• Geomechanics and Engineering
• /
• v.28 no.1
• /
• pp.11-23
• /
• 2022

The response of pile foundations under lateral loads are usually analyzed using beam-on-nonlinear-Winkler-foundation (BNWF) model framework employing various forms of empirically derived p-y curves and p-multipliers. In practice, the p-y curve presented by the American Petroleum Institute (API) is most often utilized for piles in granular soils, although its shortcomings are recognized. The objective of this study is to evaluate the performance of the BNWF model and to quantify the error in the estimated pile response compared to a rigorous numerical model. BNWF analyses are performed using three sets of p-y curves to evaluate reliability of the procedure. The BNWF model outputs are compared with results of 3D nonlinear finite element (FE) analysis, which are validated via field load test measurements. The BNWF model using API p-y curve produces higher load-displacement curve and peak bending moment compared with the results of the FE model, because empirical p-y curve overestimates the stiffness and underestimates ultimate resistance up to a depth equivalent to four times the pile diameter. The BNWF model overestimates the peak bending moment by approximately 20-30% using both the API and Reese curves. The p-multipliers are revealed to be sensitive on the p-y curve used as input. These results highlight a need to develop updated p-y curves and p-multipliers for improved prediction of the pile response under lateral loading.

• Computers and Concrete
• /
• v.32 no.2
• /
• pp.217-232
• /
• 2023

Numerous studies have been performed on the behavior of pile foundations in cold regions. This study first attempted to employ artificial neural networks (ANN) to predict pile-bearing capacity focusing on pile data recorded primarily on cold regions. As the ANN technique has disadvantages such as finding global minima or slower convergence rates, this study in the second phase deals with the development of an ANN-based predictive model improved with an Elephant herding optimizer (EHO), Dragonfly Algorithm (DA), Genetic Algorithm (GA), and Evolution Strategy (ES) methods for predicting the piles' bearing capacity. The network inputs included the pile geometrical features, pile area (m²), pile length (m), internal friction angle along the pile body and pile tip (Ø°), and effective vertical stress. The MLP model pile's output was the ultimate bearing capacity. A sensitivity analysis was performed to determine the optimum parameters to select the best predictive model. A trial-and-error technique was also used to find the optimum network architecture and the number of hidden nodes. According to the results, there is a good consistency between the pile-bearing DA-MLP-predicted capacities and the measured bearing capacities. Based on the R2 and determination coefficient as 0.90364 and 0.8643 for testing and training datasets, respectively, it is suggested that the DA-MLP model can be effectively implemented with higher reliability, efficiency, and practicability to predict the bearing capacity of piles.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.4A
• /
• pp.639-645
• /
• 2006

FRP (Fiber Reinforced Polymer) is an excellent new constructional material in resistibility to corrosion, high intensity, resistibility to fatigue, and plasticity. FBG (Fiber Bragg Grating) sensor is widely used at present as a smart sensor due to lots of advantages such as electric resistance, small-sized material, and high durability. However, with insufficiency of measuring displacement, FBG sensor is used only as a sensor measuring physical properties like strain or temperature. In this study, FRP and FBG sensors are to be hybridized, which could lead to the development of a smart FRP rod. Moreover, developing the estimated model for deflection with neural network method, with the data measured through FBG sensor, could make conquest of a disadvantage of FBG sensor - uniquely used for sensing strain. Artificial neural network is MLP (Multi-layer perceptron), trained within error rate of 0.001. Nonlinear object function and back-propagation algorithm is applied to training and this model is verified with the measured axial displacement through UTM and the estimated numerical values.

• Steel and Composite Structures
• /
• v.49 no.3
• /
• pp.337-348
• /
• 2023

Successive wetting and drying cycles of concrete due to weather changes can endanger the safety of engineering structures over time. Considering wetting and drying cycles in concrete tests can lead to a more correct and reliable design of engineering structures. This study aims to provide a model that can be used to estimate the resistance properties of concrete under different wetting and drying cycles. Complex sample preparation methods, the necessity for highly accurate and sensitive instruments, early sample failure, and brittle samples all contribute to the difficulty of measuring the strength of concrete in the laboratory. To address these problems, in this study, the potential ability of six machine learning techniques, including ANN, SVM, RF, KNN, XGBoost, and NB, to predict the concrete's tensile strength was investigated by applying 240 datasets obtained using the Brazilian test (80% for training and 20% for test). In conducting the test, the effect of additives such as glass and polypropylene, as well as the effect of wetting and drying cycles on the tensile strength of concrete, was investigated. Finally, the statistical analysis results revealed that the XGBoost model was the most robust one with R2 = 0.9155, mean absolute error (MAE) = 0.1080 Mpa, and variance accounted for (VAF) = 91.54% to predict the concrete tensile strength. This work's significance is that it allows civil engineers to accurately estimate the tensile strength of different types of concrete. In this way, the high time and cost required for the laboratory tests can be eliminated.

• Geomechanics and Engineering
• /
• v.37 no.5
• /
• pp.475-498
• /
• 2024

The prediction of the susceptibility of soil to liquefaction using a limited set of parameters, particularly when dealing with highly unbalanced databases is a challenging problem. The current study focuses on different ensemble learning classification algorithms using highly unbalanced databases of results from in-situ tests; standard penetration test (SPT), shear wave velocity (V_s) test, and cone penetration test (CPT). The input parameters for these datasets consist of earthquake intensity parameters, strong ground motion parameters, and in-situ soil testing parameters. liquefaction index serving as the binary output parameter. After a rigorous comparison with existing literature, extreme gradient boosting (XGBoost), bagging, and random forest (RF) emerge as the most efficient models for liquefaction instance classification across different datasets. Notably, for SPT and V_s-based models, XGBoost exhibits superior performance, followed by Light gradient boosting machine (LightGBM) and Bagging, while for CPT-based models, Bagging ranks highest, followed by Gradient boosting and random forest, with CPT-based models demonstrating lower G_mean(error), rendering them preferable for soil liquefaction susceptibility prediction. Key parameters influencing model performance include internal friction angle of soil (ϕ) and percentage of fines less than 75 µ (F₇₅) for SPT and V_s data and normalized average cone tip resistance (q_c) and peak horizontal ground acceleration (a_max) for CPT data. It was also observed that the addition of V_s measurement to SPT data increased the efficiency of the prediction in comparison to only SPT data. Furthermore, to enhance usability, a graphical user interface (GUI) for seamless classification operations based on provided input parameters was proposed.

• Computers and Concrete
• /
• v.34 no.2
• /
• pp.151-168
• /
• 2024

This research aimed to appraise the effectiveness of four optimization approaches - cuckoo optimization algorithm (COA), multi-verse optimization (MVO), particle swarm optimization (PSO), and teaching-learning-based optimization (TLBO) - that were enhanced with an artificial neural network (ANN) in predicting the bearing capacity of shallow foundations located on cohesionless soils. The study utilized a database of 97 laboratory experiments, with 68 experiments for training data sets and 29 for testing data sets. The ANN algorithms were optimized by adjusting various variables, such as population size and number of neurons in each hidden layer, through trial-and-error techniques. Input parameters used for analysis included width, depth, geometry, unit weight, and angle of shearing resistance. After performing sensitivity analysis, it was determined that the optimized architecture for the ANN structure was 5×5×1. The study found that all four models demonstrated exceptional prediction performance: COA-MLP, MVO-MLP, PSO-MLP, and TLBO-MLP. It is worth noting that the MVO-MLP model exhibited superior accuracy in generating network outputs for predicting measured values compared to the other models. The training data sets showed R² and RMSE values of (0.07184 and 0.9819), (0.04536 and 0.9928), (0.09194 and 0.9702), and (0.04714 and 0.9923) for COA-MLP, MVO-MLP, PSO-MLP, and TLBO-MLP methods respectively. Similarly, the testing data sets produced R² and RMSE values of (0.08126 and 0.07218), (0.07218 and 0.9814), (0.10827 and 0.95764), and (0.09886 and 0.96481) for COA-MLP, MVO-MLP, PSO-MLP, and TLBO-MLP methods respectively.

• Korean Journal of Soil Science and Fertilizer
• /
• v.39 no.3
• /
• pp.123-135
• /
• 2006

Spatial variability and distribution map of soil properties and the relationships between soil properties and crop yields are not well characterized in agroecosystems that have been land leveled to facilitate more cultivation of the new reclaimed sloping highland. Potato, onion, carrot, Chinese cabbage and radish were grown on the coarse sandy loam soil in 2004. Soil moisture content, soil penetration resistance and crop yield were sampled in the $10m{\times}50m$ field consisted of five plots. Sampling sites of each cultivation plot were 33 for the soil moisture, 11 for the soil penetration and 33 for the crop yield. The results of semivariance analysis, most of models were shown spherical equation. The significant ranges of each spatial variability model for the soil moisture, soil penetration and crop yield were broad as 33-35 meters in the potato cultivation plot, and that in the Chinese cabbage cultivation plot was narrow as 5-6 meters. The coefficient of variances (C.V.) of moisture, penetration and yield were various from 14 to 59 percents in five cultivation plots. The highest C.V. of potato yield was 59 percents, and that of the radish cultivation plot was as low as 14 percents. The required sample numbers for the determination of soil moisture content, soil penetration resistance and crop yield with error 10% at 0.05 significant level were ranged 8-40 for soil moisture, 7-25 for soil penetration and 424-4,678 for crop yield. The variogram and distribution map by kriging described field characteristics well so that the spatial variability would be useful for soil management for better efficiency and precision agriculture in the reclaimed highland.

• Tuberculosis and Respiratory Diseases
• /
• v.43 no.2
• /
• pp.201-209
• /
• 1996

Background : Auto-PEEP which develops when expiratory lung emptying is not finished until the beginning of next inspiration is frequently found in patients on mechanical ventilation. Its presence imposes increased risk of barotrauma and hypotension, as well as increased work of breathing (WOB) by adding inspiratory threshold load and/or adversely affecting to inspiratory trigger sensitivity. The aim of this study is to evaluate the relationship of auto-PEEP with WOB and to evaluate the effect of PEEP applied by ventilator (external PEEP) on WOB in patients with auto-PEEP. Method : 15 patients, who required mechanical ventilation for management of acute respiratory failure, were studied. First, the differences in WOB and other indices of respiratory mechanics were examined between 7 patients with auto-PEEP and 8 patients without auto-PEEP. Then, we applied the 3 cm $H_2O$ of external PEEP to patients with auto-PEEP and evaluated its effects on lung mechanics as well as WOB. Indices of respiratory mechanics including tidal volume ($V_T$), repiratory rate, minute ventilation ($V_E$), peak inspiratory flow rate (PIFR), peak expiratory flow rate (PEFR), peak inspiratory pressure (PIP), $T_I/T_{TOT}$, auto-PEEP, dynamic compliance of lung (Cdyn), expiratory airway resistance (RAWe), mean airway resistance (RAWm), $p_{0.1}$, work of breathing performed by patient (WOB), and pressure-time product (PTP) were obtained by CP-100 Pulmonary Monitor (Bicore, USA). The values were expressed as mean $\pm$ SEM (standard error of mean). Results : 1) Comparison of WOB and other indices of respiratory mechanics in patients with and without auto-PEEP : There was significant increase in WOB ($l.71{\pm}0.24$ vs $0.50{\pm}0.19\;J/L$, p=0.007), PTP ($317{\pm}70$ vs $98{\pm}36\;cm$ $H_2O{\cdot}sec/min$, p=0.023), RAWe ($35.6{\pm}5.7$ vs $18.2{\pm}2.3\;cm$ H2O/L/sec, p=0.023), RAWm ($28.8{\pm}2.5$ vs $11.9{\pm}2.0cm$ H2O/L/sec, p=0.001) and $P_{0.1}$ ($6.2{\pm}1.0$ vs 2.9+0.6 cm H2O, p=0.021) in patients with auto-PEEP compared to patients without auto-PEEP. The differences of other indices including $V_T$, PEFR, $V_E$ and $T_I/T_{TOT}$ showed no significance. 2) Effect of 3 cm $H_2O$ external PEEP on respiratory mechanics in patients with auto-PEEP : When 3 cm $H_2O$ of external PEEP was applied, there were significant decrease in WOB ($1.71{\pm}0.24$ vs $1.20{\pm}0.21\;J/L$, p=0.021) and PTP ($317{\pm}70$ vs $231{\pm}55\;cm$ $H_2O{\cdot}sec/min$, p=0.038). RAWm showed a tendency to decrease ($28.8{\pm}2.5$ vs $23.9{\pm}2.1\;cm$ $H_2O$, p=0.051). But PIP was increased with application of 3 cm $H_2O$ of external PEEP ($16{\pm}2$ vs $22{\pm}3\;cm$ $H_2O$, p=0.008). $V_T$, $V_E$, PEFR, $T_I/T_{TOT}$ and Cdyn did not change significantly. Conclusion : The presence of auto-PEEP in mechanically ventilated patients was accompanied with increased WOB performed by patient, and this WOB was decreased by 3 cm $H_2O$ of externally applied PEEP. But, with 3 cm $H_2O$ of external PEEP, increased PIP was noted, implying the importance of close monitoring of the airway pressure during application of external PEEP.

• Korean Journal of Agricultural Science
• /
• v.41 no.4
• /
• pp.473-480
• /
• 2014

Upon setting up a dedicated plastic greenhouse for tomato cultivation developed by the Rural Development Administration on the Gyehwa reclaimed land, this study was aimed at analyzing the problems can be occurred in the installation of plastic greenhouse on reclaimed lands as well as finding out solutions for improvement. A relatively cheaper wooden pile was used in the installation in order to supplement the soft ground conditions. Based on the results of ground investigation of the installation site, both the allowable bearing capacity and pulling resistance of the wooden pile with a diameter of 150 mm and a length of 10 m were computed and came out to be 30.645 kN. It was determined that the values were enough to withstand the maximum compressive force (17.206 kN) and the pullout force (20.435 kN) that are generally applied to the greenhouse footing. There are three problems aroused in the process of greenhouse installation, and the corresponding countermeasures are as follow. First, due to the slightly bent shape of the wooden pile, there were phenomenon such as deviation, torsion, and fracture when driving the pile. This could be prevented by the use of the backhoe (0.2) rotating tongs, which are holding the pile, to drive the pile while pushing to the direction of the driving and fixing it until 5 m below ground and applying a soft vibrating pressure until the first 2 m. Second, there exists a concrete independent footing between the column of the greenhouse and the wooden pile driven to the underground water level. Since it is difficult to accurately drive the pile on this independent footing, the problem of footing baseplate used to fix the column being off the independent footing was occurred. In order to handle with this matter, the diameter of the independent footing was changed from 200 mm to 300 mm. Last, after films were covered in the condition that the reinforcing frame and bracing are not installed, there was a phenomenon of columns being pushed away by the strong wind to the maximum of $11m{\cdot}s^{-1}$. It is encouraged to avoid constructions in winter, and the film covering jobs always to be done after the frame construction is completely over. The height of the independent footing was measured for 9 months after the completion of the greenhouse installation, and it was found to be within the margin of error meaning that there was no subsidence. The extent to the framework distortion and the value of inclinometers as well showed not much alteration. In other words, the wooden pile was designed to have a sufficient bearing capacity.

• Journal of the Korean Institute of Telematics and Electronics D
• /
• v.36D no.9
• /
• pp.37-45
• /
• 1999

For the purpose of reducing the output voltage fluctuation of thin film multijunction thermal converter, EVANOHM alloy-S and chromel-alumel thermocouple were used as a thin film heater material and as a thermoelement of thrmopile, respectively. The temperature coefficient of the resistance of thin film EVANOHM alloy-S heater was about $1.4 {\times} 10^4/^{\circ}C$, which is very small compared to other materials, and thin film chromel-alumel thermocouple showed relatively small difference of the Seebeck coefficients about $38 {\mu}V/K$. The output voltage fluctuation of the thermal converter was about 0.06% for the initial 120 seconds in air and decreased considerably after preheating for 5 minutes or more. The respective AC-DC voltage and current transfer error ranges of the thermal converter were about ${\pm}$1.6 ppm and ${\pm}$0.7 ppm in the frequency range from 10Hz to 10 kHz and increased remarkably below 10 Hz or above 10 kHz.