A numerical method for system residual life prediction based on Simpson formula. Issue 12 (2nd December 2021)

• Record Type: Journal Article
• Authors: Song, Zhao-Li; Zhao, Qian; Jiang, Ping; Guo, Bo
• Is Part Of: Communications in statistics. Volume 50:Issue 12(2021)
• Page Start: 4171
• Page End: 4186
• Publication Date: 2021-12-02
• Subjects: Residual life prediction -- Numerical integration -- Simpson formula; Mathematical statistics -- Periodicals; Mathematical statistics -- Data processing -- Periodicals; Digital computer simulation -- Periodicals; 519.5
• DOI: 10.1080/03610918.2019.1642479
• Languages: English
• ISSNs: 0361-0918

Abstract

Abstract: Residual life prediction for complex system is attracting increasing attentions in practice. However, it is usually difficult to obtain analytical solution due to system complexity. In this paper, based on Simpson formula, a numerical method is proposed to simplify the computation, by which the point estimate of system's residual life can be derived according to the structure characteristics of the system. Four typical reliability subsystems, including series, parallel, voting and cold standby subsystems, are studied, and the analytic relationships between the residual life of each subsystem and the reliability functions of components is discussed respectively. Then, the integral procedure of the Simpson formula is used to obtain the point estimations of residual life of the subsystems as well as the entire system. Finally, an illustrative example is given and the proposed method is verified by Monte Carlo simulation.