State space

Quantum mechanics

Complex system

Algorithm

Dempster–Shafer theory

Common cause failure

Engineering

Reliability engineering

Uncertainty quantification

Statistics

Bayesian network

Power (physics)

Data mining

Computer science

Business decision mapping

Physics

Evidential reasoning approach

Mathematics

Reliability (semiconductor)

Artificial intelligence

Parametric statistics

Decision support system

Common cause and special cause

Machine learning

State (computer science)

Reliability Engineering & System Safety

With the increasing complexity and size of modern advanced engineering systems, the traditional reliability theory cannot characterize and quantify the complex characteristics of complex systems, such as multi-state properties, epistemic uncertainties, common cause failures (CCFs). This paper focuses on the reliability analysis of complex multi-state system (MSS) with epistemic uncertainty and CCFs. Based on the Bayesian network (BN) method for reliability analysis of MSS, the Dempster-Shafer (DS) evidence theory is used to express the epistemic uncertainty in system through the state space reconstruction of MSS, and an uncertain state used to express the epistemic uncertainty is introduced in the new state space. The integration of evidence theory with BN which called evidential network (EN) is achieved by adapting and updating the conditional probability tables (CPTs) into conditional mass tables (CMTs). When multiple CCF groups (CCFGs) are considered in complex redundant system, a modified β factor parametric model is introduced to model the CCF in system. An EN method is proposed for the reliability analysis and evaluation of complex MSSs in this paper. The reliability analysis of servo feeding control system for CNC heavy-duty horizontal lathes (HDHLs) by this proposed method has shown that CCFs have considerable impact on system reliability. The presented method has high computational efficiency, and the computational accuracy is also verified.

Reliability analysis of complex multi-state system with common cause failure based on evidential networks