A Knowledge-Based Method for Rapid Design Concept Evaluation

• Main Authors: Jia Hao, Lingyan Xu, Guoxin Wang, Yiling Jin, Yan Yan
• Format: Article
• Language: English
• Published: IEEE 2019-01-01
• Series: IEEE Access
• Subjects: Concept evaluation; configuration flow graph; feasibility; Naïve Bayesian classifier; neural network; novelty
• Online Access: https://ieeexplore.ieee.org/document/8790704/

Concept generation is one of the most critical steps in product design process. Recently, several computational tools for automatically generating design concepts were developed, which can generate a big number of design concepts. This brings a new challenge to traditional expert-based design concept evaluation methods since experts are not capable of evaluating a large number of design concept in a short time. Therefore, this work develops a knowledge-based method to roughly evaluation design concepts and elect a small number of design concepts for expert-based evaluation. In the proposed method, a knowledge base containing 100 design concepts extracted from existing products is constructed, and four features, including Number of Function (#F), Function Compatibility Index (FCI), Function Component Mapping Index (FCMI) and Component Compatibility Index (CCI) are defined for building evaluation models. Based on the knowledge base and features, several computational evaluation models are developed including novelty evaluation model (NEM), feasibility discrimination model (FDM) and feasibility evaluation model (FEM). Empirical results show the proposed method is capable of evaluating design concepts. This work makes two-fold contributes to the research community, the first is a manually constructed knowledge base is published, while the second is four features are defined and used to define design concept evaluation models.