Seismic reliability assessment of structures using artificial neural network

Vazirizade, Sayyed Mohsen; Nozhati, Saeed; Zadeh, Mostafa Allameh

doi:10.1016/j.jobe.2017.04.001

Cited by 53 publications

(17 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[30][31][32] Furthermore, structural reliability analyses have been performed by using machine learning approaches. [33][34][35][36][37][38] Neural-network-enhanced estimation techniques of aftershock collapse vulnerability 39 and postearthquake safety 40,41 have shown auspicious results. A highly relevant topic constitutes the seismological prediction of earthquake events by neural networks.…”

Section: Introductionmentioning

confidence: 99%

Machine‐learning‐enhanced tail end prediction of structural response statistics in earthquake engineering

Thaler

Stoffel

Markert

et al. 2021

Earthq Engng Struct Dyn

View full text Add to dashboard Cite

Evaluating the response statistics of nonlinear structures constitutes a key issue in engineering design. Hereby, the Monte Carlo method has proven useful, although the computational cost turns out to be considerably high. In particular, around the design point of the system near structural failure, a reliable estimation of the statistics is unfeasible for complex high-dimensional systems. Thus, in this paper, we develop a machine-learning-enhanced Monte Carlo simulation strategy for nonlinear behaving engineering structures. A neural network learns the response behavior of the structure subjected to an initial nonstationary ground excitation subset, which is generated based on the spectral properties of a chosen ground acceleration record. Then using the superior computational efficiency of the neural network, it is possible to predict the response statistics of the full sample set, which is considerably larger than the initial training sample set. To K E Y W O R D Searthquake generation, elastoplastic structures, Kanai-Tajimi filter, machine learning, Monte Carlo method, neural networks This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

show abstract

Section: Introductionmentioning

confidence: 99%

Machine‐learning‐enhanced tail end prediction of structural response statistics in earthquake engineering

Thaler

Stoffel

Markert

et al. 2021

Earthq Engng Struct Dyn

View full text Add to dashboard Cite

show abstract

“…Under the dual action of long-term exposure to the natural environment and service loads, the bearing capacity of concrete structures gradually decreases [1]. Therefore, the reliability of the structure will gradually decline, endangering the safe use of the structure [2,3]. With the development of urbanization and the national economy in China, a huge market demand is expected in the field of building maintenance and reinforcement.…”

Section: Introductionmentioning

confidence: 99%

“…The grafting of nano-TiO 2 onto the surface of flax fiber sheets can not only change the chemical composition and To investigate the effect of flax fiber sheets on the shear resistance of RC beams at different directions and compositions, a flax fiber composite material was prepared using two-way linen fiber sheets produced by the China Harbin Flax Textile Co., Ltd. The density of the fiber cloth was 1.5 g/cm 3 , nominal thickness was 0.16 mm, and the spinning process was ring spinning. To compare the effects of different types of flax fiber sheets on the shear reinforcement of RC beams, basalt fiber sheets were also used to reinforce the RC beams in this study.…”

Section: Introductionmentioning

confidence: 99%

Shear Capacity of RC Beams Strengthened with Flax Fiber Sheets Grafted with Nano-TiO2

Wang

Xian

2020

Materials

View full text Add to dashboard Cite

Flax fiber sheets provide the advantages of high specific strength, a short growth cycle, environmental friendliness, wide availability, and low cost. Therefore, in this study, the shear capacities of reinforced concrete (RC) beams strengthened with ordinary flax fiber sheets, flax fiber sheets grafted with nano-TiO 2 , and unidirectional basalt fiber sheets were compared. The bearing characteristics and failure modes of RC beams strengthened with flax fiber sheets were investigated. The results showed that after reinforcement with flax fiber sheets, the bearing capacity and mid-span deflection of the RC beams are considerably improved, and the reinforcing effect of flax fiber sheets grafted with nano-TiO 2 is greater than that of unmodified flax fiber sheets. After reinforcement with flax fiber sheets grafted with nano-TiO 2 , the shear capacity of the RC beams is considerably improved to 653 kN, which is 72.8% higher than that of the unreinforced RC beams. Meanwhile, the mid-range deflection of the beam reached 14.6 mm, which is 75.9% higher than that of the unreinforced RC beams.surface morphology of the flax fiber sheets, but it can also transform the hydrophilic surface into a lipophilic surface, which improves the compatibility of the flax fiber monofilament with epoxy resin [15,16]. After grafting, a nanoparticle layer structure is produced on the surface of the flax fiber. This can create new covalent bonds, such as -Ti-O-Si-and -Si-O-C-. The degree of defects on the surface of the flax fiber sheets is reduced, and a nano-reinforced epoxy resin composite layer is formed between the flax fiber sheets and the epoxy resin, which fully exerts the reinforcing effect of the nano-TiO 2 [15,17].In this study, the shear capacity, bearing characteristics, and failure modes of reinforced concrete (RC) beams and RC beams strengthened with ordinary flax fiber sheets, unidirectional basalt fiber sheets, and flax fiber sheets grafted with nano-TiO 2 were analyzed and compared. An equation for the shear bearing capacity of RC beams strengthened with flax fiber sheets was also proposed. Materials and Methods Materials and ReagentsThe RC beam was cast with commercial concrete. The concrete grade was C30, water-cement ratio was 0.42, and ratio of cement:water:sand:gravel was 360:151:632:1282 by weight. The cement was Swan brand P.O grade 42.5 ordinary Portland cement, produced by the Harbin Cement Factory of the Jilin Yatai Group, China. The maximum particle size of the coarse aggregate was approximately 25 mm. The measured concrete slump was 43 mm [18]. After pouring was completed, the RC beam was continuously watered at room temperature for 7 days, after which it was removed from the mold and rinsed until 28 days. According to the requirements in the standards for the test of mechanical properties of ordinary concrete (GB/T 50081-2011) [18], the compressive strength of the concrete cube (100 mm × 100 mm) was measured to be 38.2 ± 0.3 MPa.The vertical, structural, and erecting steel rebars were HRB400 grade ordinary hot ro...

show abstract

“…To address this problem, artificial neural network (ANN) algorithms based on the neural structure of the brain were introduced to solve problems with unclear formulations, especially for the marine engineering field with strong nonlinearity. 2,22–25 The mooring system dynamic response is a nonlinear process due to the complex environmental loads and nonlinear properties of floating body motions. Over the past few years, ANN models have found widespread application in the study of the response and fatigue analysis of mooring lines.…”

Section: Introductionmentioning

confidence: 99%

Reliability analysis of mooring lines for floating structures using ANN-BN inference

Zhao

Dong

Jiang

2020

Proceedings of the Institution of Mechanical Engineers, Part M:

View full text Add to dashboard Cite

The harsh marine environment is a significant threat to the safety of floating structure systems. To address this, mooring systems have seen widespread application as an important component in the stabilization of floating structures. This article proposes a methodology to assess the reliability of mooring lines under given extreme environmental conditions based on artificial neural network–Bayesian network inference. Different types of artificial neural networks, including radial basis function neural networks and back propagation neural networks, are adopted to predict the extreme response of mooring lines according to a series of measured environmental data. A failure database under extreme sea conditions is then established in accordance with the failure criterion of mooring systems. There is a failure of mooring lines when the maximum tension exceeds the allowable breaking strength. Finally, the reliability analysis of moored floating structures under different load directions is conducted using Bayesian networks. To demonstrate the proposed methodology, the failure probability of a sample semi-submersible platform at a water depth of 1500 m is estimated. This approach utilizes artificial neural networks’ capacity for calculation efficiency and validates artificial neural networks for the response prediction of floating structures. Furthermore, it can also be employed to estimate the failure probability of other complex floating structures.

show abstract

Seismic reliability assessment of structures using artificial neural network

Cited by 53 publications

References 12 publications

Machine‐learning‐enhanced tail end prediction of structural response statistics in earthquake engineering

Machine‐learning‐enhanced tail end prediction of structural response statistics in earthquake engineering

Shear Capacity of RC Beams Strengthened with Flax Fiber Sheets Grafted with Nano-TiO2

Reliability analysis of mooring lines for floating structures using ANN-BN inference

Contact Info

Product

Resources

About