency. The isentropic efficiency of the turbine in most of the reported organic Rankine cycle studies was assumed constant, while the current work allows the turbine isentropic efficiency to change (dynamic value) with both operating conditions and working fluids. Three-dimensional computational fluid dynamics analysis and multi-objective genetic algorithm optimization were performed using three-dimensional Reynolds-averaged Navier-Stokes equations with k-omega shear stress transport turbulence model in ANSYS(R17)-CFX and design exploration for various working fluids. The optimization was carried out using eight design paraMeters for the turbine stage geometry optimization including stator and rotor number of blades, rotor leading edge beta angle, trailing edge beta angle, stagger angle, throat width, trailing half wedge angle and shroud tip clearance. Results showed that using working fluid R123 for a turbine with mean diameter of 70 mm, the maximum isentropic efficiency was about 88% and power output of 6.3 kW leading to cycle thermal efficiency of 10.5% showing an enhancement of 14.08% compared to the baseline design. Such results highlight the potential of the 3D optimization technique to improve the organic Rankine cycle performance. (C) 2016 Elsevier Ltd. All

关键词： Small-scale axial turbine ORC Mean-line design CFD 3D optimization multi-objective genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

Altitude and roll control of a hovering quad-rotor air vehicle using the multi-objective approximate optimization of proportional-integral-differential control

引用

ENGINEERING OPTIMIZATION 2017年第10期49卷 1704-1718页

作者： Yoon, Jaehyun Lee, Jongsoo Yonsei Univ Sch Mech Engn Seoul South Korea

This study explores the optimal proportional-integral-differential (PID) gains of a hovering quad-copter to allow recovery from disturbed altitude and roll positions. Computational fluid dynamics was used to determine the rotor distance and the blade shape parameters for maximizing the hovering thrust. Using a six-degree-of-freedom quad-copter dynamics model, a control algorithm was then used to obtain PID gains. The PID control was approximated using back-propagation neural networks (BPNs). Position control of the quad-copter model was performed by determining the optimal PID gains required to minimize the control duration for altitude and roll. The non-dominated sorting genetic algorithm (NSGA-II) was used for multi-objective optimization and a BPN was used for meta-modelling the PID control. The PID gains generated from bi-objective optimal designs were compared with the initial design. The results confirmed that the recovery time from an unbalanced position was reduced and that the motion of the quad-copter was better stabilized.

关键词： Quad-rotor air vehicle altitude and roll control back-propagation neural network 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

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

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：