Abstract
In the engineering design process, design fixation significantly constrains the diversity of design solutions. Numerous studies have aimed to mitigate design fixation, yet determining its occurrence in real-time remains a challenge. This research seeks to systematically identify the emergence of fixation through the behavior of novice designers in the early stages of the design process. We conducted a laboratory study, involving 50 novice designers possessing engineering drafting skills. Their design processes were monitored via video cameras, with both their design solutions and physical behaviors recorded. Subsequently, expert evaluators categorized design solutions into three types: Fixation, Low-quality, and Innovative. We manually recorded the names and durations of 31 different physical behaviors observed in the videos, which were then coded and filtered. Meanwhile, we propose a filtering and calculation method for the behavior in the design process. From this, four fixation behaviors were identified using variance analysis (ANOVA): Touch Mouth (TM), Touch Head (TH), Rest Head in Hands (RH), and Hold Face in Hands (HF). Our findings suggest that continuous interaction between the hand and head, mouth, or face can be indicative of a fixation state. Finally, we developed a Behavior-Fixation model based on the Support Vector Machine (SVM) for stage fixation judgment tasks, achieving an accuracy rate of 85.6%. This machine-learning model outperforms manual assessment in speed and accuracy. Overall, our study offers promising prospects for assisting designers in recognizing and avoiding design fixation. These findings, coupled with our proposed computational techniques, provide valuable insights for the development of automated and intelligent design innovation systems.