• CN:11-2187/TH
  • ISSN:0577-6686

机械工程学报 ›› 2016, Vol. 52 ›› Issue (4): 73-81.doi: 10.3901/JME.2016.04.073

• 材料科学与工程 • 上一篇    下一篇

基于相对误差平方和的神经网络预测镁合金多轴疲劳寿命

熊缨, 岑恺   

  1. 浙江工业大学机械工程学院 杭州 310032
  • 出版日期:2016-02-15 发布日期:2016-02-15
  • 作者简介:熊缨(通信作者),女,1969年出生,教授,博士研究生导师。主要研究方向为材料的疲劳与损伤。E-mail:yxiong@zjtu.edu.cn;岑恺,男,1989年出生,硕士研究生。主要研究方向为镁合金疲劳和神经网络。E-mail:nbcxck@163.com
  • 基金资助:
    国家自然科学基金(51275472)和浙江省自然科学基金(LY12E05024)资助项目

Neural Network Based on Sum Squared Relative Error to Predict the Multixial Fatigue Life of Magnesium Alloy

XIONG Ying, CEN Kai   

  1. College of Mechanical Engineering, Zhejiang University of Technology, Hangzhou 310032
  • Online:2016-02-15 Published:2016-02-15

摘要: 提出一种以相对误差平方和(Sum squared relative error,SSRE)作为误差性能函数的反向传播(Back propagation,BP)神经网络算法(SSRE-BP),针对3种不同镁合金AZ31B、ZK60和AZ61A在单轴拉压、纯扭、45°比例和90°圆形非比例等4种不同加载路径下的疲劳寿命进行预测。并与以均方误差(Mean squared error,MSE)作为误差性能函数的传统BP神经网络(MSE-BP)以及基于临界平面法的SWT疲劳损伤模型预测的结果进行比较。结果表明,在3种镁合金材料总共138组疲劳数据中,神经网络只有一组预测值在3倍偏差界限外,而用SWT预测结果分别有16组、13组、10组数据在3倍偏差界限外。两种BP神经网络能够较好地预测镁合金不同加载路径下的疲劳寿命,相比于SWT疲劳模型预测的寿命在精度上有较大幅度的提升。其中,SSRE-BP算法的精度略高于传统的MSE-BP算法。

关键词: BP神经网络, 镁合金, 疲劳寿命, 相对误差平方和

Abstract: An improved BP network which use sum of squared relative error (SSRE) as the performance function is applied to predict the fatigue life of three kinds of magnesium alloy under different loading paths. Stain-controlled fatigue experiments are conducted on AZ31B and ZK60 magnesium alloy under four loading paths, which including fully reversed tension-compression, cyclic torsion, 45° in-phase axial-torsion and 90° out-of-phase axial-torsion. In addition, the fatigue data of AZ61A magnesium alloy from literature are also adopted. Two fatigue life prediction methods, namely, a standard BP network which use mean squared error(MSE) as the performance function, and Smith-Watson-Topper(SWT) critical plane fatigue models, are evaluated based on the experimentally obtained fatigue results. Result shows that all of the predicted results except one date by both BP network are within factor-of-three boundaries, there are 16 date, 13 date and 10 date predicted by SWT model outside factor-of-three boundaries even factor-of-five boundaries, respectively. Both BP network are found to be able to correlate the fatigue experiments reasonably well in comparison with SWT model, and SSRE-BP network is better than MSE-BP network.

Key words: BP network, fatigue life, magnesium alloy, sum of squared relative error

中图分类号: