• Applied Chemistry for Engineering
• /
• v.31 no.5
• /
• pp.520-525
• /
• 2020

In this study, we developed a machine learning-based model for predicting the production stage temperature of distillation process. It is necessary to predict an accurate temperature for control because the control of the distillation process is done through the production stage temperature. The temperature in distillation process has a nonlinear complex relationship with other variables and time series data, so we used the recurrent neural network algorithms to predict temperature. In the model development process, by adjusting three recurrent neural network based algorithms, and batch size, we selected the most appropriate model for predicting the production stage temperature. LSTM₁₂₈ was selected as the most appropriate model for predicting the production stage temperature. The prediction performance of selected model for the actual temperature is RMSE of 0.0791 and R² of 0.924.

• Applied Science and Convergence Technology
• /
• v.23 no.5
• /
• pp.248-253
• /
• 2014

Air Gap Membrane Distillation (AGMD) is one of several technologies that can be used to solve problems fresh water availability. AGMD exhibits several advantages, including low conductive heat loss and higher thermal efficiency, due to the presence of an air gap between the membrane and condensation wall. A previous study by Bhardwaj found that the condensation surface properties (materials and contact angle) affected the total collected fresh water in the solar distillation process. However, the process condition differences between solar distillation and AGMD might result in different condensation phenomena. In contrast, N. Miljkovic showed that a hydrophobic surface has higher condensation heat transfer. Moreover, to the best of our knowledge, there is no study that investigates the effect of condensation surface properties in AGMD to overall process performance (i.e. flux and thermal efficiency). Thus, in this study, we treated the AGMD condensation surface to make it hydrophobic or hydrophilic. The condensation surface could be made hydrophilic by immersing and boiling plate in deionized (DI) water, which caused the formation of hydrophilic aluminum hydroxide (AlOOH) nanostructures. Afterwards, the treated plate was coated using hexamethyldisiloxane (HMDSO) through plasma-enhanced chemical vapor deposition (PECVD). The result indicated that condensation surface properties do not affect the permeate flux or thermal efficiency significantly. In general, the permeate flux and thermal efficiency for the treated plates were lower than those of the non-treated plate (pristine). However, at a 1 mm and 3 mm air gap, the treated plate outperformed the non-treated plate (pristine) in terms of permeate flux. Therefore, although surface wettability effect was not significant, it still provided a little influence.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.13 no.8
• /
• pp.3764-3773
• /
• 2012

In this study, modeling and optimization works were completed for the separation of 99.9 mol% of methyl ethyl ketone from water through a pressure-swing distillation process since the azeotropic composition varies very sensitively with the change of system pressure. PRO/II with PROVISION release 9.1 was used for the computer simulation and Wilson activity coefficient model was chosen as a modeling equation. A pressure-swing distillation process can be classified into a low-high pressure columns configuration and a high-low pressure columns configuration. In this work, each configurations were optimized for the minimization of steam consumptions, respectively and were compared.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.9
• /
• pp.1244-1253
• /
• 2021

In this paper, we propose a method for predicting in advance whether pedestrians will enter the hazardous area after the current time using the pedestrian trajectory prediction method and an efficient simplification method of the trajectory prediction network. In addition, we propose a method to apply KD(Knowledge Distillation) to a small network for real-time operation in an embedded environment. Using the correlation between predicted future paths and hazard zones, we determined whether to enter or not, and applied efficient KD when learning small networks to minimize performance degradation. Experimentally, it was confirmed that the model applied with the simplification method proposed improved the speed by 37.49% compared to the existing model, but led to a slight decrease in accuracy. As a result of learning a small network with an initial accuracy of 91.43% using KD, It was confirmed that it has improved accuracy of 94.76%.

• Journal of Broadcast Engineering
• /
• v.26 no.4
• /
• pp.419-428
• /
• 2021

Shadow removal plays a key role for the pre-processing of image processing techniques such as object tracking and detection. With the advances of image recognition based on deep convolution neural networks, researches for shadow removal have been actively conducted. In this paper, we propose a novel method for shadow removal, which utilizes self attention distillation to extract semantic features. The proposed method gradually refines results of shadow detection, which are extracted from each layer of the proposed network, via top-down distillation. Specifically, the training procedure can be efficiently performed by learning the contextual information for shadow removal without shadow masks. Experimental results on various datasets show the effectiveness of the proposed method for shadow removal under real world environments.

• Proceedings of the Korean Radioactive Waste Society Conference
• /
• 2018.05a
• /
• pp.57-57
• /
• 2018

The electrorefining process is generally composed of two recovery steps in pyroprocessing - the deposit of uranium onto a solid cathode and the recovery of the remaining uranium and TRU elements simultaneously by a liquid cadmium cathode. The liquid cathode processing is necessary to separate cadmium from the actinide elements since the actinide deposits are dissolved or precipitated in a liquid cathode. Distillation process was employed for the cathode processing. It is very important to avoid a splattering of cadmium during evaporation due to the high vapor pressure. In this study, a multi-layer porous round cover was proposed and examined to develop a splatter shield for the Cd distillation crucible. Cadmium vapor can be released through the holes of the shield, whereas liquid drops can be collected in the multiple hemisphere. The collected drops flow on the round surface of the cover and flow down into the crucible. The crucible cover was fabricated and tested in the Cd distiller. The cover was made with three stainless steel round plates with a diameter of 33.50 mm. The distance between the hemispheres and the diameter of the holes are 10 and 1 mm, respectively. About 40 grams of Cd and about 4 grams of Bi was distilled at a reduced pressure for two hours at $470^{\circ}C$. After the Cd distillation experiment, cadmium was not detected and more than 90 % of Bi remained in the ICP-OES analysis. Therefore the crucible cover can be a candidate for the splatter shield of the Cd distillation crucible. Further development of the crucible cover is necessary for the decision of the optimum cover geometry and the operating conditions of the Cd distiller.

• Korean Journal of Metals and Materials
• /
• v.48 no.2
• /
• pp.154-162
• /
• 2010

A fundamental study of the distillation behavior of ferromanganese alloy melts was carried out at 1773 K and 0.1333 kPa (=1 Torr). During the distillation of ferromanganese alloy melts under reduced pressure, manganese vaporizes preferentially to phosphorus and other solute elements. High purity manganese metal with a very low content of solute elements can be obtained by distillation of ferromanganese alloy melts. The evaporation of manganese is suppressed as the carbon content of ferromanganese alloy melt increases due to the decrease of activity and vapor pressure of the manganese. When the carbon content of ferromanganese alloy melt is high, melt droplets are ejected from the bath, especially in the early stages of the distillation, and the solute elements in the splashed droplets contaminate the condensed material. The ejection of melt droplets is presumed to be caused by the increase of melting temperature and viscosity of the surface layer of melt due to the enrichment of solute elements such as carbon and iron.

• Membrane and Water Treatment
• /
• v.13 no.5
• /
• pp.235-243
• /
• 2022

The paper presents the effect of operating temperatures and flow rates on the distillate flux that can be obtained from a hydrophobic membrane having the characteristics: pore size of 0.15 ㎛; thickness of 130 ㎛; and 85% porosity. That membrane in the present investigation could be the direct contact (DCMD) or the air-gap membrane distillation (AGMD). To model numerically the membrane distillation processes, the two-dimensional computational fluid dynamic (CFD) is used for the DCMD and AGMD cases here. In this work, DCMD and AGMD models have been validated with the experimental data using different flows (Parallel and Counter-current flows) in non-steady-state situations. A good agreement is obtained between the present results and those of the experimental data in the literature. The new approach in the present numerical modeling has allowed examining effects of the nature of materials (Polyvinylidene fluoride (PVDF) polymers, copolymers, and blends) used on thermal properties. Moreover, the effect of the area surface of the membrane (0.021 to 3.15 ㎡) is investigated to explore both the laminar and the turbulent flow regimes. The obtained results found that copolymer P(VDF-TrFE) (80/20) is more effective than the other materials of membrane distillation (MD). The mass flux and thermal efficiency reach 193.5 (g/㎡s), and 83.29 % using turbulent flow and an effective area of 3.1 ㎡, respectively. The increase of feed inlet temperatures and its flow rate, with the reduction of cold temperatures and its flow rate are very effective for increasing distillate water flow in MD applications.

• Journal of Radiation Protection and Research
• /
• v.48 no.2
• /
• pp.77-83
• /
• 2023

Background: The purpose of this study is to purify uranium (U[VI])-contaminated soil-flushing effluent using the precipitation-distillation process for clearance. Precipitation and distillation are commonly used techniques for water treatment. We propose using a combination of these methods for the simple and effective removal of U(VI) ions from soil-flushing effluents. In addition, the U concentration (Bq/g) of solid waste generated in the proposed treatment process was analyzed to confirm whether it satisfies the clearance level. Materials and Methods: Uranium-contaminated soil was decontaminated by soil-flushing using 0.5 M sulfuric acid. The soil-flushing effluent was treated with sodium hydroxide powder to precipitate U(VI) ions, and the remaining U(VI) ions were removed by phosphate addition. The effluent from which U(VI) ions were removed was distilled for reuse as a soil-flushing eluent. Results and Discussion: The purification method using the precipitation-distillation process proposed in this study effectively removes U(VI) ions from U-contaminated soil-flushing effluent. In addition, most of the solid waste generated in the purification process satisfied the clearance level. Conclusion: The proposed purification process is considered to have potential as a soil-flushing effluent treatment method to reduce the amount of radioactive waste generated.

• Membrane and Water Treatment
• /
• v.1 no.1
• /
• pp.1-12
• /
• 2010

Membrane distillation process was used for purification of pre-treated natural water (tap water). The rejection of inorganic and organic compounds in this process was investigated. The obtained rejection of inorganic solutes was closed to 100%, but the volatile organic compounds (VOCs) diffused through the membrane together with water vapour. The content of trihalomethanes (THMs) in the obtained distillate was two-three fold higher than that in the feed, therefore, the rejection of the total organic compounds present in the tap water was reduced to a level of 98%. The intensive membranes scaling was observed during the water separation. The morphology and composition of the fouling layer was studied using scanning electron microscopy coupled with energy dispersion spectrometry. The influence of thermal water pre-treatment performed in a heat exchanger followed by filtration on the MD process effectiveness was evaluated. This procedure caused that significantly smaller amounts of $CaCO_3$ crystallites were deposited on the membrane surface, and a high permeate flux was maintained over a period of 160 h.