检索结果-内蒙古大学图书馆

An improved differential evolution algorithm for the task assignment problem

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2011年第4期24卷 616-624页

作者： Zou, Dexuan Liu, Haikuan Gao, Liqun Li, Steven Xuzhou Normal Univ Sch Elect Engn & Automat Xuzhou 221116 Jiangsu Peoples R China Northeastern Univ Sch Informat Sci & Engn Shenyang 110004 Liaoning Peoples R China Univ S Australia Div Business Adelaide SA 5001 Australia

An improved differential evolution algorithm (IDE) is proposed to solve task assignment problem. The IDE is an improved version of differential evolution algorithm (DE), and it modifies two important parameters of DE algorithm: scale factor and crossover rate. Specially, scale factor is adaptively adjusted According to the objective function values of all candidate solutions, and crossover rate is dynamically adjusted with the increasement of iterations. The adaptive scale factor and dynamical crossover rate are combined to increase the diversity of candidate solutions, and to enhance the exploration capacity of solution space of the proposed algorithm. In addition, a usual penalty function method is adopted to trade-off the objective and the constraints. Experimental results demonstrate that the optimal solutions obtained by the IDE algorithm are all better than those obtained by the other two DE algorithms on solving some task assignment problems. (C) 2011 Elsevier Ltd. All rights reserved.

关键词： Improved differential evolution algorithm Task assignment problem differential evolution algorithm Scale factor Crossover rate Penalty function method

来源：评论

学校读者我要写书评

暂无评论

Back analysis of an operating subsea tunnel considering the degradation of ground and concrete lining

引用

MARINE GEORESOURCES & GEOTECHNOLOGY 2019年第4期37卷 517-523页

作者： An, Joon-Sang Song, Ki-Il Inha Univ Dept Civil Engn 100 Inha Ro Incheon 22212 South Korea

An evaluation of the stability of subsea tunnels during operation is very important considering the risks involved with subsea tunnels. Although a large volume of monitoring information can be obtained, back analysis has been performed based on the internal displacement. In this study, the efficiency of an estimation of the safety of an operating subsea tunnel has been improved by implementing the back analysis algorithm based on various monitoring information. The differential evolution algorithm was adopted for back analysis of an operating subsea tunnel. The differential evolution algorithm was improved to accommodate the multiple target variables for back analysis, such as the elastic modulus, cohesion, friction angle of the ground, and the time-dependent elastic modulus of concrete lining. In addition, the elastic modulus of the concrete lining and the properties of reinforced ground can be evaluated with the proposed algorithm using a range of monitoring data, such as the internal displacement and stress acting on the lining. In summary, back analysis with a differential evolution algorithm can be used to evaluate the stability of an operating subsea tunnel.

关键词： Concrete lining degradation degradation of reinforced ground differential evolution algorithm operating subsea tunnel

来源：评论

学校读者我要写书评

暂无评论

Optimization of Epsilon-and-mu-near-zero Refractive Index Photonic Structure to Design Unidirectional Transmission Device 20

Optimization of Epsilon-and-mu-near-zero Refractive Index Ph...

引用

20th International Conference on Transparent Optical Networks (ICTON)

作者： Turduev, M. Bor, E. Yasa, U. G. Kurt, H. TED Univ Dept Elect & Elect Engn TR-06420 Ankara Turkey TOBB Univ Econ & Technol Dept Elect & Elect Engn TR-06560 Ankara Turkey

ISBN: (纸本)9781538666050

In this study, we introduce a novel approach for designing an unidirectional transmission device by using a photonic crystal (PC) structure that exhibits the properties of epsilon-mu-near-zero media. The selected PC structure consists of dielectric rods and positions of certain preselected rods in y-direction are optimized via an evolutionary algorithm to obtain the unidirectional transmission of light. Finite-difference time-domain (FDTD) method is used to perform numerical analyses for the proposed device. In addition, experiments are carried out at microwave frequencies to demonstrate the unidirectional light transmission. It is shown that a good agreement between numerical calculations and experimental measurements is achieved.

关键词： photonic crystals integrated optics phase shift mode order converter differential evolution algorithm

来源：评论

学校读者我要写书评

暂无评论

New method of bearing fault diagnosis based on mmemd and DE_ELM

引用

JOURNAL OF ENGINEERING-JOE 2019年第23期2019卷 9152-9156页

作者： Hu, Yongtao Dong, Mingru Wang, Guozhu Fan, Zheng Zhang, Shuqing Henan Inst Technol Sch Elect Engn & Automat Xinxiang Henan Peoples R China Yanshan Univ Inst Elect Engn Qinhuangdao Hebei Peoples R China

A new method of bearing fault diagnosis based on multi-masking empirical mode decomposition (MMEMD) and extreme machine learning optimised by differential evolution algorithm (DE_ELM) is proposed in this study. MMEMD is an improvement of empirical mode decomposition (EMD). By adding masking signals to the signals to be decomposed in different levels, MMEMD can restrain low-frequency components from mixing in high-frequency components effectively in the sifting process and then suppress the mode mixing. differential evolution algorithm is applied to determine the parameters of ELM for improving the classification accuracy. The four parameters are determined at one time by uniformly coded as the individuals of the differential evolution algorithm. To achieve the bearing fault diagnosis, the fault signals are first decomposed into different intrinsic mode functions (IMFs) and the sample entropy of each IMF was calculated as the fault feature. Then the fault feature was divided into training set and testing set. Input the training set to the DE_ELM to obtain the fault classification model. Finally, the testing set was put into the model for fault diagnosis. The experiment and wind turbine bearing fault diagnosis results show that the method could identify the different bearing faults with high reliability and accuracy.

关键词： machine bearings Hilbert transforms wind turbines mechanical engineering computing fault diagnosis learning (artificial intelligence) entropy evolutionary computation feedforward neural nets signal processing pattern classification MMEMD differential evolution algorithm DE_ELM masking signals low-frequency components high-frequency components fault signals fault feature fault classification model intrinsic mode functions multimasking empirical mode decomposition extreme machine learning sample entropy wind turbine bearing fault diagnosis

来源：评论

学校读者我要写书评

暂无评论

Study The Effect of High Dimensional Objective Functions on Multi-Objective evolutionary algorithms 18

Study The Effect of High Dimensional Objective Functions on ...

引用

4th International Conference on Engineering and MIS (ICEMIS)

作者： Safi, Hayder H. Ucan, Osman N. Bayat, Oguz Altinbas Univ Dept Elect & Comp Engn Istanbul Turkey

ISBN: (纸本)9781450363921

Multi-objective evolutionary algorithms (MOEAs) have been widely studied by many researchers and they have been used to solve different real-world applications that have more than one objective function. However, most MOEAs work well only when the number of objective functions is small such as two or three. The performance of MOEAs starts degrading significantly when number of objective functions increases. Therefore, there is increasing importance for studying and analyzing the effect of increasing the number of objective functions on the performance of current multi objective evolutionary algorithms. In this paper, the performance of three state-of-the-art multi objective evolutionary algorithms is investigated when increasing the number of objective functions. The tested algorithms are analyzed using test DTLZ test suit. The results show that SMPSO and NSGA-II algorithms are the best two algorithms for high number of objective functions. In addition, the results show that the running time of SMPSO and GDE3 algorithms was effected and increased much when the number of objective functions is large.

关键词： NSGA-II differential evolution algorithm PSO multi-objective problems evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

Optimization of Industrial Robot Trajectory in Composite Production 18

Optimization of Industrial Robot Trajectory in Composite Pro...

引用

18th International Conference on Mechatronics - Mechatronika (ME)

作者： Mlynek, Jaroslav Petru, Michal Martinec, Tomas Tech Univ Liberec FP Dept Math Studentska 2 Liberec 46117 1 Czech Republic Tech Univ Liberec Inst Nanomat Adv Technol & Innovat Studentska 2 Liberec 46117 1 Czech Republic

ISBN: (纸本)9788021455443;9788021455429

Currently, traditional materials (e.g. iron, steel, aluminium alloy, wood) are increasingly being replaced by composites in many industrial areas. The main advantages of these new materials are their light weight, high strength and flexibility, corrosion resistance, long lifespan and the reduced price of the produced components. This article discusses the quality of the manufacturing process technology of a shaped composite in 3D space. The technology used is based on a winding of carbon filaments on a polyurethane frame with a circular cross-section (this type of composites is used, for example, in automotive chassis). One important factor in composite frame quality is making the correct winding angles of fibres on the frame and the homogeneity of the individual winding layers. The composite frame is attached to the end-effector of the robot and successively passes through the fibre-processing head during the winding process with three layers. Each layer of fibres is wound at a different angle (usually at pi/4, 0 and - pi/4). The mathematical model of the winding process and the matrix calculus (especially matrices of rotations, translates and calculations of Euler angles) are used to determine the optimized 3D trajectory of end-effector in this paper. The differential evolution algorithm is applied to finding the optimized 3D trajectory of the end-effector. In this way the winding angles and homogeneity of winding layers are maintained during production of the frame composite. The optimized end-effector trajectory is defined by calculated sequence of tool-centre-point values. The calculation of optimized trajectory is programmed and tested in the Delphi development environment. This approach to determining the optimized trajectory of the robot is substantially more effective than the repeated search of a suitable trajectory using the control panel (teach pendant) of the robot.

关键词： frame composite industrial robot fibre placement fibre-processing head robot trajectory calculation and optimization differential evolution algorithm

来源：评论

学校读者我要写书评

暂无评论

Aspects of Solution of the Problem of the Shooting Parameters Optimization Using Modifications of the evolutionary algorithm 7

Aspects of Solution of the Problem of the Shooting Parameter...

引用

7th Mediterranean Conference on Embedded Computing (MECO)

作者： Demidova, Liliya Petrova, Nataliya Sablina, Victoria Ryazan State Radio Engn Univ Gagarin Str 59-1 Ryazan 390005 Russia Branch JSC SRC Progress Special Design Bur Spectr Gagarin Str 59a Ryazan 390005 Russia

ISBN: (纸本)9781538656839

The problem of the parameters optimization of the shooting system has been considered and the application's possibility of modifications of an evolutionary algorithm for its decision has been investigated. The idea of hybridization of the proposed evolutionary algorithm and the differential evolution algorithm has been presented. Aspects of application of the multiobjective optimization in the problem of the shooting parameters optimization have been researched. The example of application of the offered modifications of the evolutionary algorithm for the problem of the shooting parameters optimization for the observation object has been given.

关键词： optimization parameter evolutionary algorithm differential evolution algorithm hybrid algorithm multiobjective optimization shooting system observation object

来源：评论

学校读者我要写书评

暂无评论

All Dielectric Mode Order Transformation Photonic Structure Design by evolutionary Optimization Approach 20

All Dielectric Mode Order Transformation Photonic Structure ...

引用

20th International Conference on Transparent Optical Networks (ICTON)

作者： Bor, E. Babayigit, C. Kurt, H. Turduev, M. TOBB Univ Econ & Technol Dept Elect & Elect Engn TR-06560 Ankara Turkey TED Univ Dept Elect & Elect Engn TR-06420 Ankara Turkey

ISBN: (纸本)9781538666050

In this manuscript, an evolutionary algorithm is applied to design a mode order converter photonic crystal structure for achieving transformation of the propagating fundamental mode to the higher order mode. In order to transform incident light mode from an even mode to an odd mode, predefined mask object functions are employed. The cross-sectional field profiles at the output face of the optimized structure are utilized to evaluate the optimization cost function to achieve mode order transformation task. In the study, the optimized structure composed of dielectric alumina (Al2O3) rods and time domain analyses of the optimization process are done by using finite-difference time domain method. Furthermore, numerical results are confirmed by experiments for designed structure at the microwave frequencies. It is shown that the numerical calculations and experimental measurements agree well with each other.

关键词： photonic crystals integrated optics phase shift mode order converter differential evolution algorithm

来源：评论

学校读者我要写书评

暂无评论

Identifying Soil Parameters from Excavation Using MOOP 4th

Identifying Soil Parameters from Excavation Using MOOP

引用

4th GeoShanghai International Conference on Fundamentals of Soil Behaviours

作者： Jin, Yin-Fu Yin, Zhen-Yu Zhou, Wan-Huan Zhang, Dong-Mei Univ Macau Fac Sci & Technol Dept Civil & Environm Engn Macau Peoples R China Tongji Univ Coll Civil Engn Dept Geotech Engn Shanghai 200092 Peoples R China Tongji Univ Minist Educ Key Lab Geotech & Underground Engn Shanghai 200092 Peoples R China Ecole Cent Nantes Res Inst Civil Engn & Mech GeM UMR 6183 CNRS Nantes France

ISBN: (纸本)9789811301254;9789811301247

In this paper, a framework that combines the stochastic multi-objective optimization (MOOP) and the observed field data for identifying soil parameters is presented. For conducting the parameter identification, a multi-objective differential evolution algorithm is employed. Then, an elasto-plastic soil model accounting for the small-strain stiffness and anisotropic elasticity behaviors of clays is developed and adopted. Finally, the proposed procedure is applied to a well-instrumented deep excavation. The observed wall deflection and ground settlement are used as objective in the optimization. The results demonstrate that the anisotropy of elasticity and small strain stiffness are two important factors influencing the ground settlement and wall deflection in the excavation. All the comparisons demonstrate that the proposed framework is effective and efficient for identifying soil parameters from excavation.

关键词： Excavation Multi-objective optimization differential evolution algorithm Parameter identification Small-strain stiffness Anisotropy

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Gravitational Search algorithm for Unconstrained Problems 30

A Hybrid Gravitational Search Algorithm for Unconstrained Pr...

引用

30th Chinese Control and Decision Conference (CCDC)

作者： Zhang, Xin Zou, Dexuan Kong, Zhi Shen, Xin Jiangsu Normal Univ Sch Elect Engn & Automat Xuzhou 221116 Jiangsu Peoples R China Northeastern Univ Sch Control Engn Qinhuangdao 066004 Hebei Peoples R China

ISBN: (纸本)9781538612446

The basic gravitational search algorithm (GSA) could fall into local optima solution easily, and thus we proposed a hybrid gravitational search algorithm (HGSA) in order to overcome the shortcoming of GSA. This improved gravitational search algorithm, which only uses the position update formula that was affected by the Gbest in its iteration process, is combined with the differential evolution (DE) algorithm. Ten benchmark functions have been introduced for testing the improved algorithms' performance. We also use the statistical method "T-test" to verify the difference in results. Experimental results show that HGSA is superior to the basic gravitational search algorithm and its three improved algorithms in terms of both convergence accuracy and convergence rate.

关键词： Gravitational Search algorithm differential evolution algorithm Swarm Intelligence Unconstrained Problems Benchmark Functions

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：