Neural network applied to prediction of the failure stress for a pressurized cylinder containing defects

被引:9
作者
Han, LH [1 ]
Han, LX [1 ]
Liu, CD [1 ]
机构
[1] Tsing Hua Univ, Inst Nucl Energy Technol, CAD, Beijing 100084, Peoples R China
关键词
neural network; pressurized cylinder; failure stress;
D O I
10.1016/S0308-0161(98)00129-X
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
An application of the neural network to predict the failure stress of a cylinder with penetrating flaws under internal pressure is studied in this article, The results from the new method are compared with the experimental results. In addition, the neural network method is used to analyze the sensitivity of parameters of a pressurized cylinder with defects. Satisfactory results are obtained. It is shown that the neural network could be a potential tool in engineering practice. (C) 1999 Elsevier Science Ltd. All rights reserved.
引用
收藏
页码:215 / 219
页数:5
相关论文
共 7 条
[1]  
DESHAN K, 1994, COMPUTERS APPL CHEM, V11, P225
[2]  
Hertz J., 1991, Introduction to the Theory of Neural Computation
[3]  
Kiefner J.F., 1973, ASTM STP, V536, P461
[4]  
Pao Y. H., 1989, ADAPTIVE PATTERN REC
[5]   LEARNING REPRESENTATIONS BY BACK-PROPAGATING ERRORS [J].
RUMELHART, DE ;
HINTON, GE ;
WILLIAMS, RJ .
NATURE, 1986, 323 (6088) :533-536
[6]  
RUMELHART DE, 1986, PARALLEL DISTRUBED P, V2
[7]  
RUMELHART DE, 1986, PARALLEL DISTRUBED P, V1