AN APPROACH TO CONSIDER UNCERTAIN COMPONENTS' FAILURE RATES IN SERIES-PARALLEL RELIABILITY SYSTEMS WITH REDUNDANCY ALLOCATION

Redundancy Allocation Problem (RAP) is a combinatorial problem to maximize system reliability by discrete selection from available components. The main purpose of this study is to prove the effectiveness of robust optimization to solve RAP. In this study it is assumed to have Erlang distribution density for components' failures where to implement robust optimization. We suppose that failure rate attains dynamic values instead of exact and fixed values. Therefore, a new calculation method is presented to consider dynamic values for failure rate in RAP. Another assumption is that each subsystem can have one of cold-standby or active redundancy strategies. Moreover, due to complexity of RAP, two Simulated Annealing (SA) and Ant Colony Optimization (ACO) algorithms are designed to determine the robust system with respect to uncertain values for parameters. In order to solve this problem and prove efficiency of proposed algorithms, a problem benchmark in literature is solved and discussed.