当前位置: X-MOL 学术Proc. Inst. Mech. Eng. C J. Mec. Eng. Sci. › 论文详情
Artificial neural network for Gaussian and non-Gaussian random fatigue loading analysis
Proceedings of the Institution of Mechanical Engineers Part C-Journal of Mechanical Engineering Science ( IF 1.359 ) Pub Date : 2019-10-01 , DOI: 10.1177/0954406219878763
JF Durodola

Stationary ergodic Gaussian random data have been the convenient basis of many of the data used for the development of models for the analysis of random vibration fatigue problems especially using spectral-based methods.1–5 It is, however, known that non-Gaussian excitations occur due to road irregularities in automobiles and turbulent pressure flections in the aerospace sector.6,7 Highly non-Gaussian excitations occur on rail vehicles caused by wheel–rail contact.8 Wind loading effects are also known to be non-Gaussian with high uncertainties and peak values.9 The main consequence of non-Gaussian data effect is that its peakedness effect can be overlooked in analysis and may lead to failure. There have, therefore, been a lot of interest in non-Gaussian fatigue loading analysis.7,10 A number of researchers have attempted to use higher order statistical properties such as signal Kurtosis as an additional parameter to resolve issues associated with inaccuracies encountered in fatigue life prediction under non-Gaussian loading condition.11 A lot of effort has also been going on towards the modelling simulation of non-Gaussian data for fatigue analysis.7,10,12,13
更新日期:2020-01-06

 

全部期刊列表>>
Springer Nature 2019高下载量文章和章节
化学/材料学中国作者研究精选
《科学报告》最新环境科学研究
ACS材料视界
自然科研论文编辑服务
中南大学国家杰青杨华明
南开大学陈弓课题组招聘启事
中南大学
材料化学和生物传感方向博士后招聘
课题组网站
X-MOL
北京大学分子工程苏南研究院
华东师范大学分子机器及功能材料
中山大学化学工程与技术学院
试剂库存
天合科研
down
wechat
bug