• Steel and Composite Structures
• /
• 제48권5호
• /
• pp.531-545
• /
• 2023

Composite dowels are implemented as a powerful alternative to headed studs for the efficient combination of Ultra High-Performance Concrete (UHPC) with high-strength steel in novel composite structures. They are required to provide sufficient shear resistance and ensure the transmission of tensile forces in the composite connection in order to prevent lifting of the concrete slab. In this paper, the load bearing capacity of puzzle-shaped and clothoidal-shaped dowels encased in UHPC specimen were investigated based on validated experimental test data. Considering the influence of the embedment depth and the spacing width of shear dowels, the characteristics of UHPC square plate on the load bearing capacity of composite structure, 240 numeric models have been constructed and analyzed. Three artificial intelligence approaches have been implemented to learn the discipline from collected experimental data and then make prediction, which includes Artificial Neural Network-Particle Swarm Optimization (ANN-PSO), Adaptive Neuro-Fuzzy Inference System (ANFIS) and an Extreme Learning Machine (ELM). Among the factors, the embedment depth of composite dowel is proved to be the most influential parameter on the load bearing capacity. Furthermore, the results of the prediction models reveal that ELM is capable to achieve more accurate prediction.

• 한국지진공학회논문집
• /
• 제10권5호
• /
• pp.63-71
• /
• 2006

건축구조물의 비선형 지진응답해석에서 입력지진동은 구조물의 탄소성 지진응답을 좌우하는 중요한 요소이다. 지진동파형은 지진발생과 전파경로에 따른 여러 가지 인자에 의해 그 특성이 결정되기 때문에 구조물의 지진응답해석에서 일반성을 갖는 입력지진동을 선정하는 것은 매우 어려운 문제이다. 본 논문은 내진설계용 스펙트럼에 대응하는 인공지진동파형을 작성한 후, 작성된 인공지진동에 대한 탄소성 응답스펙트럼 특성을 분석한 것이다. 여기서 작성된 인공지진동파형은 과거의 지진에서 얻어진 기록지진동파형을 이용하여 기록지진동과 동일한 위상각을 가지며, 감쇠정수 h=5%일 때의 내진설계용 스펙트럼과 거의 일치하도록 작성되었다. 작성된 인공지진동은 원 기록지진동과 동일한 위상각을 가지며, 주기 $T=0.02{\sim}10.0sec$ 범위에서 설계용 스펙트럼과 매우 근접하게 작성되었다. 인공지진동을 입력한 1자유도계의 탄성 및 탄소성 지진응답해석을 수행하여 탄소성 응답스펙트럼 및 탄소성 응답특성을 분석하였다. 본 논문에서 작성된 인공지진동은 건축구조물의 탄소성 지진응답해석용 입력지진동으로 충분히 타당성이 있다고 사료된다.

• 정보화정책
• /
• 제29권2호
• /
• pp.3-36
• /
• 2022

지금까지의 인공지능 연구는 컴퓨터 분야의 새로운 알고리즘에 관한 것이 대부분이며, 인공지능의 활용 사례연구도 주로 인간과의 대결에서 승리한 것을 보여 주고 있다. 사회와 기업의 지속적인 관심 속에 학계에서도 단순 기술적 측면의 인공지능 연구에서 벗어나 인공지능의 활용적 측면, 특히 조직·전략과의 연계, 인공지능의 활용 리스크 등의 문제에서 이론을 정립하려는 노력이 최근 시도되고 있다. 본 문헌 연구에서는 2015년부터 2022년 현재까지 인공지능의 활용에 관한 연구를 인공지능 활용 분야, 인공지능 프로젝트 관리 그리고 인공지능의 활용 리스크 측면에서 조사하였다. 또한 세부 분석을 위하여 인용 수 20개 이상의 785개 연구에 대하여 세부 분야로 분류하여 조사하였다. 연구 결과 아직 많은 인공지능의 활용연구는 산업 또는 기업 업무별 과거 데이터를 중심으로 한 프로토타이핑 프로젝트 연구에 치우쳐져 있었다. 향후 인공지능 활용을 위한 조직 구조, 프로젝트 선정과 적용과정 등의 연구가 인공지능 활용의 리스크 연구와 함께 필요할 것으로 보인다.

• Smart Structures and Systems
• /
• 제6권4호
• /
• pp.389-403
• /
• 2010

By using image recognition technology, this paper presents a new fault diagnosis method for rotating machinery with artificial immune algorithm. This method focuses on the vibration state parameter image. The main contribution of this paper is as follows: firstly, 3-D spectrum is created with raw vibrating signals. Secondly, feature information in the state parameter image of rotating machinery is extracted by using Wavelet Packet transformation. Finally, artificial immune algorithm is adopted to diagnose rotating machinery fault. On the modeling of 600MW turbine experimental bench, rotor's normal rate, fault of unbalance, misalignment and bearing pedestal looseness are being examined. It's demonstrated from the diagnosis example of rotating machinery that the proposed method can improve the accuracy rate and diagnosis system robust quality effectively.

• 한국어업기술학회:학술대회논문집
• /
• 한국어업기술학회 2000년도 추계수산관련학회 공동학술대회발표요지집
• /
• pp.243-243
• /
• 2000

There are a large number of researches concerning about artificial reefs in Japan, and many Japanese companies have developed and specialized in the coastal engineering in recent years. Various shape, size and material of artificial reefs are constructed, however, concrete and steel structures are popular material in Japan. Five kinds of artificial reefs were put down on gravel bottoms 5-10 m deep in February 1999, which is located 100 m off Ikata, Shikoku, southern part of Japan. (omitted)

• Wind and Structures
• /
• 제5권1호
• /
• pp.1-14
• /
• 2002

Artificial Neural Networks (ANN) have the capability to develop functional relationships between input-output patterns obtained from any source. Thus ANN can be conveniently used to develop a generalised relationship from limited and sometimes inconsistent data, and can therefore also be applied to tackle the data obtained from wind tunnel tests on building models with large number of variables. In this paper ANN model has been developed for predicting wind induced pressures in various zones of a Gable Building from limited test data. The procedure is also extended to a case wherein interference effects on a gable roof building by a similar building are studied. It is found that the Artificial Neural Network modelling is seen to predict successfully, the pressure coefficients for any roof slope that has not been covered by the experimental study. It is seen that ANN modelling can lead to a reduction of the wind tunnel testing effort for interference studies to almost half.

• 대한기계학회논문집A
• /
• 제26권4호
• /
• pp.701-710
• /
• 2002

The framework, described in this paper, involves artificial evolutionary systems that re -produce aimed solutions through a simulated Darwinian evolution process. Through this process the framework designs structures of machines innovatively and emergently especially in the stages of conceptual and basic design. Since the framework simulates the evolution of nature, it inevitably involves processes that converse the natural evolution to the artificial evolution. For the conversion, based on several methods as the building block modeling, Artificial Life, evolutionary computation and the law of natural selection, we propose a series of processes that consists of modeling, evaluation, selection, evolution etc. We have demonstrated the implementation of the framework with the design of multi-step gear systems.

• Structural Engineering and Mechanics
• /
• 제71권4호
• /
• pp.377-390
• /
• 2019

A method for estimating the floor response spectra (FRS) of elastic structures under earthquake excitations is proposed. The method is established based on a previously proposed direct estimation method for single degree of freedom systems, which generally overestimates the FRS of a structure, particularly in the resonance period range. A modification factor is introduced to modify the original method; the modification factor is expressed as a function of the period ratio and is determined through regression analysis on time history analysis results. Both real and artificial ground motions are considered in the analysis, and it is found that the modification factors obtained from the real and artificial ground motions are significantly different. This suggests that the effect of ground motion should be considered in the estimation of FRS. The modified FRS estimation method is further applied to a 10-story building structure, and it is verified that the proposed method can lead to a good estimation of FRS of multi-story buildings.

• Computers and Concrete
• /
• 제24권3호
• /
• pp.271-282
• /
• 2019

Concrete undergoes a series of thermo-based physio-chemical changes once exposed to elevated temperatures. Such changes adversely alter the composition of concrete and oftentimes lead to fire-induced explosive spalling. Spalling is a multidimensional, complex and most of all sophisticated phenomenon with the potential to cause significant damage to fire-exposed concrete structures. Despite past and recent research efforts, we continue to be short of a systematic methodology that is able of accurately assessing the tendency of concrete to spall under fire conditions. In order to bridge this knowledge gap, this study explores integrating novel artificial intelligence (AI) techniques; namely, artificial neural network (ANN), adaptive neuro-fuzzy inference system (ANFIS) and genetic algorithm (GA), together with traditional statistical analysis (multilinear regression (MLR)), to arrive at state-of-the-art procedures to predict occurrence of fire-induced spalling. Through a comprehensive datadriven examination of actual fire tests, this study demonstrates that AI techniques provide attractive tools capable of predicting fire-induced spalling phenomenon with high precision.

• Fisheries and Aquatic Sciences
• /
• 제13권2호
• /
• pp.167-181
• /
• 2010

To predict changes in the marine environment of the Beolgyo Stream Estuary in Jeonnam Province, South Korea, where cohesive tidal flats cover a broad area and a large bridge is under construction, this study conducted numerical simulations involving tidal flow and cohesive sediment transport. A wetting and drying (WAD) technique for tidal flats from the Princeton Ocean Model (POM) was applied to a large-scale-grid hydrodynamic module capable of evaluating the flow resistance of structures. Derivation of the eddy viscosity coefficient for wakes created by structures was accomplished through the explicit use of shear velocity and Chezy's average velocity. Furthermore, various field observations, including of tide, tidal flow, suspended sediment concentrations, bottom sediments, and water depth, were performed to verify the model and obtain input data for it. In particular, geologic parameters related to the evaluation of settling velocity and critical shear stresses for erosion and deposition were observed, and numerical tests for the representation of suspended sediment concentrations were performed to determine proper values for the empirical coefficients in the sediment transport module. According to the simulation results, the velocity variation was particularly prominent around the piers in the tidal channel. Erosion occurred mainly along the tidal channels near the piers, where bridge structures reduced the flow cross section, creating strong flow. In contrast, in the rear area of the structure, where the flow was relatively weak due to the formation of eddies, deposition and moderated erosion were predicted. In estuaries and coastal waters, changes in the flow environment caused by artificial structures can produce changes in the sedimentary environment, which in turn can affect the local marine ecosystem. The numerical model proposed in this study will enable systematic prediction of changes to flow and sedimentary environments caused by the construction of artificial structures.