A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Deep Convolutional Neural Network with Differential Feature Maps for Construction Safety Risks Assessment of Bridge Engineering
The bridge engineering is the essential element for transportation system and construction safety risks are significant to bridge the safety of engineering construction. Hence, assessing and finding the potential risks associated with road projects are significant for attaining the project success. Though, these risks are difficult and dynamic and classical risk assessment techniques can't correctly assess the risks. So, is it essential for assessing the construction safety risks while constructing the bridge engineering. In this research, the Deep Convolutional Neural Network (DCNN) with Differential Feature Maps (DFM) method is proposed for assessing the construction safety risk in bridge engineering. The DFM process is included in the traditional DCNN method, that effectively assess the construction safety risk in bridge engineering. The system model and the assessing by DCNN with DFM method is analyzed. The performance of DCNN with DFM method is analyzed with risks indicators from C1 to C12 and it is varied from 71.200 to 73.200 while compared to conventional methods.
Deep Convolutional Neural Network with Differential Feature Maps for Construction Safety Risks Assessment of Bridge Engineering
The bridge engineering is the essential element for transportation system and construction safety risks are significant to bridge the safety of engineering construction. Hence, assessing and finding the potential risks associated with road projects are significant for attaining the project success. Though, these risks are difficult and dynamic and classical risk assessment techniques can't correctly assess the risks. So, is it essential for assessing the construction safety risks while constructing the bridge engineering. In this research, the Deep Convolutional Neural Network (DCNN) with Differential Feature Maps (DFM) method is proposed for assessing the construction safety risk in bridge engineering. The DFM process is included in the traditional DCNN method, that effectively assess the construction safety risk in bridge engineering. The system model and the assessing by DCNN with DFM method is analyzed. The performance of DCNN with DFM method is analyzed with risks indicators from C1 to C12 and it is varied from 71.200 to 73.200 while compared to conventional methods.
Deep Convolutional Neural Network with Differential Feature Maps for Construction Safety Risks Assessment of Bridge Engineering
Wang, Yunan (author)
2024-07-26
220511 byte
Conference paper
Electronic Resource
English
Vehicle load identification based on bridge response using deep convolutional neural network
| DOAJ | 2024
A deep convolutional neural network based on U-Net to predict annual luminance maps
| Taylor & Francis Verlag | 2022