Predicting human design decisions with deep recurrent neural network combining static and dynamic data
Predicting human design decisions with deep recurrent neural network combining static and dynamic data
复制标题
利用结合静态和动态数据的深度循环神经网络预测人类设计决策
DOI：
10.1017/dsj.2020.12
复制
发表时间：
2020
期刊：
影响因子：
2.4
通讯作者：
Sha, Zhenghui
中科院分区：
文献类型：
--
作者：
Rahman, Molla Hafizur;Yuan, Shuhan;Xie, Charles;Sha, Zhenghui
人类顺序设计过程的计算建模和未来设计决策的成功预测是设计知识提取、转移和人工设计代理开发的基础。然而，在设计实践中往往很难获得与设计者相关的属性（静态数据），而在工程设计中基于静态和动态数据（设计动作序列）相结合的研究还有待探索。本文提出了一种方法，结合静态和动态数据的人的设计决策预测使用两种不同的方法。第一种方法直接将顺序设计操作与递归神经网络（RNN）模型中的静态数据相结合，而第二种方法集成了一个前馈神经网络，该网络单独处理静态数据，但与RNN并行。本研究从三个方面对该领域做出了贡献：（a）提出了一种利用设计师的聚类信息作为静态特征的替代，将设计动作序列与设计动作联合收割机结合起来，以解决获取设计师相关属性的难题;（B）设计了一种将功能-行为-结构设计过程模型与单一设计过程模型相结合的方法，RNN中的热向量化，将设计动作数据转换为设计过程阶段，在设计过程阶段可以获得对设计思维的洞察;（c）据我们所知，这是第一次比较RNN中静态和动态数据的两种结合方法，这提供了新的知识，不同的组合方法在研究顺序设计决策的效用。该方法在两个太阳能系统设计的案例研究中得到了证明。结果表明，通过适当的内核模型，具有静态和动态数据的RNN优于仅依赖于设计动作序列的传统模型，从而更好地支持静态特征（如人体特征）通常起重要作用的设计研究。
Computational modeling of the human sequential design process and successful prediction of future design decisions are fundamental to design knowledge extraction, transfer, and the development of artificial design agents. However, it is often difficult to obtain designer-related attributes (static data) in design practices, and the research based on combining static and dynamic data (design action sequences) in engineering design is still underexplored. This paper presents an approach that combines both static and dynamic data for human design decision prediction using two different methods. The first method directly combines the sequential design actions with static data in a recurrent neural network (RNN) model, while the second method integrates a feed-forward neural network that handles static data separately, yet in parallel with RNN. This study contributes to the field from three aspects: (a) we developed a method of utilizing designers’ cluster information as a surrogate static feature to combine with a design action sequence in order to tackle the challenge of obtaining designer-related attributes; (b) we devised a method that integrates the function–behavior–structure design process model with the one-hot vectorization in RNN to transform design action data to design process stages where the insights into design thinking can be drawn; (c) to the best of our knowledge, it is the first time that two methods of combining static and dynamic data in RNN are compared, which provides new knowledge about the utility of different combination methods in studying sequential design decisions. The approach is demonstrated in two case studies on solar energy system design. The results indicate that with appropriate kernel models, the RNN with both static and dynamic data outperforms traditional models that only rely on design action sequences, thereby better supporting design research where static features, such as human characteristics, often play an important role.
登录
查看更多内容
DOI：
10.1115/detc2018-86300
发表时间：
2018
期刊：
ASME 2018 International Design Engineering Technical Conferences & Computers and Information in Engineering Conference
影响因子：
--
作者：
Rahman, Molla Hafizur;Gashler, Michael;Xie, Charles;Sha, Zhenghui
通讯作者：
Sha, Zhenghui
链接摄影术
DOI：
10.2307/j.ctv22jnr93.10
发表时间：
2018
期刊：
The Military-Entertainment Complex
影响因子：
--
作者：
M. Bassetti;E. Righi;C. Viscoli
通讯作者：
C. Viscoli
影响因子：
3.6
作者：
Griffin, Susan;Welton, Nicky J.;Claxton, Karl
通讯作者：
Claxton, Karl
设计作为顺序决策过程的两种应用
DOI：
--
发表时间：
2017
期刊：
Design Automation Conference
影响因子：
--
作者：
S. Miller;T. Simpson;M. Yukish
通讯作者：
M. Yukish
影响因子：
2.2
作者：
C. Lingard
通讯作者：
C. Lingard