| Title |
A Framework Development for Sketched Data-Driven Building Information Model Creation to Support Efficient Space Configuration and Building Performance Analysis |
| Authors |
Kong, ByungChan ; Jeong, WoonSeong |
| DOI |
https://dx.doi.org/10.6106/KJCEM.2024.25.1.050 |
| Keywords |
BIM; Deep Learning; Sketched Data Retrieval; Building Performance Analysis; Cost Estimation |
| Abstract |
The market for compact houses is growing due to the demand for floor plans prioritizing user needs. However, clients often have difficulty communicating their spatial requirements to professionals including architects because they lack the means to provide evidence, such as spatial configurations or cost estimates. This research aims to create a framework that can translate sketched data-driven spatial requirements into 3D building components in BIM models to facilitate spatial understanding and provide building performance analysis to aid in budgeting in the early design phase. The research process includes developing a process model, implementing, and validating the framework. The process model describes the data flow within the framework and identifies the required functionality. Implementation involves creating systems and user interfaces to integrate various systems. The validation verifies that the framework can automatically convert sketched space requirements into walls, floors, and roofs in a BIM model. The framework can also automatically calculate material and energy costs based on the BIM model. The developed frame enables clients to efficiently create 3D building components based on the sketched data and facilitates users to understand the space and analyze the building performance through the created BIM models. |