Study on Dynamic Reliability of Barrel Shell Based on RBF Neural Network

DOI

10.2991/msmee-17.2017.238How to use a DOI?

Keywords

Dynamic reliability; RBF neural network; Response Surface Method; First Excursion Failure Criterion; Linearized Nataf transformation

Abstract

An algorithm for dynamic reliability analysis of a stochastic structure is proposed based on the theory of Neural Network Response Surface Method. On the basis of First Excursion Failure Criterion of random vibration, the performance function of dynamic reliability is established. Sequential Surface Response Method is introduced, and subsequently three-layer BP network is used to fit the performance function. A new method combining linearized Nataf transformation and iHLRF algorithm is proposed, which is introduced to compute dynamic reliability in barrel shell. Compared with other existing methods, the proposed method not only markedly reduces the iterations times, but also have better accuracy. It has wide prospect in dynamic reliability of spatial structures.

Copyright

© 2017, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Zhifei Song
AU  - Huijun Li
AU  - Biao Li
AU  - Jinlei Qin
PY  - 2017/05
DA  - 2017/05
TI  - Study on Dynamic Reliability of Barrel Shell Based on RBF Neural Network
BT  - Proceedings of the 2017 2nd International Conference on Materials Science, Machinery and Energy Engineering (MSMEE 2017)
PB  - Atlantis Press
SP  - 1265
EP  - 1269
SN  - 2352-5401
UR  - https://doi.org/10.2991/msmee-17.2017.238
DO  - 10.2991/msmee-17.2017.238
ID  - Song2017/05
ER  -