BROWSE
Detail
Conference Paper
물리 기반 화재 합성 데이터 생성 및 검증 프레임워크
Cited - time in 
Share 
Share
- Issue Date
- 2026-06
- Citation
- 경영정보관련 학회 통합학술대회 (춘계) 2026, pp.1-2
- Publisher
- 한국경영정보학회/한국빅데이터학회/한국인터넷전자상거래학회/한국정보시스템학회/한국지식경영학회
- Language
- Korean
- Type
- Conference Paper
- Abstract
- This study proposes a physics-informed surrogate framework for generating synthetic compartment fire time- series data in sensor-scarce building environments. The generator solves an energy-balance ODE with two-zone modeling, wall conduction, ventilation loss, and radiation loss. We validate 20 representative scenarios against real CFAST and FDS simulations, achieving MAE of 15.8°C against FDS volume-mean. Downstream ML benchmarks confirm data utility (R²=0.918 vs. R²=−346 for naive baselines).
- Keyword
- 물리 기반 데이터 생성, 화재 시뮬레이션, CFAST, FDS, 기계학습
- KSP Keywords
- Compartment fire, Data utility, Energy Balance