• Transactions of the Korean Society of Pressure Vessels and Piping
• /
• v.19 no.2
• /
• pp.93-101
• /
• 2023

In this study, a deep learning algorithm was used to diagnose electric potential signals obtained through CIPS and DCVG, used indirect inspection methods to confirm the soundness of buried pipes. The deep learning algorithm consisted of CNN(Convolutional Neural Network) model for diagnosing the electric potential signal and Grad CAM(Gradient-weighted Class Activation Mapping) for showing the flaw prediction point. The CNN model for diagnosing electric potential signals classifies input data as normal/abnormal according to the presence or absence of flaw in the buried pipe, and for abnormal data, Grad CAM generates a heat map that visualizes the flaw prediction part of the buried pipe. The CIPS/DCVG signal and piping layout obtained from the 3D finite element model were used as input data for learning the CNN. The trained CNN classified the normal/abnormal data with 93% accuracy, and the Grad-CAM predicted flaws point with an average error of 2m. As a result, it confirmed that the electric potential signal of buried pipe can be diagnosed using a CNN-based deep learning algorithm.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.11 no.3
• /
• pp.159-166
• /
• 2007

This paper evaluates the soundness of structural elements using Wavelet Packet Transform (WPT). WPT is applied to the response acceleration of a framed structure which is subjected to earthquake load to decompose the response acceleration, then the energy of each component is calculated. The first five largest components in energy magnitude among the decomposed components are selected as input to an ANN to identify the damage location and severity. Two nodes in output layer yield damaged element and damage severity respectively. This method successfully evaluates the amount of damage and its location in the structure.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.12 no.6
• /
• pp.140-146
• /
• 2008

The damage evaluation method for framed structures using continuous wavelet transform (CWT) is proposed. CWT is applied to the response acceleration of a structure subjected to earthquake load to decompose the response acceleration corresponding to each scale, then the normalized energy value for each scale is calculated. The difference between the normalized energy curvature (NEC) in each node before and after damage indicates a damaged element, which makes it possible to assess the soundness of structural elements. As damage becomes more severe the difference in normalized energy curvature becomes larger. The NEC calculated from the signal corresponding to high scale in CWT analysis is found to be a good index that shows the location and severity of damage.

• Smart Structures and Systems
• /
• v.33 no.5
• /
• pp.333-347
• /
• 2024

There has been an increasing interest in the construction of smart buildings that can actively monitor and react to their surroundings. The capacity of these intelligent structures to precisely predict and respond to deflection is a crucial feature that guarantees both their structural soundness and efficiency. Conventional techniques for determining deflection often depend on intricate mathematical models and computational simulations, which may be time- and resource-consuming. Artificial intelligence (AI) algorithms have become a potent tool for anticipating and controlling deflection in intelligent structures in response to these difficulties. The term "deflection-aware smart structures" in this sense refers to constructions that have AI algorithms installed that continually monitor and analyses deflection data in order to proactively detect any problems and take appropriate action. These structures anticipate deflection across a range of operating circumstances and environmental factors by using cutting-edge AI approaches including deep learning, reinforcement learning, and neural networks. AI systems are able to predict real-time deflection with high accuracy by using data from embedded sensors and actuators. This capability enables the systems to identify intricate patterns and linkages. Intelligent buildings have the potential to self-correct in order to reduce deflection and maximize performance. In conclusion, the development of deflection-aware smart structures is a major stride forward for structural engineering and has enormous potential to enhance the performance, safety, and dependability of designed systems in a variety of industries.

• Proceedings of the Korean Society for Technology of Plasticity Conference
• /
• 2008.10a
• /
• pp.197-198
• /
• 2008

The forging process produces complicated and designed components in a die at high productivity for mass production and minimizes the machining amount for favorable material utilization; the forging products used at highly stressed sections are well accepted at a wide range of industry such as automobile, aerospace, electric appliance and et cetera. Accordingly, recent R&D activities have been emphasized on improvement of forging die-life and near net shaping technology for cost effectiveness and better performance. Usually closing and consolidation of internal void defects in a ingot is a vital matter when utilized as large forged products. It is important to develop cogging process for improvement of internal soundness without a void defect and cost reduction by solid forging alone with limited press capacity. For experiments of cogging process, hydraulic press with a capacity of 800 ton was used together with a small manipulator which was made for rotation and overlapping of a billet. Size of a void was categorized into two types; ${\phi}$ 6.0 mm and ${\phi}$ 9.0 mm to investigate the change of closing and consolidation of void defects existed in the large ingot during the cogging process. In addition for forming experiment of piston grown air drop hammer with a capacity of 16 ton was used. The experiment with piston crown was carried out to show the formability and void closing status. In this paper systematic configuration for closing process of void defects were expressed based on this experiment results in the cogging process. Also forging defects through forming process for piston crown was improved using the experiment results and FE analysis. Consequently this paper deals with the effect of radial parameters in cogging process on a void closure far large forged products and formability of piston crown.

• Journal of KIISE:Databases
• /
• v.31 no.5
• /
• pp.445-456
• /
• 2004

The database schema is assumed to be stable enough to remain valid even as the modeled environment changes. However, in practice. data models are not nearly as stable as commonly assumed by the database designers. Even though a rich set of schema change operations is provided in current database systems, the users suffer from the problem that schema change usually impacts existing application programs that have been written against the schema. In this paper, we are exploring the possible solutions to overcome this problem of impacts on the application programs. We believe that for continued support of the existing programs on the old schema, the old schema should continue to allow updates and queries, as before. Furthermore, its associated data has to be kept up-to-date. We call this the program independency property of schema change tools. For this property. we devise so-called program independency schema evolution (PISE) methodology. For each of the set of schema change operations in the relational schemas, the sketch of the additional algorithms due to the PISE compliance is presented in order to prove the comprehensiveness and soundness of our PISE methodology.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.39 no.1
• /
• pp.117-123
• /
• 2015

To remove heat generated during a burn-up test of nuclear fuels, the heat generation rate of nuclear fuels should be calculated accurately, and a coolant should be circulated in the test loop at an adequate flow rate. HANARO is an open pool-type reactor with an independent test loop for the burn-up test of nuclear fuels. A test rig is installed in the test loop, and a coolant is circulated through the test loop to maintain the temperature of the nuclear fuel rods within a desired temperature during an irradiation test. The components and sensors in the test rig can be broken or malfunction owing to the flow-induced vibration. In this study, a coolant flow simulation system was developed to verify and confirm the soundness of components and sensors assembled in the test rig with a high flow rate of the coolant.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.57 no.3
• /
• pp.41-54
• /
• 2015

시간-면적 기법을 이용해 유역의 수문과정을 묘사하는 분산형 (distributed) 연속 (continuous) 강우유출모형인 HYSTAR의 거동특성과 주요 매개변수에 대한 민감도를 분석하였다. 유역의 수문조건에 따른 모형거동의 변화를 분석하기 위해 연속되는 4개의 개별 강우사상에 대한 민감도를 조사하고 비교하였다. 또한, 매개변수의 상호작용이 민감도 분석결과에 미치는 영향을 파악하기 위해 두 가지 서로 다른 기법 (one-factor-at-a-time 과 all-factor-at-a-time 방법)을 이용하여 산정된 민감도를 비교하였다. 분석결과, 모형의 직접유출량, 첨두유량 및 도달시간 모의결과는 유출곡선번호 (curve number)에 가장 민감하게 반응하는 것으로 나타났으며, 토양의 깊이, van Genuchten 식의 매개변수, 작물계수에 큰 영향을 받았다. 한편, 모의된 기저유출량은 토양의 깊이를 비롯하여 van Genuchten 식의 매개변수, 작물계수 (crop coefficient), 이방성계수 (anisotropic coefficient), 유출곡선번호의 변화에 민감하였다. 매개변수에 대한 민감도는 분석에 이용된 강우사상에 따라 다르게 나타났으며, 유역의 토양수분조건에 따라 다르게 거동하는 모형의 중요한 특성을 잘 반영하였다. 두 가지 서로 다른 기법을 이용한 민감도 분석결과는 모의된 직접유출량 및 기저유출량의 변화가 매개변수의 상호작용에 의해 제한될 수 있음을 보여 주었다. 본 연구는 HYSTAR 모형의 매개변수에 대한 민감도 분석을 통해서 해당 모형의 거동을 정량적으로 보여주었고, 이를 통해 모형의 건전성 (soundness)을 입증할 수 있는 하나의 근거를 제시하였다. 본 연구결과는 향후 HYSTAR 모형을 이용한 수문분석 시 보정을 위한 매개변수 선정에 활용될 수 있을 것으로 사료된다. 또한, 본 연구결과에서 나타난 민감도의 수문조건 (또는 선정된 강우사상)에 대한 의존성은 연속유출 모형의 민감도 분석을 위한 강우 사상 선정 및 민감도 분석결과의 해석에 유용한 정보를 제공할 수 있을 것으로 기대된다.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.32 no.3B
• /
• pp.185-192
• /
• 2012

Drought vulnerability index was developed by selecting drought-related indicators with trend test. Study areas were determined by considering the weir locations from the four major rivers restoration project in Nakdong and Geum river watersheds. Ten indicators were selected and they were categorized into three groups, water resources, precipitation pattern, and social aspects. Annual average surface water level, annual minimum surface water level, annual average groundwater level, and annual minimum groundwater level data sets were collected for water resources aspects. The number of non-rainy days, rainfall concentration ratio, and rainfall deviation were considered for precipitation pattern category. The amount of water available per capita, financial soundness for water resources, and water usage equity were related to social aspects. Mann-Kendall, Hotelling-Pabst, and Sen trend tests were performed for the ten indicator data sets and the results were scored for the drought vulnerability index. The results shows Gumi, Sangjoo, and Hapcheon weirs are relatively vulnerable to drought. The indices were relatively low for the regions in Geum river watershed compared to those in Nakdong river watershed.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.22 no.5
• /
• pp.879-885
• /
• 2013

Satellites provide a lot of information and essay roles in the areas of defense and space observations. The precise distances to the satellites are measured by emitting and retro-reflecting a laser. For such surveys, satellite laser ranging (SLR) systems have been developed in different forms and for different areas. The structural integrity of the tracking mount is essential for it to be able to track a high-speed satellite precisely, overcoming the various external and internal disturbances and operating conditions. In this study, the analysis of a tracking mount was performed for weight, wind loads, and inertia loads in order to verify its soundness. The results of the comparison between aluminum and steel were analyzed in order to select the optimal material for the fork and main housing part. In addition, the natural frequency and mode shape were predicted. Optimal material selection and structural integrity will also be verified using static analysis.