A fuzzy reliability model for series-parallel systems

Fuzzy set based methods have been proved to be effective in handling many types of uncertainties in different fields, including reliability engineering. This paper presents a new approach on fuzzy reliability, based on the use of beta type distribution as membership function. Considering experts' ideas and by asking operators linguistic variables, a rule base is designed to determine the level of reliability of each component. Hence, we can determine the level of reliability of components with expending low costs. Also in this work a simple approach is presented for reducing the number of rules. The outputs of the presented model are fuzzy sets representing the reliability levels of components. In order to determine the level of reliability as linguistic variables, a new method is presented. Also the validity of the model is investigated by two methods. After determining the level of reliability of each component, the reliability of the composed system can be determined by using t-norm and s-norm functions. The system can be parallel, series, parallel-series or series-parallel. The presented model has been applied in a glass manufacturing company.