• 한국토양비료학회지
• /
• 제31권4호
• /
• pp.334-341
• /
• 1998

Sodium hydroxide concentrations were adjusted to 2.0, 2.5, 3.0 and 3.5M by dissolution in seawater. The fly ash was hydrothermally reacted with sodium hydroxide solutions (1:8, W:V) at $100^{\circ}C$ under the closed system. X-ray diffractogram proved that Na-P1 type zeolite was produced from bituminous coal fly ash. It is different from the X-ray of artificial zeolite produced by using sodium hydroxide solution dissolving in distilled water. Solid sieve structure was developed well by hydrothermal reaction with the ash and 3.0M sodium hydroxide. However chinks were observed in the structure of the product by 3.5M sodium hydroxide. CEC of the artificial zeolite was $244.5cmol^+\;kg^{-1}$ at 2.0M, 259.8 at 3.0M, 263.4 at 3.0M and 179.8 at 3.5M after 24 hours hydrothermal reaction; Artificial zeolite having high CEC, above $244.5cmol^+\;kg^{-1}$ could produce by using lower concentration of NaOH prepared in seawater than other production methods.

• Design & Manufacturing
• /
• 제13권3호
• /
• pp.53-58
• /
• 2019

This paper presents Artificial Neural Network(ANN) method to predict maximum injection pressure of injection molding machine and weights of injection molding products. 5 hidden layers with 10 neurons is used in the ANN. The ANN was conducted with 5 Input parameters and 2 response data. The input parameters, i.e., melt temperature, mold temperature, fill time, packing pressure, and packing time were selected. The combination of the orthogonal array L27 data set and 23 randomly generated data set were applied in order to train and test for ANN. According to the experimental result, error of the ANN for weights was $0.49{\pm}0.23%$. In case of maximum injection pressure, error of the ANN was $1.40{\pm}1.19%$. This value showed that ANN can be successfully predict the injection pressure and the weights of injection molding products.

• 전기전자학회논문지
• /
• 제24권4호
• /
• pp.1180-1183
• /
• 2020

최근 들어 IoT와 스마트홈의 발전에 따라 낙상 사고 감지, 화상 위험 감지와 같이 일상 생활에서의 안전 감지 기능이 많이 보급되기 시작했다. 이러한 안전 감지 기능은 대부분 인공지능에 의해 수행된다. 그러나 실험실 환경에서 안전 감지의 정확도만 평가하는 경우에는 실제로 일상 생활 환경에서 체감하게 되는 성능과 꽤 큰 차이를 보이는 경우가 많다. 본 논문에서는 이러한 문제점을 보완하기 위해 사용하는 두 가지 기법인 리빙랩과 혼동 매트리스를 소개한다. 리빙랩은 단순히 일상 생활환경의 모사를 넘어서 사용자가 직접 기술 개발 및 제품 설계에 참여할 수 있는 통로가 된다. 또한 혼동 매트리스에서 도출되는 다양한 성능 척도는 사용 목적에 적합하게 인공지능 시스템의 성능을 평가하는데 큰 도움을 준다.

• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2020년도 봄 학술논문 발표대회
• /
• pp.126-127
• /
• 2020

Recently, as interest in environmental issues increases, minimizing carbon dioxide generated during cement manufacturing is a problem to be solved. In order to solve such a problem, it is required to use an industrial by-product of recycled aggregate, blast furnace slag, and circulating fluidized bed boiler fly ash to replace it on the basis of geopolymer(=cementless). This study examines the characteristics of eco-friendly artificial stone according to the mixing ratio of geopolymer-based recycled aggregate. As a result of the experiment, when the addition rate of the alkali stimulant was 15% and the mixing ratio of the circulating aggregate was 70%, the flexural strength and compressive strength were the highest. Density and water absorption decreased as density of circulating aggregates increased and water absorption increased. However, when the mixing ratio of the circulating aggregate exceeded 70%, the flexural strength and compressive strength decreased. Therefore, in order to obtain strengths meeting the KS standards, the mixing ratio of recycled aggregate was set to 70%, and artificial stone was manufactured using industrial by-products.

• The Journal of Asian Finance, Economics and Business
• /
• 제7권12호
• /
• pp.109-114
• /
• 2020

The aim of this study is to develop basic artificial neural network models in forecasting the in-sample gross domestic product (GDP) of Malaysia. GDP is one of the main indicators in presenting the macro economic condition of a country as set by the world authority bodies such as the World Bank. Hence, this study uses an artificial neural network-based approach to make predictions concerning the economic growth of Malaysia. This method has been proposed due to its ability to overcome multicollinearity among variables, as well as the ability to cope with non-linear problems in Malaysia's growth data. The selected inputs and outputs are based on the previous literatures as well as the economic growth theory. Therefore, the selected inputs are exports, imports, private consumption, government expenditure, consumer price index (CPI), inflation rate, foreign direct investment (FDI) and money supply, which includes M1 and M2. Whilst, the output is real gross domestic product growth rate. The results of this study showed that the neural network method gives the smallest value of mean error which is 0.81 percent with a total difference of 0.70 percent. This implies that the neural network model is appropriate and is a relevant method in forecasting the economic growth of Malaysia.

• 전자통신동향분석
• /
• 제35권1호
• /
• pp.60-70
• /
• 2020

Artificial intelligence (AI) is expected to bring about a wide range of changes in the industry, based on the assessment that it is the most innovative technology in the last three decades. The manufacturing field is an area in which various artificial intelligence technologies are being applied, and through accumulated data analysis, an optimal operation method can be presented to improve the productivity of manufacturing processes. In addition, AI technologies are being used throughout all areas of manufacturing, including product design, engineering, improvement of working environments, detection of anomalies in facilities, and quality control. This makes it possible to easily design and engineer products with a fast pace and provides an efficient working and training environment for workers. Also, abnormal situations related to quality deterioration can be identified, and autonomous operation of facilities without human intervention is made possible. In this paper, AI technologies used in smart factories, such as the trends in generative product design, smart workbench and real-sense interaction guide technology for work and training, anomaly detection technology for quality control, and intelligent manufacturing facility technology for autonomous production, are analyzed.

• Current Photovoltaic Research
• /
• 제6권2호
• /
• pp.62-67
• /
• 2018

Multi-wire busbar-type bifacial n-type Si solar cells have been used for the fabrication of monofacial and bifacial photovoltaic (PV) module, where bifacial module was equipped with transparent backsheet while monofacial module was prepared using white backsheet. The comparison of six-day accumulated power production obtained from outdoor test under gray cement ground conditions using 60cell monofacial and bifacial PV modules suggested the bifacial gain of over 20% could be achieved. Furthermore, the outdoor evaluation tests of bifacial modules with different ground conditions such as cement (reference), green paint, white paint and green artificial grass, were performed. It turned out white paint showed the best albedo and thus the highest power production, while green paint and artificial grass showed less power generation than cement ground.

• 응용통계연구
• /
• 제19권3호
• /
• pp.461-479
• /
• 2006

본 논문에서는 이원오차성분을 갖는 패널회귀모형에서 모형식별을 위하여 LM 검정통계량을 유도하고 검정통계량의 연산을 위하여 인공회귀방법(Double-Length Artificial Regression, DLR)을 이용한다. 모의 실험 결과, 소표본의 경 우에는 Outer-Product Gradient(OPG)에 근거한 LM 검정통계량은 유위수준이 과대기각하는 경향을 보인 반면 DLR에 근거한 LM 검정통계량은 명목유의수준을 잘 유지하고 검정력도 높게 나타났다.

• 한국인공지능학회지
• /
• 제8권1호
• /
• pp.11-18
• /
• 2020

In this paper, it is to identify the effects of differences in interpretation levels depending on the type of brand association and the brain psychological distance on the evaluation of the product of that brand through two experiments. To test our hypotheses empirically, we conducted online survey. We addressed the hypotheses involving the general and relative impact of actual and ideal self-congruence on emotional brand attachment (H1) and explored the effect of product involvement as the moderating variable (H1-1 and H1-2). The goal of this research was to validate the results from involving our basic model and to explore the impact of two additional moderating variables (self-esteem and public self-consciousness: H2). We followed the same procedure. This finding is theoretical to the extent of the interpretation level theory in brand association research by applying the interpretation level theory to the brand association, and provides the meaning that, in practice, it is necessary to utilize the message of different types of brain psychological distance depending on the brand association characteristics that the brand has in defining the brand. In particular, it was confirmed that functional brand associations and symbolic brand annals have representational harmonization, respectively, depending on the low and high levels of interpretation levels.

• 한국분말재료학회지
• /
• 제27권5호
• /
• pp.365-372
• /
• 2020

Predicting the quality of materials after they are subjected to plasma sintering is a challenging task because of the non-linear relationships between the process variables and mechanical properties. Furthermore, the variables governing the sintering process affect the microstructure and the mechanical properties of the final product. Therefore, an artificial neural network modeling was carried out to correlate the parameters of the spark plasma sintering process with the densification and hardness values of Ti-6Al-4V alloys dispersed with nano-sized TiN particles. The relative density (%), effective density (g/㎤), and hardness (HV) were estimated as functions of sintering temperature (℃), time (min), and composition (change in % TiN). A total of 20 datasets were collected from the open literature to develop the model. The high-level accuracy in model predictions (>80%) discloses the complex relationships among the sintering process variables, product quality, and mechanical performance. Further, the effect of sintering temperature, time, and TiN percentage on the density and hardness values were quantitatively estimated with the help of the developed model.