A data-driven design parameter recommendation approach based on personalized requirements for product conceptual design

Haoran Cui, Lin Gong*, Yan Yan

*此作品的通讯作者

科研成果: 期刊稿件文章同行评审

摘要

To rapidly meet various personalized customer requirements (PCRs) in the product conceptual design process, the requirement automatic analysis and design parameters (DPs) intelligent recommendation approach is regarded as a critical factor in the competition of enterprises’ design capabilities. Nevertheless, most existing DP recommendation methods cannot achieve ideal performance under the background of massive personalized data and high-accuracy demand of the results. To fill in this gap, this paper proposes a data-driven DP recommendation approach for PCRs, which assists designers in automatically getting a design scheme to users’ input requirements. Focusing on problems such as complexity concerns, namely requirement features elicitation, personalized requirements generic expression. et al., the proposed approach contains a completed requirements analysis process, the quantification expression of personalized requirements, and the accuracy DP prediction process. Hence, the proposed approach not only automates the conceptual design process for PCR but also guarantees the accuracy of the output DPs. Moreover, a practical case on the design of refrigerators is utilized, and satisfaction of the recommended results could be predicted to verify the efficacy of the proposed approach. It can be inferred that this work can effectively assist designers in a more efficient and accurate design process.

源语言英语
文章编号110885
期刊Computers and Industrial Engineering
201
DOI
出版状态已出版 - 3月 2025

指纹

探究 'A data-driven design parameter recommendation approach based on personalized requirements for product conceptual design' 的科研主题。它们共同构成独一无二的指纹。

引用此

Cui, H., Gong, L., & Yan, Y. (2025). A data-driven design parameter recommendation approach based on personalized requirements for product conceptual design. Computers and Industrial Engineering, 201, 文章 110885. https://doi.org/10.1016/j.cie.2025.110885