Design thinking is often hidden and implicit, so empirical approach based on experiments and data-driven methods has been the primary way of doing such research. In support of empirical studies, design behavioral data which reflects design thinking becomes crucial, especially with the recent advances in data mining and machine learning techniques. In this paper, a research platform that supports data-driven design thinking studies is introduced based on a computer-aided design (cad) software for solar energy systems, energy3d, developed by the team. We demonstrate several key features of energy3d including a fine-grained design process logger, embedded design experiment and tutorials, and interactive cad interfaces and dashboard. These features make energy3d a capable testbed for a variety of research related to engineering design thinking and design theory, such as search strategies, design decision-making, artificial intelligent (AI) in design, and design cognition. Using a case study on an energy-plus home design challenge, we demonstrate how such a platform enables a complete research cycle of studying designers” sequential decision-making behaviors based on fine-grained design action data and unsupervised clustering methods. The results validate the utility of energy3d as a research platform and testbed in supporting future design thinking studies and provide domain-specific insights into new ways of integrating clustering methods and design process models (e.g., the function–behavior–structure model) for automatically clustering sequential design behaviors.

Design is essentially a decision-making process, and systems design decisions are sequentially made. In-depth understanding on human sequential decision-making patterns in design helps discover useful design heuristics to improve existing algorithms of computational design. In this paper, we develop a framework for clustering designers with similar sequential design patterns. We adopt the Function-Behavior-Structure based design process model to characterize designers’ action sequence logged by computer-aided design (CAD) software as a sequence of design process stages. Such a sequence reflects designers’ thinking and sequential decision making during the design process. Then, the Markov chain is used to quantify the transitions between design stages from which various clustering methods can be applied. Three different clustering methods are tested, including the K-means clustering, the hierarchical clustering and the network-based clustering. A verification approach based on variation of information is developed to evaluate the effectiveness of each method and to identify the clusters of designers who show strong behavioral similarities. The framework is applied in a solar energy systems design problem — energy-plus home design. The case study shows that the proposed framework can successfully cluster designers and identify their sequential decision-making similarities and dissimilarities. Our framework can support the studies on the correlation between potential factors (e.g., designers’ demographics) and certain design behavioral patterns, as well as the correlation between behavioral patterns and design quality to identify beneficial design heuristics.

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.

For complex design problems, human has shown surprising capability in effectively reducing the dimensionality of design space and quickly converging it to a reasonable range for algorithms to step in and continue the search process. Therefore, modeling how human designers make decisions in such a sequential design process can help discover beneficial design patterns, strategies, and heuristics, which are essential to the development of new algorithms embedded with human intelligence to augment the computational design. In this paper, we develop a deep learning-based approach to model and predict designers’ sequential decisions in the systems design context. The core of this approach is an integration of the function-behavior-structure model for design process characterization and the long short-term memory unit model for deep leaning. This approach is demonstrated in two case studies on solar energy system design, and its prediction accuracy is evaluated benchmarking on several commonly used models for sequential design decisions, such as the Markov Chain model, the Hidden Markov Chain model, and the random sequence generation model. The results indicate that the proposed approach outperforms the other traditional models. This implies that during a system design task, designers are very likely to rely on both short-term and long-term memory of past design decisions in guiding their future decision making in the design process. Our approach can support human-computer interactions in design and is general to be applied in other design contexts as long as the sequential data of design actions are available.

During a design process, designers iteratively go back and forth between different design stages to explore the design space and search for the best design solution that satisfies all design constraints. For complex design problems, human has shown surprising capability in effectively reducing the dimensionality of design space and quickly converging it to a reasonable range for algorithms to step in and continue the search process. Therefore, modeling how human designers make decisions in such a sequential design process can help discover beneficial design patterns, strategies, and heuristics, which are important to the development of new algorithms embedded with human intelligence to augment computational design. In this paper, we develop a deep learning based approach to model and predict designers’ sequential decisions in a system design context. The core of this approach is an integration of the function-behavior-structure model for design process characterization and the long short term memory unit model for deep leaning. This approach is demonstrated in a solar energy system design case study, and its prediction accuracy is evaluated benchmarked on several commonly used models for sequential design decisions, such as Markov Chain model, Hidden Markov Chain model, and random sequence generation model. The results indicate that the proposed approach outperforms the other traditional models. This implies that during a system design task, designers are very likely to reply on both short-term and long-term memory of past design decisions in guiding their decision making in future design process. Our approach is general to be applied in many other design contexts as long as the sequential design action data is available.