• Journal of the Korean Society for Geothermal and Hydrothermal Energy
• /
• v.18 no.3
• /
• pp.1-6
• /
• 2022

Ground source heat pump (GSHP) system is highly efficient and environment-friendly and supplies heating, cooling and hot water to buildings. For an optimal design of the GSHP system, the ground thermal properties should be determined to estimate the heat exchange rate between ground and borehole heat exchangers (BHE) and the system performance during long-term operating periods. However, the process increases the initial cost and construction period, which causes the system to be hindered in distribution. On the other hand, much research has been applied to the artificial neural network (ANN) to solve problems based on data efficiently and stably. This research proposes the predictive performance model utilizing ANN considering local characteristics and weather data for the predictive performance model. The ANN model predicts the entering water temperature (EWT) from the GHEs to the heat pump for the modular GHEs, which were developed to reduce the cost and spatial disadvantages of the vertical-type GHEs. As a result, the temperature error between the data and predicted results was 3.52%. The proposed approach was validated to predict the system performance and EWT of the GSHP system.

• Journal of Power Electronics
• /
• v.18 no.2
• /
• pp.467-481
• /
• 2018

Modular multilevel converter (MMC)-based high-voltage direct current (HVDC) presents attractive technical advantages and contributes to enhanced system operation and reduced oscillation damping in dynamic MMC-HVDC systems. We propose an advanced small-signal multi-terminal MMC-HVDC based on dynamic phasors and state space for power system stability analysis to enhance computational accuracy and reduce simulation time. In accordance with active and passive network control strategies for multi-terminal MMC-HVDC, the matchable small-signal stability models containing high harmonics and dynamics of internal variables are conducted, and a related theoretical derivation is carried out. The proposed advanced small-signal model is then compared with electromagnetic-transient and traditional small-signal state-space models by adopting a typical multi-terminal MMC-HVDC network with offshore wind generation. Simulation indicates that the advanced small-signal model can successfully follow the electromechanical transient response with small errors and can predict the damped oscillations. The validity and applicability of the proposed model are effectively confirmed.

• The KIPS Transactions:PartB
• /
• v.8B no.6
• /
• pp.699-704
• /
• 2001

ABSTRACT In this paper, a new hybrid modular recurrent TDNN (time-delay neural network)-HMM (hidden Markov model) architecture for speech recognition has been studied. In TDNN, the recognition rate could be increased if the signal window is extended. To obtain this effect in the neural network, a high-level memory generated through a feedback within the first hidden layer of the neural network unit has been used. To increase the ability to deal with the temporal structure of phonemic features, the input layer of the network has been divided into multiple states in time sequence and has feature detector for each states. To expand the network from small recognition task to the full speech recognition system, modular construction method has been also used. Furthermore, the neural network and HMM are integrated by feeding output vectors from the neural network to HMM, and a new parameter smoothing method which can be applied to this hybrid system has been suggested.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.423-426
• /
• 2003

In this paper, we use the modular neural network and recurrent neural network structure to implement the artificial brain information processing. We also select related adaptive learning methods to learn the entirely new input in the existed neural network. With this, a part of information process in brain is implemented as and autonomous and adaptive model by neural network and further more, the entire model for information process in brain can be introduced.

• Journal of the Korea Society for Simulation
• /
• v.10 no.4
• /
• pp.51-64
• /
• 2001

It is quite necessary that an organization's information network should be equipped with a proper security system based on its scale and importance. One of the effective methods is to use the simulation model for deciding which security policy and mechanism is appropriate for the complex network. Our goal is to build a foundation of knowledge-based modeling and simulation environment for the network security. With this environment, users can construct the abstracted model of security mechanisms, apply various security policies, and quantitatively analyze their security performance against possible attacks. In this study, we considered security domain from several points of view and implemented the models based on a systematic modeling approach. We enabled the model to include knowledge in modular fashion and provided well-defined guidelines for transforming security policy to concrete rule set.

• Journal of Korea Society of Industrial Information Systems
• /
• v.18 no.4
• /
• pp.25-35
• /
• 2013

This paper focuses on building a generalized mood classification model with many mood classes instead of a personalized one with few mood classes. Two methods are adopted to improve the performance of mood classification. The one of them is feature reduction based on standard deviation of feature values, which is designed to solve the problem of lowered performance when all 391 features provided by MIR toolbox used to extract features of music. The experiments show that the feature reduction methods suggested in this paper have better performance than that of the conventional dimension reduction methods, R-Square and PCA. As performance improvement by feature reduction only is subject to limit, modular neural network is used as another method to improve the performance. The experiments show that the method also improves performance effectively.

• The Korean Journal of Applied Statistics
• /
• v.34 no.2
• /
• pp.191-204
• /
• 2021

Visual Question Answering (VQA) and image captioning are tasks that require understanding of the features of images and linguistic features of text. Therefore, co-attention may be the key to both tasks, which can connect image and text. In this paper, we propose a model to achieve high performance for VQA by image caption generated using a pretrained standard transformer model based on MSCOCO dataset. Captions unrelated to the question can rather interfere with answering, so some captions similar to the question were selected to use based on a similarity to the question. In addition, stopwords in the caption could not affect or interfere with answering, so the experiment was conducted after removing stopwords. Experiments were conducted on VQA-v2 data to compare the proposed model with the deep modular co-attention network (MCAN) model, which showed good performance by using co-attention between images and text. As a result, the proposed model outperformed the MCAN model.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.4 no.5
• /
• pp.937-942
• /
• 2000

This paper describes for applications of neural networks in the field of arc welding. Conventional, automated process generally involves sophisticated sensing and control techniques applied to various processing parameters. Welding parameters affecting quality include the arc voltage, the welding current and the torch travel speed. The relationship between the welding parameters and weld quality is not a direct one, and in addition, the effect of the weld parameter variables are not independent of the each other - changing the welding current will affect the arc voltage, and so on. Finally, a suitable proposal to improve the construction of the model has also been presented in the paper.

• Nuclear Engineering and Technology
• /
• v.53 no.8
• /
• pp.2547-2555
• /
• 2021

The frequency of reactor coolant leakage is expected to increase over the lifetime of a nuclear power plant owing to degradation mechanisms, such as flow-acceleration corrosion and stress corrosion cracking. When loss of coolant accidents (LOCAs) occur, several parameters change rapidly depending on the size and location of the cracks. In this study, leak flow during LOCAs is predicted using a deep fuzzy neural network (DFNN) model. The DFNN model is based on fuzzy neural network (FNN) modules and has a structure where the FNN modules are sequentially connected. Because the DFNN model is based on the FNN modules, the performance factors are the number of FNN modules and the parameters of the FNN module. These parameters are determined by a least-squares method combined with a genetic algorithm; the number of FNN modules is determined automatically by cross checking a fitness function using the verification dataset output to prevent an overfitting problem. To acquire the data of LOCAs, an optimized power reactor-1000 was simulated using a modular accident analysis program code. The predicted results of the DFNN model are found to be superior to those predicted in previous works. The leak flow prediction results obtained in this study will be useful to check the core integrity in nuclear power plant during LOCAs. This information is also expected to reduce the workload of the operators.

• Journal of Korea Water Resources Association
• /
• v.34 no.6
• /
• pp.701-711
• /
• 2001

Forecasting of water quality variation is not an easy process due to the complicated nature of various water quality factors and their interrelationships. The objective of this study is to test the applicability of neural network models to the forecasting of the water quality at Gongju station in Geum River. This is done by forecasting monthly water qualities such as DO, BOD, and TN, and comparing with those obtained by ARIMA model. The neural network models of this study use BP(Back Propagation) algorithm for training. In order to improve the performance of the training, the models are tested in three different styles ; MANN model which uses the Moment-Adaptive learning rate method, LMNN model which uses the Levenberg-Marquardt method, and MNN model which separates the hidden layers for judgement factors from the hidden layers for water quality data. the results show that the forecasted water qualities are reasonably close to the observed data. And the MNN model shows the best results among the three models tested