采用人工免疫算法的加速寿命试验分析方法  

Analysis method of step-down-stress accelerated life test with artificial immune algorithm

作　　者：冯文晖[1] 胡昌华[1] 张琪[1] 扈晓翔[1] 

机构地区：[1]第二炮兵工程学院,西安710025

出　　处：《电光与控制》2008年第10期74-77,共4页Electronics Optics & Control

基　　金：国家自然科学基金重点课题支持项目(60734026);教育部新世纪优秀人才支持计划

摘　　要：极大似然估计是加速寿命试验统计分析中常用的分析方法,但似然函数的优化问题是该方法广泛运用的主要障碍,常用的似然函数优化算法对初值要求高,而且容易陷入局部最优解。为了有效地解决上述问题,在似然函数的优化中引入了人工免疫算法,提出了一种采用人工免疫算法的步降应力加速寿命试验分析方法。利用人工免疫算法在解决多维复杂函数优化问题时强大的全局寻优能力,有效地解决了似然函数的优化问题。最后通过实例验证表明,采用人工免疫算法的步降应力加速寿命试验分析方法是有效的,而且在统计分析中避免了查统计用表,能够很方便的实现计算机编程计算,有较大的工程应用价值。Maximum Likelihood Estimate （MLE） is a widely used method in the analysis of Accelerated Life Tests （ALT）, while the optimization of the likelihood function is a main obstacle to the application of MLE in ALT. The common algorithm to resolve likelihood function has a strict requirement to the initial value, and is easily plunged into local optimum. In order to resolve these problems, a new analysis method, step-down-stress accelerated life test based on artificial immune algorithm, is put forward, in which artificial immune algorithm is introduced to optimize the likelihood function. The advantage of the artificial immune algorithm in the optimization of the multi-dimension complicated function is used to optimize the likelihood function. Practical example demonstrated the feasibility and effectiveness of the proposed method. Besides, since it is not needed to consult statistic tables, computer programming becomes easier, thus the method can be easily applied in engineering.

关 键 词：加速寿命试验 人工免疫算法 极大似然估计 Akaike信息准则 

分 类 号：V271.4[航空宇航科学与技术—飞行器设计] TP114.3[自动化与计算机技术—控制理论与控制工程]