• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.23 no.2
• /
• pp.163-170
• /
• 2011

An optimal layout condition of the offshore wind turbines is studied by using the response surface analysis which is a kind of the design of experiments. Based on the assumption that total 36 turbines would be installed in the offshore wind farm, the number and distance of the rows and columns are used as the design variables and the efficiency decrease of power generation due to the wake decay by the interactions of turbines and the installation cost of the internal electric grid are considered as the objective functions of the response surface analysis for the layout design of turbines. Useful design information can be derived by analyzing the relationship between the design variables and target functions. It is found that the row number and the distance between rows should be minimized, and the optimal distance between columns should be estimated and adopted to the layout design within the specified design range in order to ensure the economics for the offshore wind farm.

• The Journal of Korean Institute of Next Generation Computing
• /
• v.14 no.6
• /
• pp.15-29
• /
• 2018

This paper proposes an enhanced object tracking algorithm to compensate the lack of temporal information in existing particle swarm optimization based object trackers using the trajectory of the target object. The proposed scheme also enables the tracking and documentation of the location of an online updated set of distractions. Based on the trajectories information and the distraction set, a rule based approach with adaptive parameters is utilized for occlusion detection and determination of the target position. Compare to existing algorithms, the proposed approach provides more comprehensive use of available information and does not require manual adjustment of threshold values. Moreover, an effective weight adjustment function is proposed to alleviate the diversity loss and pre-mature convergence problem in particle swarm optimization. The proposed weight function ensures particles to search thoroughly in the frame before convergence to an optimum solution. In the existence of multiple objects with similar feature composition, this algorithm is tested to significantly reduce convergence to nearby distractions compared to the other existing swarm intelligence based object trackers.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.26 no.3
• /
• pp.131-139
• /
• 2014

Infra-gravity waves (IGWs) with a period of 1~3 minutes are a factor that directly influences the motion analysis of moored ships inside a harbor and longshore sediment transport analysis. If significant levels of IGWs from far seas are transferred to a harbor and amplified, they may cause downtime of large ships and induce economic loss. In this study, transfer characteristics of the IGWs intruding from outside to inside Pohang New Harbor were analyzed using statistical analysis and transfer function of wave data measured at both outside and inside the harbor for around 5 years. Transfer characteristic analysis was limited to events where IGWs had wave heights above 0.1 m. The wave height distribution of inside the harbor was similar to that of outside the harbor, while the wave period variance of the former was larger than that of the latter. The parameters of the transfer function was optimally estimated according to each event. The estimated average RMS error of the wave height inside the harbor was around 0.013 m. The estimated parameters had a strong correlation with the linear combination information of IGW wave height, period, and direction (R = 0.95). The transfer function suggested in this study can quickly and easily estimate information on IGWs inside the harbor using IGW information predicted beforehand, and is expected to reduce damage due to unexpected restrictions on harbor usage.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.24 no.6
• /
• pp.583-598
• /
• 2022

As human-based tunnel inspections are affected by the subjective judgment of the inspector, making continuous history management difficult. There is a lot of deep learning-based automatic crack detection research recently. However, the large public crack datasets used in most studies differ significantly from those in tunnels. Also, additional work is required to build sophisticated crack labels in current tunnel evaluation. Therefore, we present a method to improve crack detection performance by inputting existing datasets into a deep learning model. We evaluate and compare the performance of deep learning models trained by combining existing tunnel datasets, high-quality tunnel datasets, and public crack datasets. As a result, DeepLabv3+ with Cross-Entropy loss function performed best when trained on both public datasets, patchwise classification, and oversampled tunnel datasets. In the future, we expect to contribute to establishing a plan to efficiently utilize the tunnel image acquisition system's data for deep learning model learning.

• Journal of the Korean GEO-environmental Society
• /
• v.17 no.1
• /
• pp.5-12
• /
• 2016

Investigation of in-situ ground in cold region is difficult due to low accessibility and environmental factors. In this study, correlation between dynamic cone resistance and shear strength is suggested to estimate the strength of frozen soils by using instrumented dynamic cone penetrometer. Tests were conducted in freezing chamber after preparing sand-silt mixture with 2.3% water content. Vertical stresses of 5 kPa and 10 kPa were applied during freezing, shearing, and penetration phase to compare the dynamic cone resistance and shear strength. The dynamic cone resistance, additionally, is calculated to minimize the effect of energy loss during hammer impact. Experimental results show that as the shear strength increases, the dynamic cone penetration index (DCPI) decreases nonlinearly, while the dynamic cone resistance increases linearly. This study provides the useful correlation to evaluate strength properties of the frozen soils from the dynamic cone penetration and direct shear tests.