北京航空航天大学学报 ›› 2005, Vol. 31 ›› Issue (11): 1172-1176.

• 论文 • 上一篇    下一篇

一类解决变应力加速寿命试验参数估计的方法

苑中魁, 王少萍   

  1. 北京航空航天大学 自动化科学与电气工程学院, 北京 100083
  • 收稿日期:2004-07-09 出版日期:2005-11-30 发布日期:2010-09-20
  • 作者简介:苑中魁(1980-),男,河北石家庄人,硕士生, yuanzhongkui@163.com.
  • 基金资助:

    国家自然科学基金资助项目(60371043); 北京市自然基金资助项目(4012009); 新世纪优秀人才支持计划(NCET)

One method solving parameter estimation of varying stress accelerated life test

Yuan Zhongkui, Wang Shaoping   

  1. School of Automation Science and Electrical Engineering, Beijing University of Aeronautics and Astronautics, Beijing 100083, China
  • Received:2004-07-09 Online:2005-11-30 Published:2010-09-20

摘要: 变应力加速寿命试验的极大似然函数是高维非线性复杂目标函数,其待估参数多,采用梯度下降优化方法进行参数估计容易陷入局部极值,而采用全局优化方法又存在寻优效率低的问题.为了解决复杂多维目标函数优化的瓶颈问题,设计了一种基于实数编码遗传算法和Powell法的遗传加速方法.利用适应度函数获得两种优化方法的最佳切换点,最大程度发挥遗传算法和Powell算法的优点,既提高了多维非线性目标函数寻优效率又保证了参数估计的全局最优.液压泵加速寿命试验实例分析结果表明,遗传加速方法可以在寻优前期利用遗传算法保证待估参数的全局最优估计,在寻优后期快速逼近最优值,使寻优成功率达到85%.

Abstract: The maximum likelihood function of varying stress accelerated life is a nonlinear multi-dimension complex object function with five evaluated parameters, whose parameter estimation is easy to get into local optimization with grads descending algorithm while has low searching efficiency with global optimal algorithm. To solve the bottleneck between direct and intellective optimization of multi-dimension complex object function, the genetic accelerated algorithm was presented based on real code genetic algorithm and Powell method. Through designing perfect switch with adaptive function, the genetic accelerated algorithm takes the advantages both genetic algorithm and Powell method at furthest that ensure global optimization and keep rapid searching velocity to multi-dimension complex object function. Application of hydraulic pump on accelerated life test shows that the genetic accelerated algorithm was able to fulfill global optimization at the beginning of parameter evaluation process and approach optimal values rapidly at the end of the process, its success rate of optimization can reach 85%.

中图分类号: 


版权所有 © 《北京航空航天大学学报》编辑部
通讯地址:北京市海淀区学院路37号 北京航空航天大学学报编辑部 邮编:100191 E-mail:jbuaa@buaa.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发