• Advances in concrete construction
• /
• 제3권2호
• /
• pp.91-102
• /
• 2015

In this paper, the load-deflection analysis of the Carbon Fiber Reinforced Polymer (CFRP) strengthened Reinforced Concrete (RC) slab using Recurrent Neural Network (RNN) is investigated. Six reinforced concrete slabs having dimension $1800{\times}400{\times}120mm$ with similar steel bar of 2T10 and strengthened using different length and width of CFRP were tested and compared with similar samples without CFRP. The experimental load-deflection results were normalized and then uploaded in MATLAB software. Loading, CFRP length and width were as neurons in input layer and mid-span deflection was as neuron in output layer. The network was generated using feed-forward network and a internal nonlinear condition space model to memorize the input data while training process. From 122 load-deflection data, 111 data utilized for network generation and 11 data for the network testing. The results of model on the testing stage showed that the generated RNN predicted the load-deflection analysis of the slabs in acceptable technique with a correlation of determination of 0.99. The ratio between predicted deflection by RNN and experimental output was in the range of 0.99 to 1.11.

• 한국공간구조학회논문집
• /
• 제18권4호
• /
• pp.69-80
• /
• 2018

In this study, an algorithm applying deep learning to the truss structures was proposed. Deep learning is a method of raising the accuracy of machine learning by creating a neural networks in a computer. Neural networks consist of input layers, hidden layers and output layers. Numerous studies have focused on the introduction of neural networks and performed under limited examples and conditions, but this study focused on two- and three-dimensional truss structures to prove the effectiveness of algorithms. and the training phase was divided into training model based on the dataset size and epochs. At these case, a specific data value was selected and the error rate was shown by comparing the actual data value with the predicted value, and the error rate decreases as the data set and the number of hidden layers increases. In consequence, it showed that it is possible to predict the result quickly and accurately without using a numerical analysis program when applying the deep learning technique to the field of structural analysis.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2018년도 추계학술대회
• /
• pp.11-14
• /
• 2018

The aim of this study is to rectify the misclassified image features and enhance the performance of image classification tasks by incorporating a channel- coding technique, widely used in telecommunication. Specifically, the proposed algorithm employs the error - correcting mechanism of convolutional coding combined with the convolutional neural networks (CNNs) that are the state - of- the- arts image classifier s. We develop an encoder and a decoder to employ the error - correcting capability of the convolutional coding. In the encoder, the label values of the image data are converted to convolutional codes that are used as target outputs of the CNN, and the network is trained to minimize the Euclidean distance between the target output codes and the actual output codes. In order to correct misclassified features, the outputs of the network are decoded through the trellis structure with Viterbi algorithm before determining the final prediction. This paper demonstrates that the proposed architecture advances the performance of the neural networks compared to the traditional one- hot encoding method.

• 한국기계가공학회지
• /
• 제21권6호
• /
• pp.8-14
• /
• 2022

In this study reports experiments were conducted to determine the quality of weld beads of different materials, Al and Cu. Among the lasers used to make battery cells for electric vehicles, non-destructive testing was performed using deep learning to determine the quality of beads welded with the ARM laser. Deep learning was performed using AlexNet algorithm with a convolutional neural network structure. The results of quality identification were divided into good and bad, and the result value was derived that all the results were in agreement with 94% or more. Overall, the best welding quality was obtained in the experiment for the fixed ring beam output/variable center beam output, in the case of the fixed beam (ring beam) 500W and variable beam (center beam) 1,050W; weld bead failure was seldom observed. The tensile force test to confirm the reliability of welding reported an average tensile force of 2.5kgf/mm or more in all sections.

• ETRI Journal
• /
• 제45권4호
• /
• pp.636-649
• /
• 2023

Renewable energy generation cannot be consistently predicted or controlled. Therefore, it is currently not widely used in the electricity market, which requires dependable production. In this study, reliability- and variance-based controls of energy storage strategies are proposed to utilize renewable energy as a steady contributor to the electricity market. For reliability-based control, photovoltaic (PV) generation is assumed to be registered in the power generation plan. PV generation yields a reliable output using energy storage units to compensate for PV prediction errors. We also propose a runtime state-ofcharge management method for sustainable operations. With variance-based controls, changes in rapid power generation are limited through ramp rate control. This study introduces new reliability and variance indices as indicators for evaluating these strategies. The reliability index quantifies the degree to which the actual generation realizes the plan, and the variance index quantifies the degree of power change. The two strategies are verified based on simulations and experiments. The reliability index improved by 3.1 times on average over 21 days at a real power plant.

• 한국환경농학회지
• /
• 제19권3호
• /
• pp.252-258
• /
• 2000

SWMM and WASP5 were applied for pollutant loading estimate from watershed and reservoir water quality simulation, respectively, to predict estuarine reservoir water quality. Application of natural systems to improve estuarine reservoir water quality was reviewed, and its effect was predicted by WASP5. Study area was the Hwa-Ong reservoir in Hwasung-Gun, Kyonggi-Do. Procedures for estimation of pollutant loading from watershed and simulation of corresponding reservoir water quality were reviewed. In this study, SWMM was proved to be an appropriate watershed model to the nonurban area, and it could evaluate land use effects and many hydrological characteristics of catchment. WASP5 is a well known lake water quality model and its application to the estuarine reservoir was proved to be suitable. These models are both dynamic and the output of SWMM can be linked to the WASP5 with little effort, therefore, use of these models for reservoir water quality prediction in connection was appropriate. Further efforts to develop more logical and practical measures to predict reservoir water quality are necessary for proper management of estuarine reservoirs.

• 한국우주과학회:학술대회논문집(한국우주과학회보)
• /
• 한국우주과학회 2011년도 한국우주과학회보 제20권1호
• /
• pp.30.2-30.2
• /
• 2011

In this report, we present in-orbit radiometric performance prediction for the Amon-Ra (Albedo Monitor and Radiometer) energy channel instrument. The Integrated Ray Tracing (IRT) computational technique uses the ray sets arriving at the Amon-Ra instrument aperture orbiting around the L1 halo orbit. Using this, the variation of flux arriving at the energy channel detector was obtained when the Amon-Ra instrument including the energy channel design observes the Sun and Earth alternately. The flux detectability was verified at the energy channel detector (LME-500-A, InfraTecTM). The detector time response and RMS signal voltage were then derived from the simulated flux variation results. The computation results demonstrate that the designed energy channel optical system satisfies the in-orbit detectability requirement. The technical details of energy channel instrument design, IRT model construction, radiative transfer simulation and output signal computation results are presented together with future development plan.

• 한국경영과학회:학술대회논문집
• /
• 한국경영과학회 2000년도 추계학술대회 및 정기총회
• /
• pp.37-39
• /
• 2000

The purpose of this paper is to present a neural network model based on change-point detection for the prediction of the U.S. Treasury Securities. Interest rates have been studied by a number of researchers since they strongly affect other economic and financial parameters. Contrary to other chaotic financial data, the movement of interest rates has a series of change points due to the monetary policy of the U.S. government. The basic concept of this proposed model is to obtain intervals divided by change points, to identify them as change-point groups, and to use them in interest rates forecasting. The proposed model consists of three stages. The first stage is to detect successive change points in the interest rates dataset. The second stage is to forecast the change-point group with the backpropagation neural network (BPN). The final stage is to forecast the output with BPN. This study then examines the predictability of the integrated neural network model for interest rates forecasting using change-point detection.

• Computers and Concrete
• /
• 제10권6호
• /
• pp.557-573
• /
• 2012

This paper discusses the combined application of two different techniques, Neural Networks (NN) and Principal Component Analysis (PCA), for improved prediction of concrete properties. The combination of these approaches allowed the development of six neural networks models for predicting slump and compressive strength of concrete with mineral additives such as blast furnace slag, fly ash and silica fume. The Back-Propagation Multi-Layer Perceptron (BPMLP) with Bayesian regularization was used in all these models. They are produced to implement the complex nonlinear relationship between the inputs and the output of the network. They are also established through the incorporation of a huge experimental database on concrete organized in the form Mix-Property. Thus, the data comprising the concrete mixtures are much correlated to each others. The PCA is proposed for the compression and the elimination of the correlation between these data. After applying the PCA, the uncorrelated data were used to train the six models. The predictive results of these models were compared with the actual experimental trials. The results showed that the elimination of the correlation between the input parameters using PCA improved the predictive generalisation performance models with smaller architectures and dimensionality reduction. This study showed also that using the developed models for numerical investigations on the parameters affecting the properties of concrete is promising.

• 한국우주과학회:학술대회논문집(한국우주과학회보)
• /
• 한국우주과학회 2003년도 한국우주과학회보 제12권2호
• /
• pp.26-26
• /
• 2003

During fabrication process for the large space optical surfaces, the traditional bound abrasive grinding with bronze bond cupped diamond wheel tools leaves the machine marks and the subsurface damage to be removed by subsequent loose abrasive lapping. We explored a new grinding technique for efficient quantitative control of precision CNC grinding for space optics materials such as Zerodur. The facility used is a NANOFORM-600 diamond turning machine with a custom grinding module and a range of resin bond diamond tools. The machining parameters such as grit number, tool rotation speed, work-piece rotation speed, depth of cut and feed rate were altered while grinding the work-piece surfaces of 20-100 mm in diameter. The input grinding variables and the resulting surface quality data were used to build grinding prediction models using empirical and multi-variable regression analysis methods. The effectiveness of the grinding prediction model was then examined by running a series of precision CNC grinding operation with a set of controlled input variables and predicted output surface quality indicators. The experiment details, the results and implications are presented.