首页 | 本学科首页   官方微博 | 高级检索  
     

基于人工神经网络的L9(34)正交实验预测特点研究
引用本文:蔡安辉,潘冶,刘永刚,孙国雄. 基于人工神经网络的L9(34)正交实验预测特点研究[J]. 应用科学学报, 2004, 22(2): 228-232
作者姓名:蔡安辉  潘冶  刘永刚  孙国雄
作者单位:东南大学机械系 江苏南京 210096
基金项目:国家自然科学基金资助项目(59974011)
摘    要:用五组L9(34)正交实验结果作为训练学习样本集,通过人工神经网络对其预测特点进行了探讨.结果表明:完备的正交实验样本集是基本训练学习单元,不可分割,其预测结果与实测结果吻合很好.同一类型同一实验条件下,完备的信息量大的正交实验样本集通过人工神经网络能很好地预测其他完备的信息量小的正交实验样本集,这为正交设计提供了有意义的参考思路.

关 键 词:人工神经网络  预测特点  样本集  正交实验  
文章编号:0255-8297(2004)02-0228-05
收稿时间:2003-03-16
修稿时间:2003-06-03

Forecasting Characters of L9(34) Orthogonal Test Based on the Artificial Neural Network
CAI An-hui,PAN Ye,LIU Yong-gang,SUN Guo-xiong. Forecasting Characters of L9(34) Orthogonal Test Based on the Artificial Neural Network[J]. Journal of Applied Sciences, 2004, 22(2): 228-232
Authors:CAI An-hui  PAN Ye  LIU Yong-gang  SUN Guo-xiong
Affiliation:Department of Technical Engineering, Southeast University, Nanjing 210096, China
Abstract:Five sets of results for different L_9(3~4) orthogonal tests were used as the training-study samples, the forecasting characters of L_9(3~4) orthogonal test were researched on the basis of the artificial neural network. The results showed that the self-contained orthogonal sample collection was the basic training-studying cell and was indivisible. Their forecasting results were tallied with the test results. When others samples were added into the self-contained orthogonal samples or the self-contained orthogonal samples were reduced, the forecasting results would be completely irresponsible. Under the same test conditions and with the same orthogonal test type, the self-contained orthogonal sample containing large information could forecast other self-contained orthogonal samples with small information. It provides a significant novel test-design approach for the orthogonal test.
Keywords:artificial neural network  orthogonal test  forecasting characters  sample collection
本文献已被 CNKI 维普 万方数据 等数据库收录!
点击此处可从《应用科学学报》浏览原始摘要信息
点击此处可从《应用科学学报》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号