• Geomechanics and Engineering
• /
• v.33 no.2
• /
• pp.183-194
• /
• 2023

This study presents the prediction of the California bearing ratio (CBR) of coarse- and fine-grained soils using artificial intelligence technology. The group method of data handling (GMDH) algorithm, an artificial neural network-based model, was used in the prediction of the CBR values. In the design of the prediction models, various combinations of independent input variables for both coarse- and fine-grained soils have been used. The results obtained from the designed GMDH-type neural networks (GMDH-type NN) were compared with other regression models, such as linear, support vector, and multilayer perception regression methods. The performance of models was evaluated with a regression coefficient (R²), root-mean-square error (RMSE), and mean absolute error (MAE). The results showed that GMDH-type NN algorithm had higher performance than other regression methods in the prediction of CBR value for coarse- and fine-grained soils. The GMDH model had an R² of 0.938, RMSE of 1.87, and MAE of 1.48 for the input variables {G, S, and MDD} in coarse-grained soils. For fine-grained soils, it had an R² of 0.829, RMSE of 3.02, and MAE of 2.40, when using the input variables {LL, PI, MDD, and OMC}. The performance evaluations revealed that the GMDH-type NN models were effective in predicting CBR values of both coarse- and fine-grained soils.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.14 no.12
• /
• pp.1233-1240
• /
• 2004

Condition monitoring and fault diagnosis of machines are gaining importance in the industry because of the need to increase reliability and to decrease possible loss of production due to machine breakdown. By comparing the nitration signals of a machine running in normal and faulty conditions, detection of faults like mass unbalance, shaft misalignment and bearing defects is possible. This paper presents a novel approach for applying the fault diagnosis of rotating machinery. To detect multiple faults in rotating machinery, a feature selection method and support vector machine (SVM) based multi-class classifier are constructed and used in the faults diagnosis. The results in experiments prove that fault types can be diagnosed by the above method.

• Proceedings of the KSR Conference
• /
• 2007.05a
• /
• pp.1875-1881
• /
• 2007

Deformations of bridge deck ends on abutments or on transition between bridge decks can cause extreme deformations on track. Especially, since slab track is fixed onto the bridge deck slab on concrete slab track-installed bridges, deformations of bridge deck ends directly affect the track behavior, and thus these interactions can bring about the premature failure of rail fastenings or other deteriorations to lower the serviceability. In this study, a foreign standard to evaluate forces on track components caused by the track-bridge interactions and the serviceability of bridge deck ends is investigated, and for the real bridges, the serviceability of bridge deck ends according to several parameters of bridge and track is analyzed. It is found that arrangements and spring coefficients of bridge bearings, as well as distance between bridge bearing and last rail support, support spacings, rail support spring coefficient, are very important parameters.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.11 no.3
• /
• pp.51-56
• /
• 2002

In order to achieve high precision machine tools, Performance enhancement of feed drive systems is required. One of the important technical issues is how to decrease thermal expansion of ball screw in proportion to the increase of machining speed. When measuring force of stretch of ball screw, since not only actual expansion and the value of bending have to be considered, it is impossible to define the exact value of expansion. In addition, support bearings of ball screw gain considerable force in axial direction. It also generates thermal expansion on the ball screw, and deteriorates the performances of the hearings. In conclusion, it is impossible to give the pretension enough to absorb all the elongation due to thermal expansion generated during machine is running. If given bed column and saddle are all bent to chance machine accuracy, and the support bearings of ball screw is damaged.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2003.11a
• /
• pp.537-543
• /
• 2003

Condition monitoring and fault diagnosis of machines are gaining importance in the industry because of the need to increase reliability and to decrease possible loss of production due to machine breakdown. By comparing the vibration signals of a machine running in normal and faulty conditions, detection of faults like mass unbalance, shaft misalignment and bearing defects is possible. This paper presents a novel approach for applying the fault diagnosis of rotating machinery. To detect multiple faults in rotating machinery, a feature selection method and support vector machine (SVM) based multi-class classifier are constructed and used in the faults diagnosis. The results in experiments prove that fault types can be diagnosed by the above method.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2014.11a
• /
• pp.203-204
• /
• 2014

Unlike other members, beams have various cross-sections and they have an important role of delivering the load of slabs. A beam form neighbors the columns and slabs, which makes it difficult to be installed. In a conventional way to exclusively use the form after concrete pouring, the form and a support should be both removed. Then, the support should reinstalled to sustain the stripping time of form, resulting in a structural issue. To solve such structural problem, the study proposes SMART beam form that uses filler panels and supports for filler. The floor filler panels and supports for filler are not removed after concrete curing, to conform to the stripping time of supports. Thus, any structural problem such as cracks and reduction of compressive strength owing to the gap of load bearing capacity can be prevented. The study results will be used as cases for studies on productivity analyses.

• Geomechanics and Engineering
• /
• v.23 no.2
• /
• pp.93-102
• /
• 2020

The excavation broken zones (EBZ) of gateways is a significant factor in determining the stability of man-made opening. The EBZ of 55 gateways with variety geological conditions were measured using Ground Penetrating Radar (GPR). The results found that the greatly depth of EBZ, the smallest is 1.5 m and the deepest is 3.5 m. Experimental investigations were carried out in the laboratory and in the coal mine fields for applying the combined arch support theory to large EBZ. The studies found that resin bolts with high tensile strength and good bond force could provide high pretension force with bolt extensible anchorage method in the field. Furthermore, the recently invented torque amplifier could greatly improve the bolt pretension force in poor lithology. The FLAC3D numerical simulation found that the main diffusion sphere of pretension force was only in the free segment zone of the surrounding rock. Further analysis found that the initial load-bearing zone thickness of the combined arch structure in large EBZ could be expressed by the free segment length of bolt. The using of high mechanical property bolts and steel with high pretension force will clearly putting forward the bolt length selection rule based on the combined arch support theory.

• Tribology and Lubricants
• /
• v.39 no.4
• /
• pp.154-166
• /
• 2023

This study establishes a numerical analysis model of the finite element overhung rotor supported by a DTRB and describes the stiffness properties of the DTRB. The vibration characteristics and contact pressure of the RBR system are predicted according to the DTRB support characteristics such as the initial axial compression and roller profile. The stiffness of the DTRB significantly varies depending on the initial axial compression and external load owing to the occurrence of rollers under the no-load condition and increase in the Hertz contact force. The increase in the initial axial compression increases the rigidity of the DTRB, thereby reducing the displacement of the RBR system and simultaneously increasing the natural frequency. However, above a certain initial axial compression, the effect becomes insignificant, and an excessive increase in the initial axial compression increases the contact pressure. The roller crowning radius, which gives a curvature in the longitudinal direction of the roller, decreases the displacement of the RBR system and increases the natural frequency as the value increases. However, an increase in the crowning radius increases the edge stress, causing a negative effect in terms of the contact pressure. These results show that the DTRB support characteristics required for reducing the vibration and contact pressure of the RBR system supported by the DTRB can be designed.

• Proceedings of the KSR Conference
• /
• 2011.05a
• /
• pp.1236-1241
• /
• 2011

Railway bridge is the most problematic thing in the railway is due to noise and vibration. To solve these problems, there have been studies. However, a fundamental alternative to the noise and vibration. It has not so far not shown, and to minimize the problem is focused. As a result, developed a lot of noise reduction measures, but the vibration is not much for reduction. In this study, to support the superstructure of the bridge vibration possible for spherical elastomeric bearing is a technical review. And it applies to the railway bridge, the numerical analysis was carried out.

• Journal of Ocean Engineering and Technology
• /
• v.25 no.2
• /
• pp.47-54
• /
• 2011

A piled raft foundation is one of the systems used to reduce the settlement of structures. However, the general design method for a piled raft foundation system assumes that the piles only support external loads, which exclude the bearing capacity of the raft itself. In this study, an experimental model test was performed to evaluate the raft capacity for the external load on the sand. Additionally, a part of the sandy ground under the raft was replaced with a gravel mat to reinforce the piled raft foundation system and increase the bearing capacity. Then, parametric studies of the reinforced ground were performed to determine the displacement and load-sharing ratio of the piled raft foundation system.