Hydrogen is considered as one of the most promising future energy carriers due to its noteworthy advantages of renewable, environmentally friendly and high calorific value. However, the low density of hydrogen makes its storage an urgent technical problem for hydrogen energy development. Compared with the density of gas hydrogen, the density of liquid hydrogen is more than 1.5 times higher. Liquid hydrogen is thus more advantageous for large-scale storage and transportation. However, due to the large difference between the liquid hydrogen temperature and the environment temperature, an inevitable heat leak into the storage tanks of liquid hydrogen occurs, causing boil-off losses and vent of hydrogen gas. Researches on insulation materials for liquid hydrogen are actively being conducted, but research on support design for minimal heat transfer and enhanced rigidity remains insufficient. In this study, to design support for liquid hydrogen storage tank, technique of thermal-structural coupled analysis including geometry, mesh, and boundary condition were developed using Ansys workbench, and equivalent stress and deformation distributions were analyzed.

Damage to gas and fire protection piping systems can lead to secondary disasters after an earthquake, so their seismic design is crucial. Accordingly, various types of seismic restraint installations are being devised, and a new suspended piping trapeze restraint installation has also recently been developed in Korea. In this study, a cyclic loading test was performed on the developed trapeze support system, and its performance was evaluated according to ASHRAE 171, the standard for seismic and wind restraint design established by the American Society of Refrigeration and Air Conditioning Engineers (ASHRAE). The three support system specimens did not break or fracture, causing only insignificant deformations until the end of the experiment. Based on the experimentally rated strength and displacement performance, this trapeze support system is expected to control the seismic movement of piping during an earthquake.

Most of the predictions using machine learning are neutral predictions considering the symmetrical situation where the predicted value is not smaller or larger than the actual value. However, in some situations, asymmetric prediction such as over-prediction or under-prediction may be better than neutral prediction, and it can induce better judgment by providing various predictions to decision makers. A method called Asymmetric Twin Support Vector Regression (ATSVR) using TSVR(Twin Support Vector Regression), which has a fast calculation time, was proposed by controlling the asymmetry of the upper and lower widths of the ε-tube and the asymmetry of the penalty with two parameters. In addition, by applying the existing GSVQR and the proposed ATSVR, prediction using the prediction propensities of over-prediction, under-prediction, and neutral prediction was performed. When two parameters were used for both GSVQR and ATSVR, it was possible to predict according to the prediction propensity, and ATSVR was found to be more than twice as fast in terms of calculation time. On the other hand, in terms of accuracy, there was no significant difference between ATSVR and GSVQR, but it was found that GSVQR reflected the prediction propensity better than ATSVR when checking the figures. The accuracy of under-prediction or over-prediction was lower than that of neutral prediction. It seems that using both parameters rather than using one of the two parameters (p_1,p_2) increases the change in the prediction tendency. However, depending on the situation, it may be better to use only one of the two parameters.

The development of IOT technology and artificial intelligence technology is promoting the smartization of manufacturing system. In this study, data extracted from acceleration sensor and current sensor were obtained through experiments in the cutting process of SKD11, which is widely used as a material for special mold steel, and the amount of tool wear and product surface roughness were measured. SVR (Support Vector Regression) is applied to predict the roughness of the product surface in real time using the obtained data. SVR, a machine learning technique, is widely used for linear and non-linear prediction using the concept of kernel. In particular, by applying GSVQR (Generalized Support Vector Quantile Regression), overestimation, underestimation, and neutral estimation of product surface roughness are performed and compared. Furthermore, surface roughness is predicted using the linear kernel and the RBF kernel. In terms of accuracy, the results of the RBF kernel are better than those of the linear kernel. Since it is difficult to predict the amount of tool wear in real time, the product surface roughness is predicted with acceleration and current data excluding the amount of tool wear. In terms of accuracy, the results of excluding the amount of tool wear were not significantly different from those including the amount of tool wear.

Support vector regression (SVR) is devised to solve the regression problem by utilizing the excellent predictive power of Support Vector Machine. In particular, the є-insensitive loss function, which is a loss function often used in SVR, is a function thatdoes not generate penalties if the difference between the actual value and the estimated regression curve is within є. In most studies, the є-insensitive loss function is used symmetrically, and it is of interest to determine the value of є. In SVQR (Support Vector Quantile Regression), the asymmetry of the width of є and the slope of the penalty was controlled using the parameter p. However, the slope of the penalty is fixed according to the p value that determines the asymmetry of є. In this study, a new ε-insensitive loss function with p1 and p2 parameters was proposed. A new asymmetric SVR called GSVQR (Generalized Support Vector Quantile Regression) based on the new ε-insensitive loss function can control the asymmetry of the width of є and the slope of the penalty using the parameters p1 and p2 , respectively. Moreover, the figures show that the asymmetry of the width of є and the slope of the penalty is controlled. Finally, through an experiment on a function, the accuracy of the existing symmetric Soft Margin, asymmetric SVQR, and asymmetric GSVQR was examined, and the characteristics of each were shown through figures.

In this study, the structural analysis was carried out according to the structure of lumber support. For the optimal design of the automotive lumber support, It was examined which one was most stable among three models A, B, and C. As the result of structural analysis, all three models showed the greatest deformations at the wire portion of the lumber support, and model A showed less equivalent stress and deformation compared with models B and C. As model A showed the lowest equivalent stress and deformation among all models, model A was shown to be the model with the excellent strength. This analysis established the stable design by comparing models A, B and C. Also, It is thought that this study result can be highly utilized at the seat design of real automobile.

This research is about a study on the flow stress of Inconel 601 under hot deformation. For Inconel 601, hot compression tests on gleeble 3500 system under 925℃, 1050℃ and 1150℃ and 0.001/s, and 5/s of strain rates were done. The flow behavior of the Inconel 601 was studied and modeled. In this study, the flow stress was modeled using deep neural network and support vector regression algorithm. The flow stress of Inconel 601 was dependent on strain rate and temperature. It was found that both the deep neural network and support vector regression adequately described the flow stress variation of Inconel 601. However, the model by the support vector regression was found to be superior to the model by the deep neural network. The construction of the model by SVR was more efficient than the construction by DNN. Also the prediction accuracy of the model by SVR was better than the accuracy of the model by DNN. It is found that the MAPE(Mean absolute percentage error) of the DNN based model was 4.89% while the MAPE of the SVR based model was 1.98%.

대공간 구조형식을 갖는 단층 래티스 돔은 역학성, 가능성, 심미성 등을 갖는 구조물로서 그 용도가 점점 확대되고 있다. 단층 래티스 돔의 골조 격자 패턴은 무수히 존재하며, 그 대표적인 패턴에는 삼각형, 사각형, 육각형, 라멜라형, 리브형 등이 있다. 대공간 구조물의 경우, 일반구조물과 달리 재래적인 공법으로 지붕 골조를 시공할 경우 많은 가설재가 소요됨으로 시공비 증가가 예상된다. 따라서 대공간 구조물의 지붕 골조 설치는 특수 Erection 공법에 의하는 것이 일반적이며, 그 중 지상에서 지붕골조를 설치 후 jack-up 서포트에 의해 골조를 인양하는 Step-Up 공법을 적용할 경우 공기와 공비의 대폭적인 절감이 예상된다. 따라서 본 논문의 목적은 Step-Up 공법에 의해 단층라멜라 돔의 지붕골조를 시공할 경우, 인양 중 가설 서포트 개수와 위치에 따른 좌굴특성을 검토하는 것이다. 연구 결과 서포트 개수 및 위치에 따른 단층라멜라 돔의 다양한 좌굴 특성에 관한 실무자를 위한 기초적인 자료를 얻을 수 있었다.

항로 설정은 통항 선박들의 안전을 위해 교통 흐름을 반영할 필요가 있으며, 선박들이 항로를 잘 준수하는지 지속적인 경과 분석 이 필요하다. 본 연구에서는 완도항 인근해역 추천항로의 문제점을 도출하고 이에 대한 개선안을 제시하였다. 효율적인 항로 중앙선을 설정하 기 위해 선박 항적을 기반으로 서포트 벡터 머신을 이용하였다. 추천항로 중앙선을 기준으로 우측으로 항해해야 하므로 통항 선박들의 항적 이 2개의 군집으로 분할된다. 서포트 벡터 머신은 패턴 인식 등 많은 분야에서 이용되고 있으며, 특히 이진 분류 기능이 뛰어나다. 연구 결과 장죽수도 방향의 2.4 NM 추천항로 구간에서 동진하는 상선은 약 79.5%가 추천항로를 준수하지 않는 것으로 나타나 선박 충돌 사고 위험이 상존하는 것을 확인하였다. 추천항로를 현 위치에서 북쪽으로 약 300 m 재설정할 경우, 동진하는 상선은 항로를 역주행할 비율이 79.5%에서 30.9%로 낮아지는 것으로 나타났다. 본 연구에서 적용한 서포트 벡터 머신은 선박 항적을 두 군집으로 분류가 가능하므로 항로 중앙선을 효 과적으로 설정하는데 응용할 수 있을 것으로 기대된다.

These days System supports are generally used at the construction sites. But the Structural capacity and Stability of the System Supports are not reviewed properly. The structural capacity of System Support should be evaluated by considering unbraced buckling length.