检索结果-内蒙古大学图书馆

Comparison of three unsupervised neural network models for first Painlev, Transcendent

NEURAL COMPUTING & APPLICATIONS 2015年第5期26卷 1055-1071页

作者： Raja, Muhammad Asif Zahoor Khan, Junaid Ali Shah, Syed Muslim Samar, Raza Behloul, Djilali COMSATS Inst Informat Technol Dept Elect Engn Attock Pakistan Hamdard Univ Fac Engn Sci & Technol Karachi Pakistan Mohammad Ali Jinnah Univ Dept Elect Engn Islamabad Pakistan USTHB Dept Comp Sci Algiers 16111 Algeria

In this paper, a reliable soft computing framework is presented for the approximate solution of initial value problem (IVP) of first Painlev, equation using three unsupervised neural network models optimized with sequential quadratic programming (SQP). These mathematical models are constructed in the form of feed-forward architecture including log-sigmoid, radial base and tan-sigmoid activation functions in the hidden layers. The optimization of designed parameters for each model is performed with SQP, an efficient constraint optimization problem-solving algorithm. The designed methodology is tested on the IVP, and comparative study is carried out with standard solution based on numerical and analytical solvers. The accuracy, convergence and effectiveness of the schemes are validated on the given benchmark problem by large number of simulations and their comprehensive analysis.

关键词： Painleve Transcendents Artificial neural network sequential quadratic programming Nonlinear differential equations Activation functions Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Constraint Handling and Multi-Objective Methods for the Evolution of Interplanetary Trajectories

引用

JOURNAL OF GUIDANCE CONTROL AND DYNAMICS 2015年第4期38卷 792-799页

作者： Izzo, Dario Hennes, Daniel Riccardi, Annalisa ESA European Space Res & Technol Ctr NL-2201 AZ Noordwijk Netherlands

A study is conducted to demonstrate constraint handling and multi-objective methods for the evolution of interplanetary trajectories. The study is based on the methods developed during GTOC6 and few advanced evolutionary techniques able to evolve complex Jupiter capture options are proposed. The evolutionary process is set up to be able to deal with constraints, along with multiple objectives and show the use of advanced evolutionary techniques to effectively search the solution space in both cases. The investigations show how these techniques allow the evolution of solutions of use to trajectory designers for the complex trajectory case considered in this study where other approaches fail to find acceptable solutions in a reasonable time.

关键词： Spacecraft Trajectory Optimization Callisto Multi Objective Evolutionary Algorithms Cumulative Distribution Function Deep Space Maneuver sequential quadratic programming Genetic Algorithm Trajectory Optimization Annealing Derivative Free Method

来源：评论

学校读者我要写书评

暂无评论

Autonomous Parafoil Guidance in High Winds

引用

JOURNAL OF GUIDANCE CONTROL AND DYNAMICS 2015年第5期38卷 963-U203页

作者： Chiel, Benjamin S. Dever, Christopher Charles Stark Draper Lab Inc Cambridge MA 02139 USA

A study is conducted to demonstrate the wind-fixed frame (WFF) approach, effectively using it as a pre-transformation to simplify path planning while explicitly accounting for estimated wind field motion. The main contribution of this study is a novel guidance algorithm enabling the system to generate trajectories in any wind condition for any phase of flight. The algorithm follows from optimal control principles and allows the specification of terminal boundary conditions while minimizing steering control effort. A nonholonomic fixed-time optimal path planning method arises naturally, with parameterized elliptic functions acting as the key trajectory descriptor by formulating parafoil guidance in this manner.

关键词： Parafoil Guidance Algorithms Optimal Control sequential quadratic programming Airspeed Motion Planning Flight Testing Guidance Laws Terminal Guidance Energy Management

来源：评论

学校读者我要写书评

暂无评论

Multi-objective Optimization Approach for Optimal Distributed Generation Sizing and Placement

引用

ELECTRIC POWER COMPONENTS AND SYSTEMS 2015年第7期43卷 828-836页

作者： Darfoun, Mohamed A. El-Hawary, Mohamed E. Coll Engn Technol Houn Elect Engn Dept Houn Libya Dalhousie Univ Dept Elect & Comp Engn Halifax NS B3H 4R2 Canada

Abstract-This article describes a multi-objective optimization method to solve the optimal distributed generation sizing and placement. The optimization problem considers two objectives: minimizing the total real power losses of the network and minimizing the overall distributed generation installation cost. The objectives are combined into a scalar objective optimization problem by using weighted sum method. Both objective functions and equality and inequality constraints are formulated as a non-linear program and solved by a sequential quadratic programming deterministic technique. The multi-objective optimization method gives several answers instead of a single (unique) one. These answers are optimal, and the designer (decision maker) can select the proper solution according to subjective preferences. These optimum results are known as the Pareto front. A fuzzy decision-making procedure for order preference is used for finding the best compromise solution from the set of Pareto solutions. The proposed method is tested using a 15-bus radial distribution system to show its applicability. A comparative study is performed to evaluate two cases-a single distributed generation unit installation and a multiple distributed generation installation-ending by a comparative study of the two cases.

关键词： distributed power losses generation sequential quadratic programming distributed generation installation cost multi-objective optimization

来源：评论

学校读者我要写书评

暂无评论

Implicit Finite Control Set Model Predictive Current Control for Modular Multilevel Converter Based on IPA-SQP Algorithm

Implicit Finite Control Set Model Predictive Current Control...

引用

Annual IEEE Applied Power Electronics Conference and Exposition

作者： Hamed Nademi Lars Einar Norum Process Automation division ABB AS Oslo-0603 Norway Department of Electrical Power Engineering Norwegian University of Science and Technology Trondheim-7491 Norway

ISBN: (纸本)9781467395519

This paper investigates a Finite-Control-Set Model Predictive Control (FCS-MPC) for the precise control of (un)balanced load currents in Modular Multilevel Converter (MMC). The control objectives are circulating currents minimization inside the converter arms, achieve a capacitors voltage balance and load current control. To achieve the converter constrained optimization and facilitate the implementation on embedded systems, an integrated perturbation analysis and sequential quadratic programming (IPA-SQP) solver is also utilized. As a case study the proposed approach is applied to a grid-connected five-level MMC. The introduced FCS-MPC formulation reduces sensitivity of the converter output voltage to disturbances in grid side and measurement noise with reducing the computational burden. Simulation results reveal the effectiveness of the developed control scheme in cases when operational objectives, e.g., load current reference tracking and disturbance rejection are considered under system model uncertainties.

关键词： Model Predictive Control sequential quadratic programming Modular Converter System Current Control

来源：评论

学校读者我要写书评

暂无评论

Orthogonal zero correlation zone codes design for MIMO radar system

引用

OPTOELECTRONICS AND ADVANCED MATERIALS-RAPID COMMUNICATIONS 2015年第1-2期9卷 201-207页

作者： Ying, Sun Be Zi-Shu Na, Liu Jun, Li Hua, Lin Univ Elect Sci & Technol China Sch Elect Engn Chengdu 611731 Peoples R China China Acad Engn Phys Inst Elect Engn Beijing Peoples R China

This paper investigates the MIMO radar orthogonal waveform design problem. The result shows the ambiguity function (AF) property of the sum of transmitted signals is as important as the autocorrelation and crosscorrelation properties of transmitted signals. An orthogonal zero correlation zone (ZCZ) phase codes design method was proposed to simultaneously satisfy these property requirements. The idea is to simultaneously constrain the peak sidelobe of the AF Of sum signal in ZCZ, and the peak sidelobe of aperiodic autocorrelation function (ACF) and peak of the aperiodic crosscorrelation function (CF) within ZCZ. We used the sequential quadratic programming (SOP) method to solve the nonlinear optimization problem with multi-variables and multi-constraints. Some of the designed results are presented, and their properties are improved significantly. The designed orthogonal ZCZ codes promise to be practically applicable.

关键词： Multiple input multiple output (MIMO) radar Zero-correlation-zone codes sequential quadratic programming

来源：评论

学校读者我要写书评

暂无评论

Homotopic Perturbed Lambert Algorithm for Long-Duration Rendezvous Optimization

引用

JOURNAL OF GUIDANCE CONTROL AND DYNAMICS 2015年第11期38卷 2215-2222页

作者： Yang, Zhen Luo, Ya-Zhong Zhang, Jin Tang, Guo-Jin Natl Univ Def Technol Coll Aerosp Sci & Engn Changsha 410073 Hunan Peoples R China

A new targeting technique using the homotopy method has been developed to obtain the non-Keplerian solution based on the Keplerian solution of a Lambert transfer orbit. To achieve this goal, a group of intermediate target points is used to approach the desired target point iteratively. This targeting technique can successfully obtain the non-Keplerian solution even for a long-duration orbit transfer problem. A universal optimization model is then built based on the homotopy targeting technique for the perturbed impulsive rendezvous problem.

关键词： Argument of Latitude Orbital Transfer Periapsis Spacecraft Rendezvous Richardson Extrapolation Annealing sequential quadratic programming Boundary Value Problems Orbital Elements Out of Plane Maneuvers

来源：评论

学校读者我要写书评

暂无评论

Diversity enhanced and local search accelerated gravitational search algorithm for data fitting with B-splines

引用

ENGINEERING WITH COMPUTERS 2015年第2期31卷 215-236页

作者： Han, XiaoHong Quan, Long Xiong, XiaoYan Wu, Bing Taiyuan Univ Technol Inst Mechatron Engn Key Lab Adv Transducers & Intelligent Control Sys Minist Educ China Taiyuan Shanxi Peoples R China

Gravitational search algorithm (GSA) has shown an effective performance for solving real-world optimization problems. However, it suffers from premature convergence because of quick losing of diversity. To enhance its performance, this paper proposes a novel GSA algorithm, called GSA-PWL (piecewise linear)-SQP (sequential quadratic programming), which employs a diversity enhancing mechanism and an accelerated local search strategy to achieve a trade-off between exploration and exploitation abilities. A comprehensive experimental study is conducted on a set of benchmark functions. Comparison results show that GSA-PWL-SQP obtains a promising performance on the majority of the test problems. Furthermore, the GSA-PWL-SQP is applied to data fitting with B-splines to solve very difficult continuous multimodal and multivariate nonlinear optimization problem. The method of data fitting based on GSA-PWL-SQP yields very accurate results even for curves with singularities and/or cusps and is very efficient in terms of data points error, AIC and BIC criteria.

关键词： Gravitational search algorithm sequential quadratic programming Piecewise linear chaotic map Function optimization Data fitting B-splines

来源：评论

学校读者我要写书评

暂无评论

Stochastic numerical treatment for thin film flow of third grade fluid using unsupervised neural networks

引用

JOURNAL OF THE TAIWAN INSTITUTE OF CHEMICAL ENGINEERS 2015年 48卷 26-39页

作者： Raja, Muhammad Asif Zahoor Khan, Junaid Ali Haroon, Tahira COMSATS Inst Informat Technol Dept Elect Engn Attock Pakistan Hamdard Univ Hamdard Inst Infromat Technol Islamabad Campus Pakistan COMSATS Inst Informat Technol Dept Math Islamabad Pakistan

In the present study, novel soft computing techniques are developed for numerical treatment of nonlinear thin film flow (TFF) problem of third grade fluids using artificial neural networks (ANNs), particle swarm optimization (PSO), sequential quadratic programming (SQP), and their hybrid combinations. The strength of universal function approximation capabilities of ANNs is exploited in formulation of mathematical model of the problem based on an unsupervised error. The training of the design parameter of the networks is performed with PSO, SQP, and hybrid approach PSO-SQP. The proposed schemes are evaluated on four variants of the two cases of TFF problems by taking different values of material parameter and Stokes number. The reliability and effectiveness of the proposed approaches are validated through the results of statistical analyses based on sufficient large number of independent runs. (C) 2014 Taiwan Institute of Chemical Engineers. Published by Elsevier B.V. All rights reserved.

关键词： Artificial neural networks Particle swarm optimization sequential quadratic programming Hybrid computing techniques Thin film flow problems Computational fluid mechanics

来源：评论

学校读者我要写书评

暂无评论

Timed Vivaldi arrays for steerable energy pattern with low side lobes

引用

JOURNAL OF ELECTROMAGNETIC WAVES AND APPLICATIONS 2015年第10期29卷 1375-1383页

作者： Reyna, Alberto Panduro, Marco A. Univ Autonoma Tamaulipas UAMR R Dept Elect Engn Reynosa 88779 Mexico CICESE Res Ctr Dept Elect & Telecommun Ensenada 22860 Baja California Mexico

A novel design of timed Vivaldi antenna arrays for steerable energy patterns is presented in this work. Three geometries are studied and designed in order to obtain an optimum energy pattern with low side lobe level (SLL) during beam steering: equally antenna array, unequally antenna array, and concentric ring array. The antenna elements are fed with the fifth derivative Gaussian pulse. The design process is carried out by the well-known sequential quadratic programming. Three design examples with 16 antenna elements are studied by considering different distribution of antenna positions. The mutual coupling phenomenon is considered by full wave simulations of Vivaldi antenna elements in the design examples. The results show a good performance of the steerable energy pattern with low SLL with ultra wideband operation.

关键词： timed antenna array UWB antenna array sequential quadratic programming energy pattern

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：