A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Fragility assessment of tunnels in soft soils using artificial neural networks
Recent earthquakes have shown that tunnels are prone to damage, posing a major threat to safety and having major cascading and socioeconomic impacts. Therefore, reliable models are needed for the seismic fragility assessment of underground structures and the quantitative evaluation of expected losses. Based on previous researches, this paper presented a probabilistic framework based on an artificial neural network (ANN), aiming at the development of fragility curves for circular tunnels in soft soils. Initially, a two-dimensional incremental dynamic analysis of the nonlinear soil-tunnel system was performed to estimate the response of the tunnel under ground shaking. The effects of soil-structure-interaction and the ground motion characteristics on the seismic response and the fragility of tunnels were adequately considered within the proposed framework. An ANN was employed to develop a probabilistic seismic demand model, and its results were compared with the traditional linear regression models. Fragility curves were generated for various damage states, accounting for the associated uncertainties. The results indicate that the proposed ANN-based probabilistic framework can results in reliable fragility models, having similar capabilities as the traditional approaches, and a lower computational cost is required. The proposed fragility models can be adopted for the risk analysis of typical circular tunnel in soft soils subjected to seismic loading, and they are expected to facilitate decision-making and risk management toward more resilient transport infrastructure.
Fragility assessment of tunnels in soft soils using artificial neural networks
Recent earthquakes have shown that tunnels are prone to damage, posing a major threat to safety and having major cascading and socioeconomic impacts. Therefore, reliable models are needed for the seismic fragility assessment of underground structures and the quantitative evaluation of expected losses. Based on previous researches, this paper presented a probabilistic framework based on an artificial neural network (ANN), aiming at the development of fragility curves for circular tunnels in soft soils. Initially, a two-dimensional incremental dynamic analysis of the nonlinear soil-tunnel system was performed to estimate the response of the tunnel under ground shaking. The effects of soil-structure-interaction and the ground motion characteristics on the seismic response and the fragility of tunnels were adequately considered within the proposed framework. An ANN was employed to develop a probabilistic seismic demand model, and its results were compared with the traditional linear regression models. Fragility curves were generated for various damage states, accounting for the associated uncertainties. The results indicate that the proposed ANN-based probabilistic framework can results in reliable fragility models, having similar capabilities as the traditional approaches, and a lower computational cost is required. The proposed fragility models can be adopted for the risk analysis of typical circular tunnel in soft soils subjected to seismic loading, and they are expected to facilitate decision-making and risk management toward more resilient transport infrastructure.
Fragility assessment of tunnels in soft soils using artificial neural networks
Zhongkai Huang (author) / Sotirios A. Argyroudis (author) / Kyriazis Pitilakis (author) / Dongmei Zhang (author) / Grigorios Tsinidis (author)
2022
Article (Journal)
Electronic Resource
Unknown
Metadata by DOAJ is licensed under CC BY-SA 1.0
Fragility functions of blockwork wharves using artificial neural networks
| British Library Online Contents | 2013
Fragility functions of blockwork wharves using artificial neural networks
| Online Contents | 2013
Fragility assessment of shallow buried tunnels under explosive hazards
| Elsevier | 2024