Real-Time Egress Model for Multiplex Buildings under Fire Based on Artificial Neural Network
When fire occurs in a large multiplex building, the direction of smoke and flames is often similar to that of the evacuation of building occupants. This causes evacuation bottlenecks in a specific compartment, especially when the occupant density is very high, which unfortunately often leads to many...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-07-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/11/14/6337 |
| _version_ | 1797527697503551488 |
|---|---|
| author | Khaliunaa Darkhanbat Inwook Heo Sun-Jin Han Hae-Chang Cho Kang Su Kim |
| author_facet | Khaliunaa Darkhanbat Inwook Heo Sun-Jin Han Hae-Chang Cho Kang Su Kim |
| author_sort | Khaliunaa Darkhanbat |
| collection | DOAJ |
| description | When fire occurs in a large multiplex building, the direction of smoke and flames is often similar to that of the evacuation of building occupants. This causes evacuation bottlenecks in a specific compartment, especially when the occupant density is very high, which unfortunately often leads to many fatalities and injuries. Thus, the development of an egress model that can ensure the safe evacuation of occupants is required to minimize the number of casualties. In this study, the correlations between fire temperature with visibility and toxic gas concentration were investigated through a fire simulation on a multiplex building, from which databases for training of artificial neural networks (ANN) were created. Based on this, an ANN model that can predict the available safe egress time was developed, and it estimated the available safe egress time (ASET) very accurately. In addition, an egress model that can guide rapid and safe evacuation routes for occupants was proposed, and the rationality of the proposed model was verified in detail through an application example. The proposed model provided the optimal evacuation route with the longest margin of safety in consideration of both ASET and the movement time of occupants under fire. |
| first_indexed | 2024-03-10T09:47:27Z |
| format | Article |
| id | doaj.art-e70ec1ccb07c4c77b722c7ef4504e665 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T09:47:27Z |
| publishDate | 2021-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-e70ec1ccb07c4c77b722c7ef4504e6652023-11-22T03:08:07ZengMDPI AGApplied Sciences2076-34172021-07-011114633710.3390/app11146337Real-Time Egress Model for Multiplex Buildings under Fire Based on Artificial Neural NetworkKhaliunaa Darkhanbat0Inwook Heo1Sun-Jin Han2Hae-Chang Cho3Kang Su Kim4Department of Architectural Engineering and Smart City Interdisciplinary Major Program, University of Seoul, 163 Seoulsiripdae-ro, Dongdaemun-gu, Seoul 02504, KoreaDepartment of Architectural Engineering, University of Seoul, 163 Seoulsiripdae-ro, Dongdaemun-gu, Seoul 02504, KoreaDepartment of Architectural Engineering, University of Seoul, 163 Seoulsiripdae-ro, Dongdaemun-gu, Seoul 02504, KoreaTechnology Center/R&D Manager, Dream Structural Engineers Co Ltd., 25 Seongsuilro 4-gil, Seongdong-gu, Seoul 04871, KoreaDepartment of Architectural Engineering and Smart City Interdisciplinary Major Program, University of Seoul, 163 Seoulsiripdae-ro, Dongdaemun-gu, Seoul 02504, KoreaWhen fire occurs in a large multiplex building, the direction of smoke and flames is often similar to that of the evacuation of building occupants. This causes evacuation bottlenecks in a specific compartment, especially when the occupant density is very high, which unfortunately often leads to many fatalities and injuries. Thus, the development of an egress model that can ensure the safe evacuation of occupants is required to minimize the number of casualties. In this study, the correlations between fire temperature with visibility and toxic gas concentration were investigated through a fire simulation on a multiplex building, from which databases for training of artificial neural networks (ANN) were created. Based on this, an ANN model that can predict the available safe egress time was developed, and it estimated the available safe egress time (ASET) very accurately. In addition, an egress model that can guide rapid and safe evacuation routes for occupants was proposed, and the rationality of the proposed model was verified in detail through an application example. The proposed model provided the optimal evacuation route with the longest margin of safety in consideration of both ASET and the movement time of occupants under fire.https://www.mdpi.com/2076-3417/11/14/6337multiplex buildingfireegress modelartificial neural network (ANN)available safe egress time (ASET) |
| spellingShingle | Khaliunaa Darkhanbat Inwook Heo Sun-Jin Han Hae-Chang Cho Kang Su Kim Real-Time Egress Model for Multiplex Buildings under Fire Based on Artificial Neural Network Applied Sciences multiplex building fire egress model artificial neural network (ANN) available safe egress time (ASET) |
| title | Real-Time Egress Model for Multiplex Buildings under Fire Based on Artificial Neural Network |
| title_full | Real-Time Egress Model for Multiplex Buildings under Fire Based on Artificial Neural Network |
| title_fullStr | Real-Time Egress Model for Multiplex Buildings under Fire Based on Artificial Neural Network |
| title_full_unstemmed | Real-Time Egress Model for Multiplex Buildings under Fire Based on Artificial Neural Network |
| title_short | Real-Time Egress Model for Multiplex Buildings under Fire Based on Artificial Neural Network |
| title_sort | real time egress model for multiplex buildings under fire based on artificial neural network |
| topic | multiplex building fire egress model artificial neural network (ANN) available safe egress time (ASET) |
| url | https://www.mdpi.com/2076-3417/11/14/6337 |
| work_keys_str_mv | AT khaliunaadarkhanbat realtimeegressmodelformultiplexbuildingsunderfirebasedonartificialneuralnetwork AT inwookheo realtimeegressmodelformultiplexbuildingsunderfirebasedonartificialneuralnetwork AT sunjinhan realtimeegressmodelformultiplexbuildingsunderfirebasedonartificialneuralnetwork AT haechangcho realtimeegressmodelformultiplexbuildingsunderfirebasedonartificialneuralnetwork AT kangsukim realtimeegressmodelformultiplexbuildingsunderfirebasedonartificialneuralnetwork |