Predicting capacity model and seismic fragility estimation for RC bridge based on artificial neural network

Huang, Caigui; Huang, Surong

doi:10.1016/j.istruc.2020.07.063

Cited by 20 publications

(7 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the fifth step, the statistical analysis was performed by the convolution of fragility curve distribution to determine reliable damage index bounds. The advantage of the performance assessment using fragility curve distribution has been recommended in several studies 21,22,60–64 . Using damage data obtained from EIDA, damage fragility can be defined through a cumulative distribution function (CDF) theory, which relates the ground motion intensity to the probability of damage in a specific limit state.…”

Section: Modeling and Methodologymentioning

confidence: 99%

“…The advantage of the performance assessment using fragility curve distribution has been recommended in several studies. 21,22,[60][61][62][63][64] Using damage data obtained from EIDA, damage fragility can be defined through a cumulative distribution function (CDF) theory, which relates the ground motion intensity to the probability of damage in a specific limit state. The lognormal damage fragility curve is determined by using two parameters, including median damage value (DI) and the standard deviation of the natural logarithm.…”

Section: Fragility Curve Distributionmentioning

confidence: 99%

See 1 more Smart Citation

Improvement of energy damage index bounds for circular reinforced concrete bridge piers under dynamic analysis

Amirchoupani

Abdollahzadeh

Hamidi

2021

Structural Concrete

View full text Add to dashboard Cite

An improvement of energy damage index bounds for circular reinforced concrete (RC) bridge piers under dynamic time history analysis is presented in this study. The energy-based damage model has been defined as a ratio of hysteresis dissipation energy to input energy for performance evaluation of circular RC bridge pier systems. Based on the energy balance equation, the mentioned damage model can consider all energy aspects, including kinematic energy, strain energy, hysteresis energy, damping energy, and input energy. Additionally, the effect of ground motion duration, amplitude, and frequency content is appropriately considered in this damage model. For this purpose, the damage limit state bounds for two empirical RC bridge piers are statistically evaluated under the 22 far-field ground motion sets of FEMA-P695 for simulation of strong-earthquake motion and consideration of record-to-record variability.First of all, appropriate validation between empirical and numerical fiber element models is implemented to estimate accurate results. Then, damage data at each performance level through strain limit states are collected by developing energy incremental dynamic analysis curves. Statistical results on collected damage data are presented in all performance levels to determine damage index bounds by the convolution of fragility curve distribution. Hence, five damage index bounds at five performance-level are suggested, including very slight, slight, moderate, extensive, and complete damage. Finally, the effect of the other damping ratios on the modified energy damage model is carried out by using the beta coefficient in the formula. In the end, the modified energy damage model is compared with other damage indices to investigate the efficiency of the proposed damage model.

show abstract

Section: Modeling and Methodologymentioning

confidence: 99%

Section: Fragility Curve Distributionmentioning

confidence: 99%

Improvement of energy damage index bounds for circular reinforced concrete bridge piers under dynamic analysis

Amirchoupani

Abdollahzadeh

Hamidi

2021

Structural Concrete

View full text Add to dashboard Cite

show abstract

“…ML methods such as the artificial neural network (ANN), Bayesian network modeling, and support vector machine (SVM) models have been widely used in the research and practice of structural engineering to improve the effectiveness of processing capability and prediction results [16]. Since the mid-1990s, ANN has been gradually applied to structural health monitoring, damage identification, and structural response prediction [17][18][19][20]. Lam et al proposed a pattern recognition method for structural health monitoring based on ANN [21].…”

Section: Structural Response Predictionmentioning

confidence: 99%

Digital Twins-Based Impact Response Prediction of Prestressed Steel Structure

Liu

Che

Sun

et al. 2022

Sensors

View full text Add to dashboard Cite

Civil infrastructure O&M requires intelligent monitoring techniques and control methods to ensure safety. Unfortunately, tedious modeling efforts and the rigorous computing requirements of large-scale civil infrastructure have hindered the development of structural research. This study proposes a method for impact response prediction of prestressed steel structures driven by digital twins (DTs) and machine learning (ML). The high-fidelity DTs of a prestressed steel structure were constructed from the perspective of both a physical entity and virtual entity. A prediction of the impact response of prestressed steel structure’s key parts was established based on ML, and a structure response prediction of the parts driven by data was realized. To validate the effectiveness of the proposed prediction method, the authors carried out a case study in an experiment of a prestressed steel structure. This study provides a reference for fusion applications with DTs and ML in impact response prediction and analysis of prestressed steel structures.

show abstract

“…However, researchers are interested to incorporate AI techniques in structural engineering due to their low computational cost and time saving. Huang and Huang have conducted a study on seismic fragility analysis of RC bridges using ANN [ 31 ]. Liu and Zhang have employed the ANN-based methodology for developing the fragility curves of steel frames [ 29 ].…”

Section: Ann and Gep Modelsmentioning

confidence: 99%

“…The most widely used activation functions are log-sigmoid and tan-sigmoid functions, which can be either linear or nonlinear. The nonlinear function enhances the nonlinear behaviour of the available data, so sigmoid, nonlinear function is adopted in this study as shown in the following equation [ 31 ]:

…”

Section: Ann and Gep Modelsmentioning

confidence: 99%

Machine Learning-Based Fragility Assessment of Reinforced Concrete Buildings

Rasheed¹,

Usman

Zain

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

In the past, large earthquakes caused the collapse of infrastructure and killed thousands of people in Pakistan, a seismically active region. Therefore, the seismic assessment of infrastructure is a dire need that can be done using the fragility analysis. This study focuses on the fragility analysis of school buildings in Muzaffarabad district, seismic zone-4 of Pakistan. Fragility curves were developed using incremental dynamic analysis (IDA); however, the numerical analysis is computationally time-consuming and expensive. Therefore, soft computing techniques such as Artificial Neural Network (ANN) and Gene Expression Programming (GEP) were employed as alternative methods to establish the fragility curves for the prediction of seismic performance. The optimized ANN model [5-25-1] was used. The feedforward backpropagation network was considered in this study. To achieve a reliable model, 70% of the data was selected for training and 15% for validation and 15% of data was used for testing the model. Similarly, the GEP model was also employed to predict the fragility curves. The results of both ANN and GEP were compared based on the coefficient of determination, R2. The ANN model accurately predicts the global drift values with R2 equal to 0.938 compared to the GEP model having R2 equal to 0.87.

show abstract

Predicting capacity model and seismic fragility estimation for RC bridge based on artificial neural network

Cited by 20 publications

References 32 publications

Improvement of energy damage index bounds for circular reinforced concrete bridge piers under dynamic analysis

Improvement of energy damage index bounds for circular reinforced concrete bridge piers under dynamic analysis

Digital Twins-Based Impact Response Prediction of Prestressed Steel Structure

Machine Learning-Based Fragility Assessment of Reinforced Concrete Buildings

Contact Info

Product

Resources

About