Analytical failure probability model for generic gravity dam classes

Hariri-Ardebili, Mohammad Amin

doi:10.1177/1748006x17712663

Cited by 11 publications

(7 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where σ (z) = 1/(1 + exp(−z)) represents the sigmoid function [36] and has two horizontal asymptotes at 0 and 1. Also, θ T x ∈ R is the inner product between the two Training the logistic regression model boils down to solving an optimization problem in the form of Equation (1) using the following loss function (known as the binary cross-entropy loss [37]):…”

Section: A Classificationmentioning

confidence: 99%

Neural Networks and Imbalanced Learning for Data-Driven Scientific Computing With Uncertainties

Pourkamali-Anaraki

Hariri-Ardebili

2021

IEEE Access

Self Cite

View full text Add to dashboard Cite

Uncertainty quantification in complex engineering problems is challenging because of necessitating large numbers of expensive model evaluations. This paper proposes a two-stage framework for developing accurate machine learning-based surrogate models in structural engineering. The studied numerical model considers aleatory and epistemic uncertainties, i.e., ground motion features and material properties. Our framework's first step trains classification algorithms on the collected data from our numerical model with a disproportionate ratio of observations from two categories, i.e., failed and safe simulations. We investigate the performance of imbalanced learning strategies along with artificial neural networks to achieve high classification accuracy. The second step of our framework aims to estimate three quantities of interest using the same network architecture, comparing our approach with regularized linear regression models. Moreover, we present a new approach to reducing the number of numerical simulations for developing machine learning-based surrogate models with limited training data. This approach employs Gaussian processes as a powerful probabilistic technique, providing an inherent uncertainty measure to determine the quality of estimated response values. Extensive numerical experiments demonstrate the superior performance of neural networks with three hidden layers compared to traditional machine learning algorithms for both classification and regression tasks. Also, empirical investigations corroborate that Gaussian processes enable us to predict the values of missing simulations for reducing the computational cost associated with numerical models. To conclude this work, we present several applications and future research directions. INDEX TERMS Uncertainty, Gaussian processes, neural networks, imbalanced classification, regression.

show abstract

Section: A Classificationmentioning

confidence: 99%

Neural Networks and Imbalanced Learning for Data-Driven Scientific Computing With Uncertainties

Pourkamali-Anaraki

Hariri-Ardebili

2021

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…Thus, there is interest in moving towards more refined methods for considering uncertainties. For these reasons, probabilistic assessment has emerged as a useful tool in dam safety, and the results have been found to be promising by recent studies [2,3,[15][16][17][18][19]. However, the use of probabilistic methods for dams within a normative framework is not well developed, but increasing scrutiny is being applied to this field.…”

Section: Related Workmentioning

confidence: 99%

Accounting for Uncertainties in the Safety Assessment of Concrete Gravity Dams: A Probabilistic Approach with Sample Optimization

Segura

Miquel

Paultre

et al. 2021

Water

View full text Add to dashboard Cite

Important advances have been made in the methodologies for assessing the safety of dams, resulting in the review and modification of design guidelines. Many existing dams fail to meet these revised criteria, and structural rehabilitation to achieve the updated standards may be costly and difficult. To this end, probabilistic methods have emerged as a promising alternative and constitute the basis of more adequate procedures of design and assessment. However, such methods, in addition to being computationally expensive, can produce very different solutions, depending on the input parameters, which can greatly influence the final results. Addressing the existing challenges of these procedures to analyze the stability of concrete dams, this study proposes a probabilistic-based methodology for assessing the safety of dams under usual, unusual, and extreme loading conditions. The proposed procedure allows the analysis to be updated while avoiding unnecessary simulation runs by classifying the load cases according to the annual probability of exceedance and by using an efficient progressive sampling strategy. In addition, a variance-based global sensitivity analysis is performed to identify the parameters most affecting the dam stability, and the parameter ranges that meet the safety guidelines are formulated. It is observed that the proposed methodology is more robust, more computationally efficient, and more easily interpretable than conventional methods.

show abstract

“…Thus, there is a need to move towards more refined methods to consider uncertainties inherent in the problem of dam safety assessment under extreme events. For these reasons, probabilistic-based methods have arisen as a useful tool in dam safety, and the results have been promising in recent studies [5][6][7][8][9]. However, the use of probabilistic methods for dams within a normative framework has not been well developed, although increasing research is being conducted.…”

Section: Introductionmentioning

confidence: 99%

Expected seismic performance of gravity dams using machine learning techniques

Segura

Padgett

Paultre

2021

BNZSEE

View full text Add to dashboard Cite

Methods for the seismic analysis of dams have improved extensively in the last several decades. Advanced numerical models have become more feasible and constitute the basis of improved procedures for design and assessment. A probabilistic framework is required to manage the various sources of uncertainty that may impact system performance and fragility analysis is a promising approach for depicting conditional probabilities of limit state exceedance under such uncertainties. However, the effect of model parameter variation on the seismic fragility analysis of structures with complex numerical models, such as dams, is frequently overlooked due to the costly and time-consuming revaluation of the numerical model. To improve the seismic assessment of such structures by jointly reducing the computational burden, this study proposes the implementation of a polynomial response surface metamodel to emulate the response of the system. The latter will be computationally and visually validated and used to predict the continuous relative maximum base sliding of the dam in order to build fragility functions and show the effect of modelling parameter variation. The resulting fragility functions are used to assess the seismic performance of the dam and formulate recommendations with respect to the model parameters. To establish admissible ranges of the model parameters in line with the current guidelines for seismic safety, load cases corresponding to return periods for the dam classification are used to attain target performance limit states.

show abstract

Analytical failure probability model for generic gravity dam classes

Cited by 11 publications

References 23 publications

Neural Networks and Imbalanced Learning for Data-Driven Scientific Computing With Uncertainties

Neural Networks and Imbalanced Learning for Data-Driven Scientific Computing With Uncertainties

Accounting for Uncertainties in the Safety Assessment of Concrete Gravity Dams: A Probabilistic Approach with Sample Optimization

Expected seismic performance of gravity dams using machine learning techniques

Contact Info

Product

Resources

About