Neural network systems to reproduce crash behavior of structural components

被引：48

作者：

Lanzi, L ^{[1
]}

Bisagni, C ^{[1
]}

Ricci, S ^{[1
]}

机构：

[1] Politecn Milan, Dipartimento Ingn Aerospaziale, I-20156 Milan, Italy

来源：

COMPUTERS & STRUCTURES | 2004年 / 82卷 / 01期

关键词：

crashworthiness; neural networks; response surfaces; riveted tubes; honeycomb structures; helicopter subfloor;

D O I：

10.1016/j.compstruc.2003.06.001

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

The use of neural networks as global approximation tool in crashworthiness problems is here investigated. Neural networks are not only asked to return some meaningful indices of the structural behavior but also to reproduce load-time curves during crash phenomena. To contain the number of examples required for the training process, parallel subsystems of small neural networks are designed. Design points for the training process are obtained by explicit finite element analyses performed by PAMCRASH. The settlement of the points in the design domain is defined using a maximum distance concept. The procedure is applied to different typical absorption structures made of aluminum alloy: riveted tubes, honeycomb structures, longitudinal keel beam and intersection elements of helicopter subfloors. (C) 2003 Elsevier Ltd. All rights reserved.

引用

页码：93 / 108

页数：16

共 34 条

[1]

[Anonymous], 1986, PARALLEL DISTRIBUTED

[2] Static and dynamic properties of high-density metal honeycombs [J].

Baker, WE ;

Togami, TC ;

Weydert, JC .

INTERNATIONAL JOURNAL OF IMPACT ENGINEERING, 1998, 21 (03) :149-163

[3] Crashworthiness of helicopter subfloor structures [J].

Bisagni, C .

INTERNATIONAL JOURNAL OF IMPACT ENGINEERING, 2002, 27 (10) :1067-1082

[4] Optimization of helicopter subfloor components under crashworthiness requirements using neural networks [J].

Bisagni, C ;

Lanzi, L ;

Ricci, S .

JOURNAL OF AIRCRAFT, 2002, 39 (02) :296-304

[5]

BISAGNI C, 1999, INT J CRASHWORTHINES, V4, P199

[6]

BISAGNI C, 2002, P 9 AIAA ISSMO S MUL

[7]

BLAZINSKY TZ, 1987, MAT HIGH STRAIN RATE

[8]

CAMMARATA S, 1997, RETI NEURONALI PERCP

[9] A COMPARISON OF POLYNOMIAL APPROXIMATIONS AND ARTIFICIAL NEURAL NETS AS RESPONSE SURFACES [J].

CARPENTER, WC ;

BARTHELEMY, JFM .

STRUCTURAL OPTIMIZATION, 1993, 5 (03) :166-174

[10]

*DEP DEF, 1988, MILSTD1290A AV DEP D

← 1 2 3 4 →