Knowledge Graph-Assisted Learning: Improving Academic Outcomes and Equity in Engineering Fluid Mechanics

To address the challenges of abstract concepts, complex derivations, and polarized academic performance in Engineering Fluid Mechanics, this study introduces the Engineering Fluid Mechanics Knowledge Graph (EFM-KG), grounded in cognitive load and meaningful learning theories. A quasi-experimental design with non-equivalent control groups compared the final examination scores of an EFM-KG-assisted group (n=51) with a traditional instruction group (n=89). The experimental group’s mean score increased by 15.0% (9.53 points), with a 28.1% reduction in standard deviation and a large effect size (Cohen’s d=0.80). These findings confirm EFM-KG’s effectiveness in enhancing academic performance and promoting educational equity by narrowing achievement gaps. This research provides robust evidence for knowledge graphs in engineering education and insights for optimizing instructional design.