As an important link of pattern recognition, pattern feature extraction and selection has been paid close attention by lots of scholars, and currently become one of the research hot spot in the field of pattern recogn...
详细信息
ISBN:
(纸本)9781424420957
As an important link of pattern recognition, pattern feature extraction and selection has been paid close attention by lots of scholars, and currently become one of the research hot spot in the field of pattern recognition. Its main purpose is "Low Loss Dimensionality Reduction";it is generally divided into two parts, that is, linear pattern feature extraction and selection and nonlinear pattern feature extraction and selection. This article gives a general discussion of pattern feature extraction and selection, and introduces the frontier methods of this field, at last discusses the development tendency of pattern feature extraction and selection.
A new method for amplitude -only optimization of circular planar slot array antennas is presented. In order to form a given three-dimensional antenna pattern for array antennas, variable metric algorithms, Davidon-Fle...
详细信息
A new method for amplitude -only optimization of circular planar slot array antennas is presented. In order to form a given three-dimensional antenna pattern for array antennas, variable metric algorithms, Davidon-Fletcher-Powell(DFP) and Broyden-Fletcher-Goldfarb-Shanno (BFGS) were jointly used to optimize the amplitude distribution of the current excitations. Thus, the optimized main lobe of the antenna pattern is fitted for the given and the side lobe level is efficiently controlled. This method solves N-dimensional unrestricted function;it shows fast convergence and small amount of computing. It is a valuable beam shaping method for array antennas.
The graph coloring is a classic NP-complete problem. Presently there is no effective method to solve this problem. Here we propose a modifled particle swarm optimization (PSO) algorithm in which a disturbance factor i...
详细信息
The graph coloring is a classic NP-complete problem. Presently there is no effective method to solve this problem. Here we propose a modifled particle swarm optimization (PSO) algorithm in which a disturbance factor is added to a particle swarm optimizer for improv- ing its performance. When the current global best solution cannot be updated in a certain time period that is longer than the disturbance factor, a certain number of particles will be chosen according to probability and their velocities will be reset to force the particle swarm to get rid of local minimizers. It is found that this operation is helpful to improve the performance of particle swarm. Classic planar graph coloring problem is resolved by using modifled particle swarm optimization algorithm. Numerical simulation results show that the per- formance of the modified PSO is superior to that of the classical PSO.
In order to improve the precision of attitude operator in GPS attitude determination, based on Quantum-behaved Particle Swarm optimization(QPSO) algorithm, a new GPS carrier phase searching technology of attitude dete...
详细信息
ISBN:
(纸本)9781424421138
In order to improve the precision of attitude operator in GPS attitude determination, based on Quantum-behaved Particle Swarm optimization(QPSO) algorithm, a new GPS carrier phase searching technology of attitude determination is proposed. In favor of the ambiguity function method's fitness function, quantum behavior is introduced to enhance the ability of global searching to achieve the GPS fast determination. The simulations show the QPSO algorithm applied to solve benchmark functions is stable, fast of the searching speed and have a high accuracy. The actual application shows the method used in GPS attitude operator based on QPSO algorithm is able to search in the complex space, and the precision is high, the speed is rapid and the application effect is notable.
As an important link of pattern recognition, pattern feature extraction and selection has been paid close attention by lots of scholars, and currently become one of the research hot spot in the field of pattern recogn...
详细信息
As an important link of pattern recognition, pattern feature extraction and selection has been paid close attention by lots of scholars, and currently become one of the research hot spot in the field of pattern recognition. Its main purpose is "Low Loss Dimensionality Reduction";it is generally divided into two parts, that is, linear pattern feature extraction and selection and nonlinear pattern feature extraction and selection. This article gives a general discussion of pattern feature extraction and selection, and introduces the frontier methods of this field, at last discusses the development tendency of pattern feature extraction and selection.
Cross-enterprise collaborative project management is a new production management pattern due to economic *** most important characteristic is that the resources used in project are *** uncertainty of resources leads t...
详细信息
Cross-enterprise collaborative project management is a new production management pattern due to economic *** most important characteristic is that the resources used in project are *** uncertainty of resources leads to plan *** multi-enterprises' collaborative project plan should have robust adaptation and *** this paper,a new uncertain resourceconstrained planning and control model for multi-enterprises collaborative project is proposed,and its project scheduling optimization algorithm is developed as *** have been put into use in a multi-enterprises collaborative project management system,and worked successfully.
作者:
Driver, J.Zingg, D. W.Univ Toronto
Inst Aerosp Studies N York ON M3H 5T6 Canada Univ Toronto
Inst Aerosp Studies Tier Canada Res Chair Computat Aerodynam 1 N York ON M3H 5T6 Canada
A two-dimensional Newton-Krylov aerodynamic shape optimization algorithm is applied to several optimization problems in which the location of laminar-turbulent transition is free. The coupled Euler and boundary-layer ...
详细信息
A two-dimensional Newton-Krylov aerodynamic shape optimization algorithm is applied to several optimization problems in which the location of laminar-turbulent transition is free. The coupled Euler and boundary-layer solver MSES is used to obtain transition locations through the e(N) method, which are then used in Optima2D, a Newton-Krylov discrete-adjoint optimization algorithm based on the compressible Reynolds-averaged Navier-Stokes equations. The algorithm is applied to the design of airfoils with maximum lift-to-drag ratio, endurance factor, and lift coefficient. The design examples demonstrate that the optimizer is able to control the transition-point locations to provide optimum performance, often producing pressure distributions with laminar rooftops followed by concave pressure recovery. In particular, the optimization algorithm is able to design an airfoil that is very similar, in terms of both shape and performance, to one of the high-lift airfoils designed by Liebeck (Liebeck, R. H., "A Class of Airfoils Designed for High Lift in Incompressible Flow," Journal of Aircraft, Vol. 10, No. 10, 1973, pp. 610-617) in the 1970s. The results provide a striking demonstration of the capability of the Newton-Krylov aerodynamic optimization algorithm to design airfoils with characteristics that previously required a great deal of expertise to achieve.
We have developed a framework that distributes multiple reservoir simulations on a cluster of CPUs for fast and efficient process optimization studies. This platform utilizes several commercial reservoir simulators fo...
详细信息
We have developed a framework that distributes multiple reservoir simulations on a cluster of CPUs for fast and efficient process optimization studies. This platform utilizes several commercial reservoir simulators for flow simulations, an experimental design and a Monte Carlo algorithm with a global optimization search engine to identify the optimum combination of reservoir decision factors under uncertainty. This approach is applied to a well placement design for a field-scale development exercise. The uncertainties considered are in the fault structure, porosity and permeability, PVT, and relative permeabilities. The results indicate that the approach is practical and efficient for performing reservoir optimization studies. (C) 2007 Elsevier B.V. All rights reserved.
A commonly used method to dry fine solid particles is drying in a fluidized bed. This paper presents the optimization problem of fluidized drying of fine solids. A drying process proceeding in a three-stage cascade of...
详细信息
A commonly used method to dry fine solid particles is drying in a fluidized bed. This paper presents the optimization problem of fluidized drying of fine solids. A drying process proceeding in a three-stage cascade of fluidized cross-current dryers was considered. Solid flows from stage to stage, and fresh gas is introduced to each stage of the cascade. The hydrodynamics of bubble fluidized bed and kinetics of heat and mass transfer are taken into account. The bed hydrodynamics is described by a two-phase model. The drying process considered proceeds in the second period of drying. To optimize this problem a generalized version of a discrete algorithm with constant Hamiltonian was used. The optimization procedure is presented in the paper. In optimization calculations, gas parameters (temperature, humidity and flow rate) minimizing total process cost are sought. The results of calculation are presented as graphs. The results obtained and the conclusions drawn are discussed.
Most real-world design problems are complex and multidisciplinary, with almost always more than one objective (cost) function to be extremized simultaneously. The primary goal of this research is to develop a framewor...
详细信息
Most real-world design problems are complex and multidisciplinary, with almost always more than one objective (cost) function to be extremized simultaneously. The primary goal of this research is to develop a framework to enable multi-objective optimization of multidisciplinary design applications, wherein each discipline is able to retain substantial autonomous control during the process. To achieve this end, we have extended the capability of the concurrent subspace optimization method to handle multi-objective optimization problems in a multidisciplinary design optimization context. Although the conventional concurrent subspace optimization approach is easily able to deal with multi-objective optimization problems by applying the weighted sum approach, the main disadvantage is that the weighted sum cannot capture Pareto points on any nonconvex part of the Pareto frontier. Moreover, an aggregate objective function simply cannot reflect the true spirit of the concurrent subspace optimization method, which was developed to allow groups of specialists to independently have more control over their own design criteria and goals, even while maintaining system level coordination. In this paper, the multi-objective Pareto concurrent subspace optimization method is proposed in which each discipline has substantial control over its own objective function during the design process, while still ensuring responsibility for constraint satisfaction in coupled subspaces. The proposed approach is particularly useful given the realities of geographical distribution, computational platform variation, and dependence upon legacy codes within individual disciplines that so predominates the design of large-scale products such as aircraft and automobiles. As part of the multi-objective Pareto concurrent subspace optimization method developed here, it is demonstrated that the endpoints of the Pareto frontier can be easily identified, together with an ability to generate Pareto points with
暂无评论