Neural network for structural stress concentration factors in reliability-based optimization

Author:

Zhang Y M1,Zhang L2,Zheng J X2,Wen B C1

Affiliation:

1. School of Mechanical Engineering and Automation, Northeastern University, Shenyang, People's Republic of China

2. College of Mechanical Science and Engineering, Nanling Campus, Jilin University, Changchun, People's Republic of China

Abstract

Stress concentration damage is one of the most troublesome problems in practical engineering structures. In order to reduce damage, it is very important to determine stress concentration factors accurately. An artificial neural network (NN) technique has been used in this article to simulate the relationship between basic random variables and stress concentration factors, and the explicit expression of the stress concentration factors can be obtained directly. The expression of the stress concentration and the reliability theory have been combined to solve the structural reliability problems; then, the corresponding methods of reliability analysis and optimization design have been presented.

Publisher

SAGE Publications

Subject

Mechanical Engineering,Aerospace Engineering

Cited by 5 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Graphic illustration for mechanical reliability design (2): theory and method;Life Cycle Reliability and Safety Engineering;2019-11-16

2. Utilizing artificial neural networks for stress concentration factor calculation in butt welds;Journal of Constructional Steel Research;2017-11

3. Neural network-based assessment of the stress concentration factor in a T-welded joint;Journal of Constructional Steel Research;2017-01

4. Reliability-based robust design optimization of vehicle components, Part I: Theory;Frontiers of Mechanical Engineering;2015-04-15

5. Reliability-based design for automobiles in China;Frontiers of Mechanical Engineering in China;2008-10-01

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3