计算机与现代化

• 网络与通信 • 上一篇    下一篇

基于PSO-BP神经网络的应力测量与补偿模型

  

  1. (南京航空航天大学计算机科学与技术学院,江苏南京210016)
  • 收稿日期:2014-12-15 出版日期:2015-06-16 发布日期:2015-06-18
  • 作者简介:郝纲(1989-),男,天津人,南京航空航天大学计算机科学与技术学院硕士研究生,研究方向:并行与分布计算; 庄毅(1956-),女,江苏南京人,教授,博士生导师,研究方向:计算机网络,并行与分布计算。
  • 基金资助:
    国家自然科学基金青年科学基金资助项目(61202351); 江苏省普通高校研究生科研创新计划资助项目(CXZZ13_0171)

A Stress Measurement and Compensation Model Based on PSO-BP Neural Network

  1. (College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China)
  • Received:2014-12-15 Online:2015-06-16 Published:2015-06-18

摘要: 针对柔性材料在工作过程中受力情况难以直接并准确测量的问题,提出一种基于粒子群优化的BP神经网络应力测量与补偿模型。在模型的训练过程中,采用粒子群算法对模型中的初始权值和阈值进行优化,解决BP神经网络收敛速度慢的问题。通过与柔性材料标准曲线的对比实验,验证了该模型对柔性材料进行应力测量的有效性和准确性。

关键词: 柔性材料, 粒子群, BP神经网络, 测量, 补偿

Abstract: For the problem that the stress distribution of flexible material is difficult to directly and accurately measure in the working process, this paper proposes a stress measurement and compensation model based on BP neural network with particle swarm optimization. In order to avoid trapping in local optimum, we use particle swarm optimization algorithm to optimize the model’s initial weights and threshold in the process of the training of the model. Through the contrast experiment with flexible material’s standard curve, effectiveness and accuracy of the model is verified when it is applied in stress measurement on the flexible fabric.

Key words: flexible material, particle swarm optimization, BP neural network, measure, compensation

中图分类号: