Applied Mechanics and Materials
Vol. 331
Vol. 331
Applied Mechanics and Materials
Vol. 330
Vol. 330
Applied Mechanics and Materials
Vol. 329
Vol. 329
Applied Mechanics and Materials
Vol. 328
Vol. 328
Applied Mechanics and Materials
Vol. 327
Vol. 327
Applied Mechanics and Materials
Vols. 325-326
Vols. 325-326
Applied Mechanics and Materials
Vols. 321-324
Vols. 321-324
Applied Mechanics and Materials
Vol. 320
Vol. 320
Applied Mechanics and Materials
Vol. 319
Vol. 319
Applied Mechanics and Materials
Vol. 318
Vol. 318
Applied Mechanics and Materials
Vols. 316-317
Vols. 316-317
Applied Mechanics and Materials
Vol. 315
Vol. 315
Applied Mechanics and Materials
Vols. 313-314
Vols. 313-314
Applied Mechanics and Materials Vols. 321-324
Paper Title Page
Abstract: Particle Swarm Optimization (PSO) is a swarm intelligence algorithm to achieve through competition and collaboration between the particles in the complex search space to find the global optimum. Basic PSO algorithm evolutionary late convergence speed is slow and easy to fall into the shortcomings of local minima, this paper presents a multi-learning particle swarm optimization algorithm, the algorithm particle at the same time to follow their own to find the optimal solution, random optimal solution and the optimal solution for the whole group of other particles with dimensions velocity update discriminate area boundary position optimization updates and small-scale perturbations of the global best position, in order to enhance the algorithm escape from local optima capacity. The test results show that several typical functions: improved particle swarm algorithms significantly improve the global search ability, and can effectively avoid the premature convergence problem. Algorithm so that the relative robustness of the search space position has been significantly improved global optimal solution in high-dimensional optimization problem, suitable for solving similar problems, the calculation results can meet the requirements of practical engineering.
2183
Abstract: The right panel drawing direction is an important prerequisite for generating qualified parts, an important step before the panel forming simulation is to determine the reasonable direction of the drawing. Manually adjust parts in order to overcome rely on experience, the drawbacks to the drawing direction, the direction of the drawing punch and forming the contact area of the sheet as the goal of automatic determination algorithm. Objective function of the direction of the drawing for the variable contact area in the drawing direction of the feasible region, the use of heritage algorithms to optimize the objective function of the contact area and, ultimately feasible within the contact area corresponding to the drawing direction, that is the best drawing direction. The measured results show that the direction of the drawing based on genetic algorithm, the automatic algorithm can fast and accurate to obtain the optimal direction of drawing.
2187
Abstract: The right management managing direction is an important prerequisite for generating qualified parts, an important step before the management forming simulation is to determine the reasonable direction of the managing. Manually adjust parts in order to overcome rely on experience, the drawbacks to the managing direction, the direction of the managing tool and forming the contact area of the sheet as the goal of automatic determination mode. Objective function of the direction of the managing for the variable contact area in the managing direction of the feasible region, the use of heritage modes to optimize the objective function of the contact area and, ultimately feasible within the contact area corresponding to the managing direction, that is the best managing direction. The measured results show that the direction of the managing based on genetic mode, the automatic mode can fast and accurate to obtain the optimal direction of managing.
2191
Abstract: The right panel drawing direction is an important prerequisite for generating qualified parts, an important step before the panel forming simulation is to determine the reasonable direction of the drawing. Manually adjust parts in order to overcome rely on experience, the drawbacks to the drawing direction, the direction of the drawing punch and forming the contact area of the sheet as the goal of automatic determination algorithm. Objective function of the direction of the drawing for the variable contact area in the drawing direction of the feasible region, the use of heritage algorithms to optimize the objective function of the contact area and, ultimately feasible within the contact area corresponding to the drawing direction, that is the best drawing direction. The measured results show that the direction of the drawing based on genetic algorithm, the automatic algorithm can fast and accurate to obtain the optimal direction of drawing.
2195
Abstract: Computer room cooling performance directly affect the operation of the engine room, the air conditioning out of the wind through the method to build a three-dimensional simulation of the engine room to explore the room hotspot locations, and to optimize the configuration of the cabinet task according to the engine room heat distribution. Using the Fluent Fluid Dynamics processing software provides simple algorithm to simulate the flow and temperature fields of the simulation engine room, the idea of sampling point using the model output parameters, use the function fitting, build a function of the wind speed of the air speed sampling point obtained reasonable outlet velocity.
2199
Abstract: This paper describes a dimension reduction method of input vector to improve classification efficiency of LVQ neural network, where GA is used to decrease the redundancy of input data. And in order to solve the initial weight vector sensitivity, GA is also employed to optimize the initial vector. The experimental results on the UCI data sets demonstrate that the efficiency and accuracy of our LVQ network by GA is higher than general LVQ neural network classification algorithm.
2203
Abstract: In the case-based reasoning in drilling fluid design expert system, it selects the corresponding representation method of attributes and matching algorithm according to the characteristics of drilling fluid system and the formulation. The representation methods of attributes in this article include digital, string and range these three methods, therefore, the corresponding matching algorithms also have nearest-neighbor, string matching and range matching these three algorithms. On this basis, and combined with the single parent genetic algorithm to optimize the initial weights combination, we can get the most optimal and realistic drilling fluid system and formula. This design method can greatly improve the efficiency and accuracy of the drilling fluid formula design.
2209
Abstract: The Particle Swarm Optimization Algorithm is a new computational method for the combinatorial optimization problem, it is simple and effective, but it does suffer from the premature convergence. For overcome this problem and finding the optimal solution of the Stochastic Loader problem, we presented a new hybrid Particle Swarm Optimization Algorithm that combines with Artificial Immune Algorithm, such as immune memory, antibody promotion and suppression, immune selection and so on. Numerical example illustrates the higher efficiency and reliability of the new hybrid PSO compared with the basic Particle Swarm Optimization Algorithm.
2214
Abstract: To improve the poor simulation results caused by the irregular changing spray flow in the dust suppression spray process, the paper gives the calculation method of particle attribute value by analysing the basic principle of the spray simulating particle system; and according to the changing spray flow , the paper designs a callback structure for pray particle system algorithm to achieve real-time updates of the particles. The experimental results show that the simulation effect of the method is reality and can be used in the common PC to simulate the dynamic spray effect.
2219
Abstract: A novel biclustering algorithm is proposed in this paper, which can be used to cluster gene expression data. One of the contributions of this paper is a novel and effective residue function of the biclustering algorithm. Furthermore, a new optimal algorithm which is mixed by the parallel genetic algorithm and the particle swarm optimal algorithm is firstly used to the algorithm of the biclustering for gene expression data. we compared our algorithm with traditional genetic algorithm in biclustering. The results reveal that novel proposed algorithms could discover the interesting patterns in the gene expression profiles.
2223