• Proceedings of the Korea Concrete Institute Conference
• /
• 1993.10a
• /
• pp.195-200
• /
• 1993

This paper develops practical and realistic reliability models and methods for the evalusion of system reliability and system reliability-based rating of R.C box-girder bridge superstructures. The precise prediction of reserved carrying capacity of bridge as a system is extremely difficult expecially when the bridges are highly redundant and significantly deteriorated or damaged. This paper proposes a new approach for the evaluation of reserved system carrying capacity of bridges in terms of equivalent system-strength, which may be defined as a bridge system-strength corresponding to the system reliability of the bridge. This can be derived from an inverse process based on the concept of FOSM form of system reliability index. The strength limit state models for R.C box-girder bridges suggested in the paper are based on the basic bending and shear strength. and the system reliability problem of box-girder superstructure is formulated as parallel-series models obtained from the FMA(Failure Mode Approach) based on major failure mechanism or critical failure states of each girder. AFOSM and IST(Importance Sampling Technique) simulation algorithm is used for the reliability analysis of the proposed models.

• Geomechanics and Engineering
• /
• v.19 no.2
• /
• pp.127-139
• /
• 2019

Available methods to determine the ultimate bearing capacity of shallow foundations may not be accurate enough owing to the complicated failure mechanism and diversity of the underlying soils. Accordingly, applying new methods of artificial intelligence can improve the prediction of the ultimate bearing capacity. The M5' model tree and the genetic programming are two robust artificial intelligence methods used for prediction purposes. The model tree is able to categorize the data and present linear models while genetic programming can give nonlinear models. In this study, a combination of these methods, called the M5'-GP approach, is employed to predict the ultimate bearing capacity of the shallow foundations, so that the advantages of both methods are exploited, simultaneously. Factors governing the bearing capacity of the shallow foundations, including width of the foundation (B), embedment depth of the foundation (D), length of the foundation (L), effective unit weight of the soil (${\gamma}$) and internal friction angle of the soil (${\varphi}$) are considered for modeling. To develop the new model, experimental data of large and small-scale tests were collected from the literature. Evaluation of the new model by statistical indices reveals its better performance in contrast to both traditional and recent approaches. Moreover, sensitivity analysis of the proposed model indicates the significance of various predictors. Additionally, it is inferred that the new model compares favorably with different models presented by various researchers based on a comprehensive ranking system.

• Geomechanics and Engineering
• /
• v.37 no.6
• /
• pp.629-641
• /
• 2024

The presence of excavations or cavities beneath the foundations of a building can have a significant impact on their stability and cause extensive damage. Traditional methods for calculating the bearing capacity and subsidence of foundations over cavities can be complex and time-consuming, particularly when dealing with conditions that vary. In such situations, machine learning (ML) and deep learning (DL) techniques provide effective alternatives. This study concentrates on constructing a prediction model based on the performance of ML and DL algorithms that can be applied in real-world settings. The efficacy of eight algorithms, including Regression Analysis, k-Nearest Neighbor, Decision Tree, Random Forest, Multivariate Regression Spline, Artificial Neural Network, and Deep Neural Network, was evaluated. Using a Python-assisted automation technique integrated with the PLAXIS 2D platform, a dataset containing 272 cases with eight input parameters and one target variable was generated. In general, the DL model performed better than the ML models, and all models, except the regression models, attained outstanding results with an R² greater than 0.90. These models can also be used as surrogate models in reliability analysis to evaluate failure risks and probabilities.

• Earthquakes and Structures
• /
• v.18 no.5
• /
• pp.555-565
• /
• 2020

The main objective of seismic codes is to prevent structural collapse and ensure life safety. Collapse probability of a structure is usually assessed by making a series of analytical model assumptions. This paper investigates the effect of finite element modeling (FEM) assumptions on the estimated collapse capacity of a reinforced concrete (RC) frame building and points out the modeling limitations. Widely used element formulations and hysteresis models are considered in the analysis. A full-scale, three-story RC frame building was utilized as the experimental model. Alternative finite element models are established by adopting a range of different modeling strategies. Using each model, the collapse capacity of the structure is evaluated via Incremental Dynamic Analysis (IDA). Results indicate that the analytically estimated collapse capacities are significantly sensitive to the utilized modeling approaches. Furthermore, results also show that models that represent stiffness degradation lead to a better correlation between the actual and analytical responses. Results of this study are expected to be useful for in developing proper models for assessing the collapse probability of RC frame structures.

• Geosystem Engineering
• /
• v.21 no.5
• /
• pp.273-281
• /
• 2018

In this study, the activated red mud was used as a new and appropriate adsorbent for the removal of ferrocyanide and ferricyanide from aqueous solution. Predicting the removal percentage and adsorption capacity of ferro-ferricyanide by activated red mud during the adsorption process is necessary which has been done by modeling and simulation. The artificial neural network (ANN) was used to develop new models for the predictions. A back propagation algorithm model was trained to develop a predictive model. The effective variables including pH, absorbent amount, absorbent type, ionic strength, stirring rate, time, adsorbate type, and adsorbate dosage were considered as inputs of the models. The correlation coefficient value ($R^2$) and root mean square error (RMSE) values of the testing data for the removal percentage and adsorption capacity using ANN models were 0.8560, 12.5667, 0.9329, and 10.8117, respectively. The results showed that the proposed ANN models can be used to predict the removal percentage and adsorption capacity of activated red mud for the removal of ferrocyanide and ferricyanide with reasonable error.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 1995.04a
• /
• pp.73-81
• /
• 1995

In Korea, the pilot construction of the first high-speed railroad on the Seoul-Pusan has already started 2 years ago. In the thesis, an attempt is made to develop reliability-based integrity-assessment models for the computer-aided control and maintenance of high-speed railroad bridges. The strength limit state models for PC railroad bridges encompass the bending and shear strengths as well as the strength interaction equations which simultaneously take into the element and system reliablities of the proposed limit states and reliability models. Then, the actual load carrying capacity and the realistic safety of bridges are evaluated using the system reliability-based equivalent strength, and the results are compared with those of the element reliability-based or conventional methods. Various parametric studies are performed for the proposed reliability-based safety and integrity-assessment models using the actual PC box girder bridges used in the pilot construction. And the sensitivity analyses are performed for the basic random variables included in strength limit state models. It is concluded that proposed models may be practically applied for the rational assessment of safety and integrity of high speed railroad bridges.

• Structural Engineering and Mechanics
• /
• v.9 no.6
• /
• pp.601-613
• /
• 2000

Existing models for the shear strength degradation of reinforced concrete members present varied conceptual approaches to interpreting test data. The relative superiority of one approach over the others is difficult to determine, particularly given the sparseness of ideal test data. Nevertheless, existing models are compared using a suite of test data that were used for the development of one such model, and significant differences emerge. Rather than relying purely on column test data, the body of knowledge concerning degradation of concrete as a material is considered. Confined concrete relations are examined to infer details of the degradation process, and to establish a framework for developing phenomenologically-based models for shear strength degradation in reinforced concrete members. The possibility of linking column shear strength degradation with material degradation phenomena is explored with a simple model. The model is applied to the results of 7 column tests, and it is found that such a link is sustainable. It is expected that models founded on material degradation phenomena will be more reliable and more broadly applicable than the current generation of empirical shear strength degradation models.

• International Journal of Concrete Structures and Materials
• /
• v.1 no.1
• /
• pp.63-73
• /
• 2007

Optimum multi-layered feed-forward neural network (NN) models using a resilient back-propagation algorithm and early stopping technique are built to predict the shear capacity of reinforced concrete deep and slender beams. The input layer neurons represent geometrical and material properties of reinforced concrete beams and the output layer produces the beam shear capacity. Training, validation and testing of the developed neural network have been achieved using 50%, 25%, and 25%, respectively, of a comprehensive database compiled from 631 deep and 549 slender beam specimens. The predictions obtained from the developed neural network models are in much better agreement with test results than those determined from shear provisions of different codes, such as KBCS, ACI 318-05, and EC2. The mean and standard deviation of the ratio between predicted using the neural network models and measured shear capacities are 1.02 and 0.18, respectively, for deep beams, and 1.04 and 0.17, respectively, for slender beams. In addition, the influence of different parameters on the shear capacity of reinforced concrete beams predicted by the developed neural network shows consistent agreement with those experimentally observed.

• Geotechnical Engineering
• /
• v.13 no.4
• /
• pp.13-24
• /
• 1997

A predicting method for ultimate vertical and horizontal bearing capacity by means of PAR(Pile Analysis Routines) was suggested. Based on the static pile load test data, case studies by means of PAR were performed. Ultimate pile capacity predicted by PAR was within 15% error range of that determined by stairs pile load tests. Also, the results of static pile load test, statnamic tests and PDA data performed on pipe piles were compared and, by using PAR, ultimate pile capacity was determined. Distributions of atrial pile load could be predicted and load transfer analysis could be done approximately by those distributions.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.1
• /
• pp.366-381
• /
• 2020

Steganography has been successfully employed in various applications, e.g., copyright control of materials, smart identity cards, video error correction during transmission, etc. Deep learning-based steganography models can hide information adaptively through network learning, and they draw much more attention. However, the capacity, security, and robustness of the existing deep learning-based steganography models are still not fully satisfactory. In this paper, three models for different cases, i.e., a basic model, a secure model, a secure and robust model, have been proposed for different cases. In the basic model, the functions of high-capacity secret information hiding and extraction have been realized through an encoding network and a decoding network respectively. The high-capacity steganography is implemented by hiding a secret image into a carrier image having the same resolution with the help of concat operations, InceptionBlock and convolutional layers. Moreover, the secret image is hidden into the channel B of carrier image only to resolve the problem of color distortion. In the secure model, to enhance the security of the basic model, a steganalysis network has been added into the basic model to form an adversarial network. In the secure and robust model, an attack network has been inserted into the secure model to improve its robustness further. The experimental results have demonstrated that the proposed secure model and the secure and robust model have an overall better performance than some existing high-capacity deep learning-based steganography models. The secure model performs best in invisibility and security. The secure and robust model is the most robust against some attacks.