Back to Search
Start Over
Structural damage levels of bridges in vehicular collision fires: Predictions using an artificial neural network (ANN) model.
- Source :
-
Engineering Structures . Nov2023, Vol. 295, pN.PAG-N.PAG. 1p. - Publication Year :
- 2023
-
Abstract
- • Implementation of Artificial Neural Network (ANN) to study the critical factors of bridge fire incidents. • Defining I-girder steel bridges as the most susceptible structural system. • Defining hydrocarbon tankers and trucks with solid combustible cargo as the most hazardous sources. • Potential hazard prevention and protection measures to improve structural and human life safety, bridge durability, and reduce maintenance costs. Fire poses a major risk to the structural integrity of a bridge or progressively to the bridge's failure. This study uses an Artificial Neural Network (ANN) to investigate the determining factors in bridge fire incidents. Implementation of this powerful model produces an estimation of the damage levels. The basis of the proposed model is determined by critical factors, including bridge location, materials, structural systems, annual average daily traffic (AADT), ignition source, combustible type, and bridge face exposed to fire. Results show that steel I-girder bridges are the most susceptible structural system in a fire. Moreover, a fire involving tankers containing hydrocarbon fuel and trucks with solid combustible cargo is the most dangerous to a bridge. The accuracy of the proposed model is verified, and its outcome can be utilized to determine fire risk based on discrete characteristics. Based on the proposed model, a combination of hazard prevention and protection measures may be utilized to improve structural integrity, human life safety, and durability, and to reduce maintenance costs. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 01410296
- Volume :
- 295
- Database :
- Academic Search Index
- Journal :
- Engineering Structures
- Publication Type :
- Academic Journal
- Accession number :
- 172042985
- Full Text :
- https://doi.org/10.1016/j.engstruct.2023.116840