PSO-BP Combined Artificial Neural Network Method Research

Gui Ling Liu; Feng Gao

doi:10.4028/www.scientific.net/AMM.353-356.3537

Paper Titles

Construction of Urban Traffic Information Service System Based on WebGIS
p.3516

Research on Image Retrieval Method Based on Shape Feature
p.3520

Application of GIS to Iron Tailing Investigation and Exploitation
p.3524

Numerical Simulations of Regular Wave Impact on Horizontal Plate Based on SPH Methods
p.3531

PSO-BP Combined Artificial Neural Network Method Research
p.3537

Modal Analysis of Coal Preparation Plant Based on ANSYS
p.3541

Numerical Simulation of Surface Wind Pressures on Low-Rise Buildings
p.3545

A New Robust Algorithm for Identifying the Orientation of Polygons Containing Arc
p.3549

The Application of ABAQUS in a Spiral Staircase Analysis
p.3555

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 353-356PSO-BP Combined Artificial Neural Network Method...

PSO-BP Combined Artificial Neural Network Method Research

Abstract:

BP artificial neural network(ANN) based on gradient algorithm method is widely applied, but because the error surface of object function is very complex and the choose of initial value effects network training results, convergence rate is slow and local minimum is likely to fall into. Particle swarm optimization(PSO) algorithm has better global searching ability to get rid the puzzles of falling into local minimum. By adequately studying on the two algorithms’ characteristics, a new type of combined ANN training method is put forward, and PSO-BP ann model is successfully built.