• KIPS Transactions on Computer and Communication Systems
• /
• v.9 no.8
• /
• pp.171-180
• /
• 2020

Smart Factory consists of digital automation solutions throughout the production process, including design, development, manufacturing and distribution, and it is an intelligent factory that installs IoT in its internal facilities and machines to collect process data in real time and analyze them so that it can control itself. The smart factory's equipment works in a physical combination of numerous hardware, rather than a virtual character being driven by a single object, such as a game. In other words, for a specific common goal, multiple devices must perform individual actions simultaneously. By taking advantage of the smart factory, which can collect process data in real time, if reinforcement learning is used instead of general machine learning, behavior control can be performed without the required training data. However, in the real world, it is impossible to learn more than tens of millions of iterations due to physical wear and time. Thus, this paper uses simulators to develop grid sortation systems focusing on transport facilities, one of the complex environments in smart factory field, and design cooperative multi-agent-based reinforcement learning to demonstrate efficient behavior control.

• The Transactions of the Korea Information Processing Society
• /
• v.3 no.6
• /
• pp.1397-1406
• /
• 1996

In this paper, we propose a discrete model of conveyor systems, which is frequently used in flexible manufacturing systems to transfer work-in-process( WIP) between manipulators. In the case where the time required for transferring WIP's between manipulators are greater than that of manufacturing itself, as in many flexible assembly lines, the quantitative model of the transfer systems is needed to analyze the behavior and productivity of the whole manufacturing system. The proposed model is based upon the assumptions that the length of any unit conveyor component is integer multiple of the length of a pallet and hat the transferring speed of the conveyor is constant. Under these assumptions, the observation moments and the length of the conveyor can be quantized. Hence, the state of a conveyor can be represented by two kinds of Boolean variables: one representing the presence of a pallet on each quantize conveyor length and the other representing the mobility of this pallet. The whole conveyor system can be modeling as a network composed of branches and knots based on these two Boolean variables. The proposed modelling method was tested with various conveyor system configurations and showed that the model can be adopted successfully for the simulation of transfer systems and of the piloting of manufacturing processes.

• Journal of the Korean Magnetics Society
• /
• v.21 no.2
• /
• pp.77-82
• /
• 2011

The use of soft magnetic materials have been increasing in the various industrial fields according to the increasing demand for high performance, automatic, miniaturing equipments in the recent our life. In this study, we investigated the effect of factors on the core loss and magnetic properties of electrical steel and soft magnetic composites. Furthermore, we reviewed the major efforts to reduce the core loss and improve the soft magnetic properties in the two main soft magnetic materials. Domain purification which results from reduced density of defects in cleaner electrical steels is combined with large grains to reduce hysteresis loss. The reduced thickness and the high electrical conductivity reduce the eddy current component of loss. Furthermore, the coating applied to the surface of electrical steel and texture control lead to improve high permeability and low core loss. There is an increasing interest in soft magnetic composite materials because of the demand for miniaturization of cores for power electronic applications. The SMC materials have a broad range of potential applications due to the possibility of true 3-D electromagnetic design and higher frequency operation. Grain size, sintering temperature, and the degree of porosity need to be carefully controlled in order to optimize structure-sensitive properties such as maximum permeability and low coercive force. The insulating coating on the powder particles in SMCs eliminates particle-to-particle eddy current paths hence minimizing eddy current losses, but it reduces the permeability and to a small extent the saturation magnetization. The combination of new chemical composition with optimum powder manufacturing processes will be able to result in improving the magnetic properties in soft magnetic composite materials, too.

• Journal of Korea Society of Industrial Information Systems
• /
• v.12 no.3
• /
• pp.116-123
• /
• 2007

Despite the number of backlight manufacturer is increased as the market of flat panel display equipments and related development devices is enlarged, the inspection based on the human eye is still used in many backlight production lines. The defects such as particle, spot and scratch on the light emitting surface of the backlight prevent the LCD device from displaying the colors correctly. From that manual inspection it is difficult to maintain the quality of backlight consistently because the accuracy and the speed of the inspection may change with the physical condition of the operater. In this paper we studied on the development of automatic backlight surface defect inspection system. For this, we made up of the computer vision system and we developed the main program with various user interfaces to operate the inspection system effectively. And we developed the image processing module to extract the defect information. Furthermore, we presented the labeling process to reconstruct defect regions using the labeling table and the defect index. From the experimental results, we found that our system can detect all defect regions identified from human eye and it is sufficient to substitute for the conventional surface inspection.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.25 no.2
• /
• pp.119-125
• /
• 2015

A concentration meter is widely used at purification plants, sewage treatment plants and waste water treatment plants to sort and transfer high concentration sludge and to control the amount of chemical dosage. When the strange substance is contained in the sludge, however, the attenuation of ultrasonic wave could be increased or not be transmitted to the receiver. At that case, the value of concentration meter is higher than the actual density value or vibrated up and down. It has also been difficult to automate the residuals treatment process according to the problems as sludge attachment or damage of a sensor. Multi-beam ultrasonic concentration meter has been developed to solve these problems, but the failure of the ultrasonic beam of a specific concentration measurement value degrade the performance of the entire system. This paper proposes the method to improve the accuracy of sludge concentration rate by choosing reliable sensor values and learning them by proposed algorithm. The prediction algorithm is chosen as neuro-fuzzy model, which is tested by the various experiments.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.9
• /
• pp.206-211
• /
• 2016

Various applications require dry air at low temperature, such automation equipment, semiconductor manufacturing, chemical production lines, and coating processes for the shipbuilding industry. Four evaporators for low temperature (below $0^{\circ}C$) were installed for a dehumidification system. Moist air is cooled sequentially over three evaporators. The first evaporator has an evaporation temperature of $13^{\circ}C$, that of the second evaporator is $5^{\circ}C$, and that of the third evaporator is maintained at $-1.3^{\circ}C$. In the fourth evaporator implantation thereby the moisture contained in the moisture air. A pressure regulator (CPCE 12) is used at this point and is defrosted when the vapor pressure is below a set value. The non-implantation moisture of the air is a heating system that uses the waste heat of a condenser with high temperature. It develops the cooling type's dehumidifier, which is important equipment that prevents the destruction of protein and measures the temperature and humidity at each interval by changing the front air velocity from 1.0 m/s to 4.0 m/s. The cooling capacity was also calculated. The greatest cooling capacity was 1.77 kcal/h for a front air velocity of 2.0 m/s

• Composites Research
• /
• v.32 no.1
• /
• pp.65-70
• /
• 2019

The aircraft composites wing parts are usually integrated with adhesive or fastener. These laminated composites have weak interlaminar strength, which can lead to delamination. In order to compensate the disadvantages of laminated composites, it is possible to improve the strength, durability, shock and fatigue resistance by reinforcing the fiber in the thickness direction. In addition, using a single structure near-net-shape saves the manufacturing time and the number of fasteners, thus can reduce the overall cost of the composite parts. In this study, compression test, tensile test and open-hole tensile test are carried out for three structural architecture of 3D (three-dimensional) textile preforms: orthogonal(ORT), layer-to-layer(LTL) and through-the-thickness(TTT) patterns. Among these, the orthogonal textile composite shows the highest Young's modulus and strength in tensile and compression. The notch sensitivity of the orthogonal textile composite was the smallest as compared with UD (unidirectional) and 2D (two-dimensional) fabric laminates.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.2
• /
• pp.104-112
• /
• 2021

For extrusion processes in the process industry, the need to build smart factories is increasing. However, in most extrusion production sites, the production method is continuous, and because the properties of the data are undeed, it is difficult to process the data. In order to solve this problem, we present a methodology utilizing a near field communication (NFC) sensor rather than water-based data entry. To this end, a wireless network environment was built, and a data management method was designed. A non-contact NFC method was studied for the production performance-data input method, and an analysis method was implemented using the pivot function of the Excel program. As a result, data input using NFC was automated, obtaining a quantitative effect from reducing the operator's data processing time. In addition, using the input data, we present a case where a bottleneck is improved due to quality problems.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.15 no.4
• /
• pp.271-282
• /
• 2022

In this paper, we propose a digital human content creation system. The digital human content creation system works with 3D AI modeling through whole-body scanning, and is produced with 3D modeling post-processing, texturing, rigging. By combining this with virtual reality(VR) content information, natural motion of the virtual model can be achieved in virtual reality, and digital human content can be efficiently created in one system. Therefore, there is an effect of enabling the creation of virtual reality-based digital human content that minimizes resources. In addition, it is intended to provide an automated pre-processing process that does not require a pre-processing process for 3D modeling and texturing by humans, and to provide a technology for efficiently managing various digital human contents. In particular, since the pre-processing process such as 3D modeling and texturing to construct a virtual model are automatically performed by artificial intelligence, so it has the advantage that rapid and efficient virtual model configuration can be achieved. In addition, it has the advantage of being able to easily organize and manage digital human contents through signature motion.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.32 no.5
• /
• pp.1019-1034
• /
• 2022

Malware attacks become more prevalent in the hyper-connected society of the 4th industrial revolution. To respond to such malware, automation of malware detection using artificial intelligence technology is attracting attention as a new alternative. However, using artificial intelligence without collateral for its reliability poses greater risks and side effects. The EU and the United States are seeking ways to secure the reliability of artificial intelligence, and the government announced a reliable strategy for realizing artificial intelligence in 2021. The government's AI reliability has five attributes: Safety, Explainability, Transparency, Robustness and Fairness. We develop four elements of safety, explainable, transparent, and fairness, excluding robustness in the malware detection model. In particular, we demonstrated stable generalization performance, which is model accuracy, through the verification of external agencies, and developed focusing on explainability including transparency. The artificial intelligence model, of which learning is determined by changing data, requires life cycle management. As a result, demand for the MLops framework is increasing, which integrates data, model development, and service operations. EXE-executable malware and documented malware response services become data collector as well as service operation at the same time, and connect with data pipelines which obtain information for labeling and purification through external APIs. We have facilitated other security service associations or infrastructure scaling using cloud SaaS and standard APIs.