Data-driven implicit design preference prediction model for product concept evaluation via BP neural network and EEG

Customer preference-involved product concept evaluation is a vital stage for developing new products. One of the key factors in this stage is to mine the potential relationships between customers' needs and technical requirements. In most new product development (NPD), design characteristics (DCs) are employed as performance indicators to describe the technical requirements of a scheme. Previous studies have focused on evaluating the degree to which a scheme meets the performance value of DCs, disregarding the relationship between DCs and potential user preferences. This oversight leads to an inability to accurately predict customer satisfaction with the candidate schemes based on their preferences. Previous research, which was aimed at ensuring the preference value of schemes by utilizing mapping data between design preference (DP) and DCs, overlooked users' psychological states and thus failed to accurately capture their cognitive preferences for the schemes. To address these issues, an electroencephalogram (EEG) data-driven, implicit DP prediction approach is proposed. The method characterizes the implicit cognitive relationship between DP and DCs by mining EEG data and utilizes a back propagation (BP) neural network to predict DP. First, a user's DP word pairs were constructed based on the approach of statistical analysis, and the best-worst method (BWM) was introduced to obtain the importance of DCs. Second, an experiment was designed based on the extracted preference word pairs to collect EEG data that reflect a user's DC preference, record the user's stimulation state toward the DCs, and label their DP based on the segmentation results of preference evaluation. Third, a BP neural network was employed to construct a preference prediction model for DCs, and the reliability of the proposed preference prediction model was validated by using the forklift design example. The prediction results further exhibited the potential association between user preferences and DCs that can be acquired by EEG data mining. The results also provide support for designers to promptly acquire design concepts that satisfy user requirements (URs), thereby enhancing the efficiency and quality of product development in a highly competitive market.