• Bulletin of the Korean Chemical Society
• /
• v.26 no.12
• /
• pp.2007-2016
• /
• 2005

An artificial neural network (ANN) is successfully presented for prediction acidity constant (pKa) of various benzoic acids and phenols with diverse chemical structures using a nonlinear quantitative structure-property relationship. A three-layered feed forward ANN with back-propagation of error was generated using six molecular descriptors appearing in the multi-parameter linear regression (MLR) model. The polarizability term $(\pi_1)$, most positive charge of acidic hydrogen atom $(q^+)$, molecular weight (MW), most negative charge of the acidic oxygen atom $(q^-)$, the hydrogen-bond accepting ability $(\epsilon_B)$ and partial charge weighted topological electronic (PCWTE) descriptors are inputs and its output is pKa. It was found that properly selected and trained neural network with 205 compounds could fairly represent dependence of the acidity constant on molecular descriptors. For evaluation of the predictive power of the generated ANN, an optimized network was applied for prediction pKa values of 37 compounds in the prediction set, which were not used in the optimization procedure. Squared correlation coefficient $(R^2)$ and root mean square error (RMSE) of 0.9147 and 0.9388 for prediction set by the MLR model should be compared with the values of 0.9939 and 0.2575 by the ANN model. These improvements are due to the fact that acidity constant of benzoic acids and phenols in water shows nonlinear correlations with the molecular descriptors.

• Transactions of the Korean hydrogen and new energy society
• /
• v.24 no.3
• /
• pp.264-274
• /
• 2013

Piping systems play an important role in gas and oil transferring system. In the piping system, there are many elements, such as valves and flow meters. In order to check their normal operating conditions, each signal from each element is displayed on the monitor in the pipe control room. By the way, there are several accidental cases in the piping system even if all signals from the local elements are judged to be normal on the monitor in the control room. Further, opposite cases often happen even the monitor shows abnormal while the local elements work normal. To overcome this abnormal functions, it is not so easy to construct the environment in which sensors detecting the working states of all elements installed in the piping system. In this paper, a new non-contact measurement technique which can calculate the elements' delicate displacements by using a PIV(particle image velocimetry) and diagnose their working states by using a neural network is proposed. The measurement system consists of a host computer, a micro system, a telescope and a high-resolution camera. As a preliminary test, the constructed measurement system was applied to measure delicate vibrations of mobile phones. For practical application, a pneumatic system was measured by the constructed system.

• Transactions of the Korean hydrogen and new energy society
• /
• v.31 no.5
• /
• pp.436-443
• /
• 2020

The performance prediction model of a solid oxide fuel cell stack has been developed using deep neural network technique, one of the machine learning methods. The machine learning has been received much interest in various fields, including energy system mo- deling. Using machine learning technique can save time and cost requried in developing an energy system model being compared to the conventional method, that is a combination of a mathematical modeling and an experimental validation. Results reveal that the mean average percent error, root mean square error, and coefficient of determination (R2) range 1.7515, 0.1342, 0.8597, repectively, in maximum. To improve the predictability of the model, the pre-processing is effective and interpolative machine learning and application is more accurate than the extrapolative cases.

• Publications of The Korean Astronomical Society
• /
• v.22 no.4
• /
• pp.189-199
• /
• 2007

In this paper, we describe the proposed KVN (Korean VLBI Network) clock system in order to make the observation of the VLBI effectively. In general, the GPS system is widely used for the time information in the single dish observation. In the case of VLBI observation, a very high precise frequency standard is needed to perform the observation in accordance with the observation frequency using the radio telescope with over 100km distance. The objective of the high precise clock system is to insert the time-tagging information to the observed data and to synchronize it with the same clock in overall equipments which used in station. The AHM (Active Hydrogen Maser) and clock system are basically used as a frequency standard equipments at VLBI station. This system is also adopted in KVN. The proposed KVN clock system at each station consists of the AHM, GPS time comparator, standard clock system, time distributor, and frequency standard distributor. The basic experiments were performed to check the AHM system specification and to verify the effectiveness of implemented KVN clock system. In this paper, we briefly introduce the KVN clock system configuration and experimental results.

• Journal of the Korean Society of Propulsion Engineers
• /
• v.25 no.6
• /
• pp.1-11
• /
• 2021

To develop an efficient procedure related to the flamelet library, the machine learning process based on artificial neural network(ANN) is applied for the gaseous hydrogen/liquid oxygen combustor under a supercritical pressure condition. For hidden layers, 25 combinations based on Rectified Linear Unit(ReLU) and hyperbolic tangent are adopted to find an optimum architecture in terms of the computational efficiency and the training performance. For activation functions, the hyperbolic tangent is proper to get the high learning performance for accurate properties. A transformation learning data is proposed to improve the training performance. When the optimal node is arranged for the 4 hidden layers, it is found to be the most efficient in terms of training performance and computational cost. Compared to the interpolation procedure, the ANN procedure reduces computational time and system memory by 37% and 99.98%, respectively.

• Journal of the Korean Institute of Gas
• /
• v.28 no.1
• /
• pp.1-10
• /
• 2024

In this study, we constructed a process simulation model for an agricultural by-products based Solid Oxide Fuel Cell (SOFC) combined heat and power generation system as part of the introduction of technology for energy self-sufficiency in the agricultural sector. The aim was to reduce the burden of increasing fuel and electricity consumption due to rapid fluctuations in international oil prices and the expansion of smart farming in domestic farms, while contributing to the national greenhouse gas reduction goals. Based on the experimental results of 0.3 ton/day torrefied agricultural by-product gasification experiment, a model for an agricultural by-product-based SOFC cogeneration system was constructed, and optimization of the heat exchange network was conducted for SOFC capacities ranging from 4 to 20 kW. The results indicated that an 8 kW agricultural by-product-based SOFC cogeneration system was optimal under the current system conditions. It is anticipated that these research findings can serve as foundational data for future commercial facility design.

• Bulletin of the Korean Chemical Society
• /
• v.25 no.4
• /
• pp.466-470
• /
• 2004

The crystals of the new melaminium salt, i.e. melaminium acetate acetic acid solvate monohydrate, $C_3H_7N_6^+ {\cdot}CH_3COO^- {\cdot}CH_3COOH{\cdot}H_2O$, were obtained by the slow evaporation of an aqueous solution at room temperature. Powder infrared and Raman spectra were measured and interpreted. The vibrational spectra in the region of internal vibrations of ions corroborate structural data recently published by Perpetuo and Janczak.$^1$ Some spectral features of this new crystal are referred to corresponding one for melamine crystal as well as other melamine complexes in crystalline form. Hydrogen-bonded network present in the crystal gives notable vibrational effect.

• Proceedings of the Polymer Society of Korea Conference
• /
• 2006.10a
• /
• pp.297-297
• /
• 2006

Recently columnar liquid crystals have been studied due to their possible application to organic conducting materials. Supramolecular columnar liquid crystals consist of mesogenic unit which can aggregate into discs that will make up the columns which associate to form a two-dimensional network. In this study, we prepared supramolecular columnar liquid crystals containing hydrogen bonding between carboxylic acid and, pyridine moieties. Thermal and structural properties of prepared complexe were investigated, and it exhibited hexagonal columnar structure ($Col_{h}$) at room temperature.

• Journal of the Korean Chemical Society
• /
• v.16 no.1
• /
• pp.6-12
• /
• 1972

The crystal structure of monoethanolamine hydrochloride is triclinic P1 with two formula units in a cell of dimensions a = $4.42\pm0.02$, b = $7.44\pm0.02$, c = $7.48\pm0.02$, $\alpha$ = $102.4\pm0.3$, $\beta$ = $91.1\pm0.3$, $\gamma$ = $77.2\pm0.3^{\circ}.$ The configuration of monoethanolamine is a gauche form with dihedral angle, $90^{\circ}$. The nitrogen atom forms four hydrogen bonds, three to Cl- ions(3.15, 3.24, $3.28\AA)$ and one to a hydroxyl group of another molecule (N${\cdot}{\cdot}{\cdot}$O, $2.90{\AA})$. The oxygen also forms two such bonds, one to a Cl- ion $(3.14\AA)$, one to an amine group of another molecule (O${\cdot}{\cdot}{\cdot}$N, $2.90{\AA}).$ Molecules are linked into two-dimensional network by hydrogen bonds.

• Proceedings of the Korea Technical Association of the Pulp and Paper Industry Conference
• /
• 2006.06b
• /
• pp.423-426
• /
• 2006

Paper has fibers and fines network structure and it is strongly affected by interface bonding between fibers. Depending on the inter-fiber bonding, paper bulk is determined. Fines play an important roll in Campbell and consolidation effect through wet pressing and drying operations. Refined Sw-BKP, Hw-BKP and BCTMP fines were used to investigate the fines effect. Wet-web strength, breaking length, scattering coefficient, and hydrodynamic specific volume were measured. According to the result of experiments, chemical and morphological compositions of fines do not strongly affect to wet-web forming, but strongly affect to drying operations which form hydrogen bonding among fiber-fines-fiber matrixes. Paper bulk should be controlled by the extent of hydrogen bonding between fibers during drying operations.