计算机与现代化 ›› 2011, Vol. 1 ›› Issue (11): 47-4.doi: 10.3969/j.issn.1006-2475.2011.11.013

• 计算机仿真 • 上一篇    下一篇

基于Matlab的概率神经网络的实现及应用

苏 亮,宋绪丁   

  1. 长安大学工程机械学院,陕西西安710064
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2011-11-28 发布日期:2011-11-28

Implementation and Application of Probabilistic Neural Network Based on Matlab

SU Liang, SONG Xu-ding   

  1. School of Construction Machinery, Chang’an University, Xi’an 710064, China
  • Received:1900-01-01 Revised:1900-01-01 Online:2011-11-28 Published:2011-11-28

摘要:

介绍概率神经网络(PNN)的模型和基本算法,以及利用Matlab神经网络工具箱设计PNN网络的方法和步骤,实现对网络的设计、训练、仿真。针对某水泥泵车臂架细部焊接结构的疲劳寿命实验数据,应用PNN的分类功能对实验数据进行训练仿真处理,得到对臂架细部结构疲劳寿命的预测分类结果,验证了此方法的可靠性。

关键词: 概率神经网络(PNN), Matlab, 分类, 疲劳寿命

Abstract:

The paper introduces the model and basic algorithms of Probabilistic Neural Network (PNN), and the methods and procedures of using Matlab neural network toolbox to design PNN, also the realization of network design training, simulation. The forecast classification results of the experimental data for the arm set of the concrete pump truck wilding structure fatigue life are obtained by using the PNN classified function on training and simulating. The reliability of this method is confirmed.

Key words: Probabilistic Neural Network(PNN), Matlab, classification, fatigue life