| 학회 |
한국화학공학회 |
| 학술대회 |
2021년 봄 (04/21 ~ 04/23, 부산 BEXCO) |
| 권호 |
27권 1호, p.274 |
| 발표분야 |
공정시스템 |
| 제목 |
미세먼지 측정 데이터 부족한 지하역사내 전이학습기반 PM2.5 예측 모델 및 환기 제어 성능 평가 |
| 초록 |
The reliability of indoor air quality (IAQ) and ventilation systems represents a common problem in subway stations as it poses a potential health risk to passengers and subway workers. The performance of existing forecasting approaches relies on a considerable amount of historical sensor data, which is usually not available in practical situations. This study introduces a transfer learning (TL) framework to address insufficient data problem for sustainable IAQ levels and ventilation management. The TL-framework outperforms the recurrent neural networks with a determination coefficient (R2) improvement of 42.84%. Moreover, the IAQ was maintained at healthy levels, and PM2.5 concentrations were reduced by 29.21% as compared to stand-alone network. Acknowledgments; This work was supported by the Ministry of Education of the Republic of Korea and the National Research Foundation of Korea (NRF-2019S1A5A2A03049104) and by a grant from the Subway Fine Dust Reduction Technology Development Project of the Ministry of Land Infrastructure and Transport (20QPPW-B152306-02). |
| 저자 |
Tariq Shahzeb1, kijeon Nam2, 유창규3
|
| 소속 |
1Kyunghee Univ., 2applied environmental science, 3integrated engineering |
| 키워드 |
인공지능 기반 공정기술 |
| E-Mail |
|
| 원문파일 |
초록 보기 |
