Research on reliability method of complex mechanical structure based on active learning

CORC > 沈阳自动化研究所 > 中国科学院沈阳自动化研究所 > 空间自动化技术研究室

	Research on reliability method of complex mechanical structure based on active learning
	Wang P(王鹏)1; Luo HT(骆海涛)2; Sun ZL (孙志礼)1
	2019
会议日期	October 25-27, 2019
会议地点	Hohhot, China
关键词	reliability Kriging Monte Carlo learning function failure probability
其他题名	Research on reliability method of complex mechanical structure based on active learning.pdf
页码	103-106
英文摘要	In order to solve the problem of implicit function and long simulation time in reliability analysis of complex mechanical structure, the reliability calculation method based on Kriging and Monte Carlo is adopted. In order to improve the accuracy of Kriging model quickly, the sample points which minimize the value of learning function are selected and substituted into the model. A learning stopping condition is proposed, which ensures the prediction accuracy of sample point symbols and significantly reduces the number of learning times. Finally, the numerical minimization problem and the artillery coordinator are taken as examples to verify the correctness of the proposed method.
产权排序	2
会议录	Proceedings - 2019 4th International Conference on Mechanical, Control and Computer Engineering, ICMCCE 2019
会议录出版者	IEEE
会议录出版地	New York
语种	英语
ISBN号	978-1-7281-4689-8
内容类型	会议论文
源URL	[http://ir.sia.cn/handle/173321/26279]
专题	沈阳自动化研究所_空间自动化技术研究室
通讯作者	Wang P(王鹏)
作者单位	1.School of Mechanical Engineering and Automation, Northeastern University, Shenyang, China 2.Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, China
推荐引用方式 GB/T 7714	Wang P,Luo HT,Sun ZL . Research on reliability method of complex mechanical structure based on active learning[C]. 见:. Hohhot, China. October 25-27, 2019.