• 한국전산구조공학회:학술대회논문집
• /
• 한국전산구조공학회 2007년도 정기 학술대회 논문집
• /
• pp.43-48
• /
• 2007

In this study, an ANN-based damage detection algorithm using acceleration signals is developed for alarming locations of damage in beam-type structures. A new ANN-algorithm using output-only acceleration responses is designed for damage detection in real time. The cross-covariance of two acceleration signals measured at two different locations is selected as the feature representing the structural condition. Neural networks are trained for potential loading patterns and damage scenarios of the target structure for which its actual loadings are unknown. The feasibility and practicality of the proposed method are evaluated from laboratory-model tests on free-free beams for which accelerations were measured before and after several damage cases.

• Safety and Health at Work
• /
• 제15권2호
• /
• pp.220-227
• /
• 2024

Background: Though the artificial neural network (ANN) technique has been used to predict noise-induced hearing loss (NIHL), the established prediction models have primarily relied on cross-sectional datasets, and hence, they may not comprehensively capture the chronic nature of NIHL as a disease linked to long-term noise exposure among workers. Methods: A comprehensive dataset was utilized, encompassing eight-year longitudinal personal hearing threshold levels (HTLs) as well as information on seven personal variables and two environmental variables to establish NIHL predicting models through the ANN technique. Three subdatasets were extracted from the afirementioned comprehensive dataset to assess the advantages of the present study in NIHL predictions. Results: The dataset was gathered from 170 workers employed in a steel-making industry, with a median cumulative noise exposure and HTL of 88.40 dBA-year and 19.58 dB, respectively. Utilizing the longitudinal dataset demonstrated superior prediction capabilities compared to cross-sectional datasets. Incorporating the more comprehensive dataset led to improved NIHL predictions, particularly when considering variables such as noise pattern and use of personal protective equipment. Despite fluctuations observed in the measured HTLs, the ANN predicting models consistently revealed a discernible trend. Conclusions: A consistent correlation was observed between the measured HTLs and the results obtained from the predicting models. However, it is essential to exercise caution when utilizing the model-predicted NIHLs for individual workers due to inherent personal fluctuations in HTLs. Nonetheless, these ANN models can serve as a valuable reference for the industry in effectively managing its hearing conservation program.

• 한국전산유체공학회지
• /
• 제19권3호
• /
• pp.29-36
• /
• 2014

In the present study, an aerodynamic design optimization of UAV rotor blades was conducted using a genetic algorithm(GA) coupled with computational fluid dynamics(CFD). To reduce computational cost in making databases, a function approximation was applied using artificial neural networks(ANN) based on a radial basis function network. Three dimensional Reynolds-Averaged Navier-Stokes(RANS) solver was used to solve the flow around UAV rotor blades. Design directions were specified to maximize thrust coefficient maintaining torque coefficient and minimize torque coefficient maintaining thrust coefficient. Design variables such as twist angle, thickness and chord length were adopted to perform a planform optimization. As a result of an optimization regarding to maximizing thrust coefficient, thrust coefficient was increased about 4.5% than base configuration. In case of an optimization minimizing torque coefficient, torque coefficient was decreased about 7.4% comparing with base configuration.

• Computers and Concrete
• /
• 제4권6호
• /
• pp.477-497
• /
• 2007

The ultrasonic pulse velocity method has been widely used to evaluate the quality of concrete and assess the structural integrity of concrete structures. But its use for predicting strength is still limited since there are many variables affecting the relationship between strength and pulse velocity of concrete. This study is focused on establishing a complicated correlation between known input data, such as pulse velocity and mixture proportions of concrete, and a certain output (compressive strength of concrete) using artificial neural networks (ANN). In addition, the results predicted by the developed multilayer perceptrons (MLP) networks are compared with those by conventional regression analysis. The result shows that the correlation between pulse velocity and compressive strength of concrete at various ages can be well established by using ANN and the accuracy of the estimates depends on the quality of the information used to train the network. Moreover, compared with the conventional approach, the proposed method gives a better prediction, both in terms of coefficients of determination and root-mean-square error.

• 한국분말재료학회지
• /
• 제26권5호
• /
• pp.369-374
• /
• 2019

The properties of powder metallurgy products are related to their densities. In the present work, we demonstrate a method to apply artificial neural networks (ANNs) trained on experimental data to predict the bulk density of barium titanates. The density is modeled as a function of pressure, press rate, heating rate, sintering temperature, and soaking time using the ANN method. The model predictions with the training and testing data result in a high coefficient of correlation (R2 = 0.95 and Pearson's r = 0.97) and low average error. Moreover, a graphical user interface for the model is developed on the basis of the transformed weights of the optimally trained model. It facilitates the prediction of an infinite combination of process parameters with reasonable accuracy. Sensitivity analysis performed on the ANN model aids the identification of the impact of process parameters on the density of barium titanates.

• Wind and Structures
• /
• 제34권4호
• /
• pp.321-334
• /
• 2022

Irregularity in plan shape is very common for any type of building as it enhances better air ventilation for the inhabitants. Systematic opening at the middle of the facades makes the appearance of the building plan as a butterfly one. The primary focus of this study is to forecast the force, moment and torsional coefficient of a butterfly plan shaped tall building. Initially, Computational Fluid Dynamics (CFD) study is done on the building model based on Reynolds averaged Navier Stokes (RANS) k-epsilon turbulence model. Fifty random cases of irregularity and angle of attack (AOA) are selected, and the results from these cases are utilised for developing the surrogate models. Parametric equations are predicted for all these aerodynamic coefficients, and the training of these outcomes are also done for developing Artificial Neural Networks (ANN). After achieving the target acceptance criteria, the observed results are compared with the primary CFD data. Both parametric equations and ANN matched very well with the obtained data. The results are further utilised for discussing the effects of irregularity on the most critical wind condition.

• Structural Engineering and Mechanics
• /
• 제57권4호
• /
• pp.657-680
• /
• 2016

Reinforced concrete (RC) deep beams are structural members that predominantly fail in shear. Therefore, determining the shear strength of these types of beams is very important. The strut-and-tie method is commonly used to design deep beams, and this method has been adopted in many building codes (ACI318-14, Eurocode 2-2004, CSA A23.3-2004). In this study, the efficiency of artificial neural networks (ANNs) in predicting the shear strength of RC deep beams is investigated as a different approach to the strut-and-tie method. An ANN model was developed using experimental data for 214 normal and high-strength concrete deep beams from an existing literature database. Seven different input parameters affecting the shear strength of the RC deep beams were selected to create the ANN structure. Each parameter was arranged as an input vector and a corresponding output vector that includes the shear strength of the RC deep beam. The ANN model was trained and tested using a multi-layered back-propagation method. The most convenient ANN algorithm was determined as trainGDX. Additionally, the results in the existing literature and the accuracy of the strut-and-tie model in ACI318-14 in predicting the shear strength of the RC deep beams were investigated using the same test data. The study shows that the ANN model provides acceptable predictions of the ultimate shear strength of RC deep beams (maximum $R^2{\approx}0.97$). Additionally, the ANN model is shown to provide more accurate predictions of the shear capacity than all the other computed methods in this study. The ACI318-14-STM method was very conservative, as expected. Moreover, the study shows that the proposed ANN model predicts the shear strengths of RC deep beams better than does the strut-and-tie model approaches.

• 대한안전경영과학회지
• /
• 제10권4호
• /
• pp.309-314
• /
• 2008

Many studies on predicting and recommending information and products have been studying to meet customers' preference. Unnecessary information should be removed to satisfy customers' needs in massive information. The some information filtering methods to remove unnecessary information have been suggested but these methods have scarcity and scalability problems. Therefore, this paper explores a personalized recommendation system based on artificial neural network (ANN) to solve these problems. The insurance product recommendation is adapted as an example to demonstrate the proposed method. The proposed recommendation system is expected to recommended a suitable and personalized insurance products for customers' satisfaction.

• Advances in nano research
• /
• 제15권2호
• /
• pp.165-174
• /
• 2023

The study investigated the effect of geometric structures of nano-patterned surfaces, such as peak sharpness, height, width, aspect ratio, and spacing, on mechano-bactericidal properties. Here, in silico models were developed to explain surface interactions with Escherichia coli. Numerical solutions were performed based on the finite element method and verified by the artificial neural network method. An E. coli cell adhered to the nano surface formed elastic and creep deformation models, and the cells' maximum deformation, maximum stress, and maximum strain were calculated. The results determined that the increase in peak sharpness, aspect ratio, and spacing values increased the maximum deformation, maximum stress, and maximum strain on E. coli cell. In addition, the results showed that FEM and ANN methods were in good agreement with each other. This study proved that the geometrical structures of nano-patterned surfaces have an important role in the mechano-bactericidal effect.

• 정보처리학회논문지:컴퓨터 및 통신 시스템
• /
• 제8권4호
• /
• pp.79-86
• /
• 2019

본 논문에서 인공 신경망을 이용한 시계열 데이터 예측 사례에 대해 서술한다. 본 연구에서는 텐서 플로우 라이브러리를 사용하여 배치 기반의 인공 신경망과 스타케스틱 기반의 인공신경망을 구현하였다. 실험을 통해, 구현된 각 신경망에 대해 훈련 에러와 시험에러를 측정하였다. 신경망 훈련과 시험을 위해서 미국의 인디아나주의 공식 웹사이트로부터 8개월간 수집된 세금 데이터를 사용하였다. 실험 결과, 배치 기반의 신경망 기법이 스타케스틱 기법보다 좋은 성능을 보였다. 또한, 좋은 성능을 보인 배치 기반의 신경망을 이용하여 약 7개월 간 종합 세수 예측을 수행하고 예측된 결과와 실제 데이터를 수집하여 비교 실험을 진행 하였다. 실험 결과, 예측된 종합 세수 금액 결과가 실제값과 거의 유사하게 측정되었다.