Application of Particle Swarm Optimization Based BP Neural Network on Engineering Project Risk Evaluating

  • Authors:

  • Chun-guang Chang;Ding-wei Wang;Ya-chen Liu;Bao-ku Qi

  • Affiliations:

  • Shenyang Jianzhu University, China;Northeastern University, China;Shenyang Jianzhu University, China;Shenyang Jianzhu University, China

  • Venue:
  • ICNC '07 Proceedings of the Third International Conference on Natural Computation - Volume 01
  • Year:
  • 2007

Quantified Score

Hi-index 0.00

Visualization

Abstract

The purpose of this paper is to improve the risk evaluating quality of engineering project. The topology structure of particle swarm optimization (PSO) based BP (PSOBP) neural network is described, the principle of PSOBP neural network is introduced, and the implement step of PSOBP neural network is given. The combination algorithm is applied to risk evaluating for the engineering project, and its result is compared with that of conventional BP neural network. The comparing result shows that PSOBP neural network fits to complex system such as risk evaluating for engineering project, it improves in a certain extent on training speed and precision, it can improve the quality of engineering project risk evaluating, and it fits to solve some problems in which evaluating indexes weights are difficult to be determined or there exists complex non-linear relation among them.