A Case Study on Selecting a Best Allocation of New Data for Improving the Estimation Precision of System and Subsystem Reliability Using Pareto Fronts

This article demonstrates how the Pareto front multiple objective optimization approach can be used to select a best allocation of new data to collect from among many different possible data sources with the goal of maximally reducing the width of the credible intervals of system and two subsystem reliability estimates. The method provides a streamlined decision-making process by identifying a set of noninferior or admissible allocations either from a given set of candidate choices or through a global optimization search and then using graphical methods for selecting the best allocation from the set of contending choices based on the specific goals of the study. The approach allows for an easy assessment of the tradeoffs between criteria and the robustness of different choices to different prioritization of experiment objectives. This is important for decision makers to make a defensible choice of a best allocation that matches their priorities as well as to quantify the anticipated advantages of their choice relative to other options. The method is demonstrated on a small nonaging series system with two subsystems comprised of six components for a total of nine possible data sources. We first consider finding the Pareto front of superior allocations based on 60 logistically viable candidates that have been identified, and second, optimizing over all possible allocations within the allowable fixed budget and comparing how global solutions perform relative to the logistically viable choices. We develop a new search algorithm to populate the Pareto front while taking into account the different costs of the data sources. The method generalizes easily to other system structures and flexible objectives of interest. In addition, a new Fraction of Weight Space plot (FWS) is proposed to provide a simple comparison between different solution choices by summarizing individual performance over the entire weighting space. This article has supplementary materials and computer code available online.