An integrated implicit user preference mining approach for uncertain conceptual design decision-making: A pipeline inspection trolley design case study

Abstract

User preference mining is one of the most crucial activities in the conceptual design process, aiming to gain customer attentions at the early design stage. Since user preference is usually ambiguous, existing methods of preference extraction and assessment strongly rely on design experience and hard to analyze the implicit design preferences at semantic level. In addition, the abstraction of the knowledge representation prevents a reasonable judgment of the scheme’s potential value. To fill these gaps, by utilizing natural language processing (NLP) technology and semantic network, an integrated implicit design preference (DP) mining approach is proposed to support the uncertain conceptual design decision-making. The proposed approach has three parts: first, the design knowledge semantic network (DKSN) is constructed by using NLP and patent data, which provides a new retrieval mode for function solving; second, TF–IDF model is introduced to extract the DPs, a similarity matrix between the principle solution (PS) retrieved from DKSN and design characteristic (DC) is constructed using word vector model, which can mine the potential satisfaction of various DPs in each PS; and third, based on the satisfaction matrix of PSs, a normalized comprehensive value matrix of the schemes is constructed, and the optimal scheme is obtained using rough VIKOR (VIseKriterijumska Optimizacija I Kompromisno Resenje). A case study of pipeline inspection trolley design is used to validate the proposed approach, sensitivity analysis shows that the proposed model truly captures the scheme’s intention. Additionally, the constructed DKSN has positive implications for assisting designers in exploring the design space.