|
|
论文:2014,Vol:32,Issue(4):637-641 |
|
|
引用本文： |
|
|
陈绍炜, 潘新, 刘涛. 基于遗传算法SVM的电子元件寿命预测[J]. 西北工业大学 |
|
|
Chen Shaowei, Pan Xin, Liu Tao. A method for Predicting Life of Electronic Components Based on Generic Algorithm and Support Vector Machine (SVM)[J]. Northwestern polytechnical university |
|
|
|
|
|
|
|
| 基于遗传算法SVM的电子元件寿命预测 |
|
| 陈绍炜, 潘新, 刘涛 |
|
| 西北工业大学 电子信息学院, 陕西 西安 710129 |
| 摘要: |
| 针对电子元件在正常应力下的寿命预测,提出了基于遗传算法SVM的预测方法。首先进行多应力水平条件下的寿命实验,得到元件在各个应力下的失效时间,根据失效时间得出相应应力下的可靠性。然后将遗传算法与SVM相结合,建立预测模型,从而不仅可以预测同一应力下元件的寿命,可根据加速应力下元件的寿命来预测正常应力水平下的寿命。实验证明,在小样本条件下,该方法同神经神经网络相比,预测结果的精确度提高了14%,该预测方法能够更准确地预测出电子元器件的寿命。 |
| 关键词:
支持向量机(SVM)
遗传算法
神经网络
寿命预测
多应力
|
|
| A method for Predicting Life of Electronic Components Based on Generic Algorithm and Support Vector Machine (SVM) |
|
| Chen Shaowei, Pan Xin, Liu Tao |
|
| Department of Electronics Engineering, Northwestern Polytechnical University, Xi'an, 710129 |
| Abstract: |
| To accurately predict the life of an electronic component under normal stress, a method based on genetic algorithm SVM is proposed. Firstly, after the test of accelerated life under several stress levels, the components time-out and corresponding reliability can be got. Then combining the genetic algorithm with SVM to build the pre-diction model, which can not only dope out the reliability under the same stress, but also can predict the compo-nents′life under normal stress level according to the life in accelerated life tests. Comparing with neural network this method can exactly predict the life of electronic components under the condition of small samples with improving the precondition accuracy by 14 percent, given in Figs. 1, 3 and 4 and Tables 2 and 3, and their com-parison. |
| Key words:
support vector machines (SVM)
genetic algorithms
neural network
life prediction
multi-stress
|
|
| 收稿日期: 2013-11-08
修回日期:
|
| DOI: |
| 基金项目: 航空科学基金(2012ZD53051)资助 |
| 通讯作者:
Email： |
| 作者简介: 陈绍炜(1970-),西北工业大学副教授、主要从事嵌入式开发、数据与计算机通信的研究。
|
|
| 相关功能 |
|
|
|
|
| 作者相关文章 |
|
| 陈绍炜 在本刊中的所有文章 |
| 潘新 在本刊中的所有文章 |
| 刘涛 在本刊中的所有文章 |
|
|
|
|
|
|
|
|
参考文献: |
|
|
[1] Lawless J F. Statistical Models and Methods for Lifetime Data[M]. 2nd Edition. New York: Wiley, 2003
[2] 邹心遥, 姚若河. 基于 LSSVM 的小子样元器件寿命预测[J]. 半导体技术, 2011, 9(36): 730-733 Zou Xinyao, Yao Ruohe. Life Prediction of Electronic Components with Small Sample Based on LSSVM[J]. Semiconductor Technology, 2011, 9(36): 730-733 (in Chinese)
[3] 胡小平, 韩泉东, 李京浩. 故障诊断中的数据挖掘[M]. 长沙: 国防科技大学出版社, 2009 Hu Xiaoping, Han Quandong, Li Jinghao. Data Mining in Fault Diagnosis[M]. Changsha: National University of Detence Technology Press, 2009 (in Chinese)
[4] Zhang L F, Xie M, Tang L C. A Study of Two Estimationapproaches for Parameters of Weibull Distribution Based on WPP[J]. Reliability Engineering & System Safety, 2007, 92(3): 360-368
[5] Michiel D, Mia H, Suykens J A K. Model Selection in Kernel Basedregression Using the Influence Function. Journal of Machine LearningResearch, 2008, 9(11): 2377-2400
[6] 戴上平, 宋永东. 基于遗传算法与粒子群算法的支持向量机参数选择[J]. 计算机工程与科学, 2012, 10(34): 113-116 Dai Shangping, Song Yongdong. Parameter Selection of Support Vector Machines Based on the Fusion of Genetic Algorithm and the Particle Swarm Optimization[J]. Computer Engineering & Science, 2012, 10(34): 113-116 (in Chinese)
[7] 李春, 邸曼丽. 故障预测技术在半导体设计中的应用[J]. 半导体技术, 2009, 3(32): 280-282 Li Chun, Di Manli. Application of Prognostic Technology in IC Design[J]. Semiconductor Technology, 2009, 3(32): 280-282 (in Chinese)
[8] 洪根深, 肖 志强, 王栩, 周淼. 0. 5 m 部分耗尽 SOI NMOSFET 热载流子可靠性研究[J]. 微电子学, 2012, 2(42): 293-296 Hong Genshen, Xiao Zhiqiang, Wang Xu, Zhou Miao. Study on Hot Carrier Reliability of 0. 5 m PD SOI NMOSFET[J]. Microelectronics, 2012, 2(42): 293-296 (in Chinese) |
|
|
|
相关文献: |
|
|
1．张烈, 冯燕.一种优化的神经网络数字预失真方法[J]. 西北工业大学, 2014,32(6): 967-973 |
|
|
2．郭阳明, 冉从宝, 姬昕禹, 马捷中.基于组合优化BP神经网络的模拟电路故障诊断[J]. 西北工业大学, 2013,31(1): 44-48 |
|
|
3．李伟, 何鹏举, 杨恒, 陈明.基于粗糙集和改进遗传算法优化BP神经网络的算法研究[J]. 西北工业大学, 2012,30(4): 601-606 |
|
|
|
|
|
|
