• Computers and Concrete
• /
• 제28권5호
• /
• pp.479-486
• /
• 2021

Reinforced concrete (RC) slabs are exposed to several static and dynamic effects during their period of service. Accordingly, there are many studies focused on the behavior of RC slabs under these effects in the literature. However, impact loading which can be more effective than other loads is not considered in the design phase of RC slabs. This study aims to investigate the dynamic behavior of two-way RC slabs under sudden impact loading. For this purpose, 3 different simply supported slab specimens are manufactured. These specimens are tested under impact loading by using the drop test setup and necessary measurement devices such as accelerometers, dynamic load cell, LVDT and data-logger. Mass and drop height of the hammer are taken constant during experimental study. It is seen that rigidity of the specimens effect experimental results. While acceleration values increase, displacement values decrease as the sizes of the specimens have bigger values. In the numerical part of the study, artificial neural networks (ANN) analysis is utilized. ANN analysis is used to model different physical dynamic processes depending upon the experimental variables. Maximum acceleration and displacement values are predicted by ANN analysis. Experimental and numerical values are compared and it is found out that proposed ANN model has yielded consistent results in the estimation of experimental values of the test specimens.

• Smart Structures and Systems
• /
• 제21권4호
• /
• pp.521-535
• /
• 2018

The main purpose of this paper is to predict missing absolute out-of-plane displacements and failure limits of infill walls by artificial neural network (ANN) models. For this purpose, two shake table experiments are performed. These experiments are conducted on a 1:1 scale one-bay one-story reinforced concrete frame (RCF) with an infill wall. One of the experimental models is composed of unreinforced brick model (URB) enclosures with an RCF and other is composed of an infill wall with bed joint reinforcement (BJR) enclosures with an RCF. An artificial earthquake load is applied with four acceleration levels to the URB model and with five acceleration levels to the BJR model. After a certain acceleration level, the accelerometers are detached from the wall to prevent damage to them. The removal of these instruments results in missing data. The missing absolute maximum out-of-plane displacements are predicted with ANN models. Failure of the infill wall in the out-of-plane direction is also predicted at the 0.79 g acceleration level. An accuracy of 99% is obtained for the available data. In addition, a benchmark analysis with multiple regression is performed. This study validates that the ANN-based procedure estimates missing experimental data more accurately than multiple regression models.

• 조명전기설비학회논문지
• /
• 제20권10호
• /
• pp.27-34
• /
• 2006

본 논문은 드라이브의 간적벡터제어에서 ANN을 이용하여 유도전동기의 회전자 저항을 온라인 추정하기 위한 새로운 기법을 제시한다. 약전파 알고리즘은 신경회로망의 학습을 위해 사용된다. 신경회로망의 실제 상태값과 유도전동기의 요구값 사이의 오차는 신경회로망 모델의 하중값 조절을 위하여 역전파 하여 실제값이 요구값을 추정하도록 한다. 드라이브의 회전자 저항, 토크, 자속응답 성능등 이러한 추정기의 성능은 고유값으로부터 회전자 저항을 연구하게 된다. 회전자 저항은 유도전동기 드라이브의 벡터제어에서 제시된 ANN을 사용하여 추정한다.

• Journal of information and communication convergence engineering
• /
• 제13권2호
• /
• pp.123-131
• /
• 2015

Training neural networks is a complex task with great importance in the field of supervised learning. In the training process, a set of input-output patterns is repeated to an artificial neural network (ANN). From those patterns weights of all the interconnections between neurons are adjusted until the specified input yields the desired output. In this paper, a new hybrid algorithm is proposed for global optimization of connection weights in an ANN. Dynamic swarms are shown to converge rapidly during the initial stages of a global search, but around the global optimum, the search process becomes very slow. In contrast, the gradient descent method can achieve faster convergence speed around the global optimum, and at the same time, the convergence accuracy can be relatively high. Therefore, the proposed hybrid algorithm combines the dynamic particle swarm optimization (DPSO) algorithm with the backpropagation (BP) algorithm, also referred to as the DPSO-BP algorithm, to train the weights of an ANN. In this paper, we intend to show the superiority (time performance and quality of solution) of the proposed hybrid algorithm (DPSO-BP) over other more standard algorithms in neural network training. The algorithms are compared using two different datasets, and the results are simulated.

• 한국항해항만학회:학술대회논문집
• /
• 한국항해항만학회 2017년도 추계학술대회
• /
• pp.50-53
• /
• 2017

장기 해운불황에 따라 불확실성이 증폭되고 있는 상황에서 경기추세의 이해뿐만 아니라 예측 또한 중요해지고 있는 실정이다. 본 논문에서는 최근 특정 복잡한 문제에 대해서 각광받고 있는 인공신경망을 적용하여 BDI 예측을 연구하였다. 사용된 인공신경망은 순환신경망으로 RNN과 LSTM 그리고 비교의 목적으로 MLP를 통해 2009.04.01.부터 2017.07.31.의 기간을 대상으로 연구를 진행하였다. 또한 전통적 시계열 예측방법론인 ARIMA 분석을 실시해 인공신경망들의 예측성능과 비교하였다. 결과로 순환신경망인 RNN의 성능이 가장 뛰어났으며 LSTM의 특정 시계열(BDI)에의 적용가능성을 확인할 수 있었다.

• 한국품질경영학회:학술대회논문집
• /
• 한국품질경영학회 1998년도 The 12th Asia Quality Management Symposium* Total Quality Management for Restoring Competitiveness
• /
• pp.696-704
• /
• 1998

Artificial neural networks (ANN) have successfully applied into various areas. But, How to effectively established network is the one of the critical problem. This study will focus on this problem and try to extensively study. Firstly, four different learning algorithms ANNs were constructed. The learning algorithms include backpropagation, simulated annealing, genetic algorithm, and tabu search. The experimental results of the above four different learning algorithms were tested by statistical analysis. The training RMS, training time, and testing RMS were used as the comparison criteria.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2005년도 학술발표회(1)
• /
• pp.157-159
• /
• 2005

• 한국농공학회논문집
• /
• 제52권5호
• /
• pp.1-9
• /
• 2010

Evapotranspiration (ET) is one of the basic components of the hydrologic cycle and is essential for estimating irrigation water requirements. In this study, artificial neural network (ANN) models for reference crop evapotranspiration ($ET_0$) estimation were developed on a monthly basis (May~October). The models were trained and tested for Suwon, Korea. Four climate factors, daily maximum temperature ($T_{max}$), daily minimum temperature ($T_{min}$), rainfall (R), and solar radiation (S) were used as the input parameters of the models. The target values of the models were calculated using Food and Agriculture Organization (FAO) Penman-Monteith equation. Future climate data were generated using LARS-WG (Long Ashton Research Station-Weather Generator), stochastic weather generator, based on HadCM3 (Hadley Centre Coupled Model, ver.3) A1B scenario. The evapotranspirations were 549.7 mm/yr in baseline period (1973-2008), 558.1 mm/yr in 2011-2030, 593.0 mm/yr in 2046-2065, and 641.1 mm/yr in 2080-2099. The results showed that the ANN models achieved good performances in estimating future reference crop evapotranspiration.

• Smart Structures and Systems
• /
• 제2권1호
• /
• pp.81-100
• /
• 2006

To calculate the shear capacity of concrete beams reinforced with fibre-reinforced polymer (FRP), current shear design provisions use slightly modified versions of existing semi-empirical shear design equations that were primarily derived from experimental data generated on concrete beams having steel reinforcement. However, FRP materials have different mechanical properties and mode of failure than steel, and extending existing shear design equations for steel reinforced beams to cover concrete beams reinforced with FRP is questionable. This paper investigates the feasibility of using artificial neural networks (ANNs) to estimate the nominal shear capacity, Vn of concrete beams reinforced with FRP bars. Experimental data on 150 FRP-reinforced beams were retrieved from published literature. The resulting database was used to evaluate the validity of several existing shear design methods for FRP reinforced beams, namely the ACI 440-03, CSA S806-02, JSCE-97, and ISIS Canada-01. The database was also used to develop an ANN model to predict the shear capacity of FRP reinforced concrete beams. Results show that current guidelines are either inadequate or very conservative in estimating the shear strength of FRP reinforced concrete beams. Based on ANN predictions, modified equations are proposed for the shear design of FRP reinforced concrete beams and proved to be more accurate than existing equations.

• 한국지반신소재학회논문집
• /
• 제19권1호
• /
• pp.11-23
• /
• 2020

본 본문에서는 도심지 지하굴착 및 터널현장의 예비설계 및 지반침하를 예측이 가능한 인공신경망 개발에 대한 내용을 다루었다. 인공신경망의 개발을 위해 먼저 다양한 도심지 터널 및 지하굴착 현장 계측자료를 수집하여 데이터베이스를 구축하고 이를 인공신경망 학습에 필용한 학습데이터를 구축하는데 활용하였다. 개발된 인공신경망은 학습에 활용되지 않은 검증 데이터 세트를 및 현장계측자료를 활용하여 결정계수(R²), 평균제곱근오차(Root Mean Square Error; RMSE), 절대평균오차(Mean Absolute Error; MAE) 등 통계적 파라메타를 근거로 하여 신뢰도를 검증하였다. 개발된 인공신경망은 도심지 굴착현장의 예비 설계 및 이에 따른 주변침하를 예측하는데 효율적으로 활용될 수 있는 것으로 평가되었다.