Open AccessNear-explosion failure of elman neural network based on bootstrap
Author(s) -
Xinyue Zhao,
S. F. Liu,
Yutong Ji,
X. B. Luo
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1721/1/012045
Subject(s) - fuze , artificial neural network , function (biology) , computer science , test data , artificial intelligence , engineering , materials science , evolutionary biology , metallurgy , biology , programming language
In this paper, for the fuze of a certain type of fuze, there is a phenomenon that the fuze function of the fuze is invalid. The method of using the Bootstrap method to resample the experimental data, increase the sample size, and obtain the regular data, and use the back propagation neural network to establish the fuze near-failure learning model, and obtain a more accurate model by training the model. Test data is brought into the model and its accuracy is verified to ensure the accuracy of the model. It provides model support for the analysis of the weak condition of the fuze near-explosion function failure, and provides reference for the analysis of other fuzes.