Data-Driven Prediction Methods for Real-Time Indoor Fire Scenario Inferences
High temperatures, toxic gases, and smoke resulting from indoor fires pose evident threats to the lives of both trapped individuals and firefighters. This study aims to predict indoor fire development effectively, facilitating rapid rescue decisions and minimizing casualties and property damage. A c...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-10-01
|
| Series: | Fire |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2571-6255/6/10/401 |
| _version_ | 1797573900519866368 |
|---|---|
| author | Lu Zhang Like Mo Cheng Fan Haijun Zhou Yangping Zhao |
| author_facet | Lu Zhang Like Mo Cheng Fan Haijun Zhou Yangping Zhao |
| author_sort | Lu Zhang |
| collection | DOAJ |
| description | High temperatures, toxic gases, and smoke resulting from indoor fires pose evident threats to the lives of both trapped individuals and firefighters. This study aims to predict indoor fire development effectively, facilitating rapid rescue decisions and minimizing casualties and property damage. A comprehensive database has been developed using Computational Fluid Dynamics (CFD) tools, primarily focused on basic fire scenarios. A total of 300 indoor fire scenarios have been simulated for different fire locations and severity levels. Using fire databases developed from simulation tools, artificial intelligence models have been developed to make spatial–temporal inferences on indoor temperature, CO concentration, and visibility. Detailed analysis has been conducted to optimize sensor system layouts while investigating the variations in prediction accuracy according to different prediction horizons. The research results show that, in combination with artificial intelligence models, the optimized sensor system can accurately predict temperature distribution, CO concentration, and visibility, achieving R<sup>2</sup> values of 91%, 72%, and 83%, respectively, while reducing initial hardware costs. The research results confirm the potential of artificial intelligence in predicting indoor fire scenarios and providing practical guidelines for smart firefighting. However, it is important to note that this study has certain limitations, including the scope of fire scenarios, data availability, and model generalization and interpretability. |
| first_indexed | 2024-03-10T21:15:36Z |
| format | Article |
| id | doaj.art-51babc3f0f2b45f1819a30c58f2caca1 |
| institution | Directory Open Access Journal |
| issn | 2571-6255 |
| language | English |
| last_indexed | 2024-03-10T21:15:36Z |
| publishDate | 2023-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Fire |
| spelling | doaj.art-51babc3f0f2b45f1819a30c58f2caca12023-11-19T16:27:21ZengMDPI AGFire2571-62552023-10-0161040110.3390/fire6100401Data-Driven Prediction Methods for Real-Time Indoor Fire Scenario InferencesLu Zhang0Like Mo1Cheng Fan2Haijun Zhou3Yangping Zhao4Sino-Australia Joint Research Center in BIM and Smart Construction, Shenzhen University, Shenzhen 518000, ChinaSino-Australia Joint Research Center in BIM and Smart Construction, Shenzhen University, Shenzhen 518000, ChinaSino-Australia Joint Research Center in BIM and Smart Construction, Shenzhen University, Shenzhen 518000, ChinaCollege of Civil and Transportation Engineering, Shenzhen University, Shenzhen 518000, ChinaCollege of Civil and Transportation Engineering, Shenzhen University, Shenzhen 518000, ChinaHigh temperatures, toxic gases, and smoke resulting from indoor fires pose evident threats to the lives of both trapped individuals and firefighters. This study aims to predict indoor fire development effectively, facilitating rapid rescue decisions and minimizing casualties and property damage. A comprehensive database has been developed using Computational Fluid Dynamics (CFD) tools, primarily focused on basic fire scenarios. A total of 300 indoor fire scenarios have been simulated for different fire locations and severity levels. Using fire databases developed from simulation tools, artificial intelligence models have been developed to make spatial–temporal inferences on indoor temperature, CO concentration, and visibility. Detailed analysis has been conducted to optimize sensor system layouts while investigating the variations in prediction accuracy according to different prediction horizons. The research results show that, in combination with artificial intelligence models, the optimized sensor system can accurately predict temperature distribution, CO concentration, and visibility, achieving R<sup>2</sup> values of 91%, 72%, and 83%, respectively, while reducing initial hardware costs. The research results confirm the potential of artificial intelligence in predicting indoor fire scenarios and providing practical guidelines for smart firefighting. However, it is important to note that this study has certain limitations, including the scope of fire scenarios, data availability, and model generalization and interpretability.https://www.mdpi.com/2571-6255/6/10/401indoor fireartificial intelligencefire detection and deductionCFD simulationbuilding safety |
| spellingShingle | Lu Zhang Like Mo Cheng Fan Haijun Zhou Yangping Zhao Data-Driven Prediction Methods for Real-Time Indoor Fire Scenario Inferences Fire indoor fire artificial intelligence fire detection and deduction CFD simulation building safety |
| title | Data-Driven Prediction Methods for Real-Time Indoor Fire Scenario Inferences |
| title_full | Data-Driven Prediction Methods for Real-Time Indoor Fire Scenario Inferences |
| title_fullStr | Data-Driven Prediction Methods for Real-Time Indoor Fire Scenario Inferences |
| title_full_unstemmed | Data-Driven Prediction Methods for Real-Time Indoor Fire Scenario Inferences |
| title_short | Data-Driven Prediction Methods for Real-Time Indoor Fire Scenario Inferences |
| title_sort | data driven prediction methods for real time indoor fire scenario inferences |
| topic | indoor fire artificial intelligence fire detection and deduction CFD simulation building safety |
| url | https://www.mdpi.com/2571-6255/6/10/401 |
| work_keys_str_mv | AT luzhang datadrivenpredictionmethodsforrealtimeindoorfirescenarioinferences AT likemo datadrivenpredictionmethodsforrealtimeindoorfirescenarioinferences AT chengfan datadrivenpredictionmethodsforrealtimeindoorfirescenarioinferences AT haijunzhou datadrivenpredictionmethodsforrealtimeindoorfirescenarioinferences AT yangpingzhao datadrivenpredictionmethodsforrealtimeindoorfirescenarioinferences |