Reliability evaluation for complex systems based on interval-valued triangular fuzzy weighted mean and evidence network

Aiming at the problem in obtaining the precise failure rates of components, this paper presents a new reliability evaluation method for complex systems using interval triangular fuzzy subset and evidence network (EN). Specifically, it develops the fault tree model based on failure mode and effects analysis (FMEA) and uses the interval-valued triangular fuzzy weighted mean to express the interval failure rates of components. Furthermore, fuzzy fault tree is mapped into an EN to calculate some reliability parameters. In addition, a possibility-based NSG ranking approach is adopted to rank components and get the critical component, which can be used to provide the basis for system optimization and maintenance decision-making. Finally, a numerical example is given to validate the availability and efficiency of the proposed method.