Learning-Based Multi-Directional Adaptive PSO

Zheng Bo Li

doi:10.4028/www.scientific.net/AMM.321-324.2183

Paper Titles

Research and Application of Move Limit Indicator Strategy with Domain Reduce Method
p.2161

An Error Minimizing Partitioning Method for the Nearest Neighbor Search
p.2165

Fast Compass Alignment Algorithm of FOG SINS under Sway Condition
p.2171

Nonlinearity Compensation for Thermocouple Vacuum Gauge Using Particle Swarm Optimized Least Squares Support Vector Machine
p.2177

Learning-Based Multi-Directional Adaptive PSO
p.2183

Automatic Algorithm of Automotive Stamping Direction Based on GA
p.2187

Mechanical & Electrical Equipment Management Mode Control Computer-Based Network (Wireless)
p.2191

Automatic Algorithm of Effectiveness of Accounting Management Systems Based on Finite Element Simulation
p.2195

The Design of the Engine Room Cooling Model Based on a Simple Algorithm
p.2199

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 321-324Learning-Based Multi-Directional Adaptive PSO

Learning-Based Multi-Directional Adaptive PSO

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.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 321-324)

Pages:

2183-2186

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.321-324.2183

Citation:

Cite this paper

Online since:

June 2013

Authors:

Zheng Bo Li

Keywords:

Adaptive, Intelligence, Learning-Based, Multi-Learning, Optimization, Particle Swarm Optimization (PSO)

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] Gong Ke-jia,Hu Ping. Method for Generating Additional Surface in Die Face Design of Automotive Panel[J]. Journal of Jilin University(Engineering and Technology Edition) , 2006, 36(1): 63-66.

Google Scholar

[2] Pernot J.-P, Moraru G. Filling holes in meshes using a mechanical model to simulate the curvature variation minimization[J]. Computers & Graphics, 30 (2006): 892-902.

DOI: 10.1016/j.cag.2006.08.020

Google Scholar

[3] Vera Rayevskaya, Larry L. Multi-sided macro-element spaces based on Clough–Tocher triangle splits with applications to hole filling[J].Computer Aided Geometric Design, 22 (2005): 57-79.

DOI: 10.1016/j.cagd.2004.09.001

Google Scholar

[4] Wang Jian-ning, Manuel M. Filling holes on locally smooth surfaces reconstructed from point clouds[J]. Image and Vision Computing, 25 (2007): 103-113.

DOI: 10.1016/j.imavis.2005.12.006

Google Scholar