An integrated methodology for robustness analysis in feature fatigue problem

Feature fatigue (FF) analysis is of critical importance for product development. To deal with the FF problem, it is essential to decide what features should be added to make the product attractive enough and not too hard to use at the same time. This paper introduces a novel methodology to search for robust feature combinations under uncertain customer preferences in FF analysis. Non-dominated sorting genetic algorithm II (NSGA-II) is firstly adopted to establish a multi-objective optimisation model. Then a grey forecasting model and a worst-case strategy are used to create different coefficient scenarios based on customer evaluation data. After running NSGA-II under each scenario, several candidate solutions for final selection can be obtained according to robustness analysis. Compared with existing studies in FF, the proposed method can obtain multiple optimal solutions rather than just a single one for designers to choose from, and the robustness degree of each solution is computed considering both present and future customer preferences. The usefulness of the proposed methodology is illustrated using a smart phone case study.