• Journal of Sensor Science and Technology
• /
• v.32 no.5
• /
• pp.320-327
• /
• 2023

In this study, an FPGA-based sealer inspection system was developed to inspect the sealer applied to install vehicle glass on a car body. The sealer is a liquid or paste-like material that promotes adhesion such as sealing and waterproofing for mounting and assembling vehicle parts to a car body. The system installed in the existing vehicle design parts line does not detect the sealer in the glass rotation section and takes a long time to process. This study developed a line laser camera sensor and an FPGA vision signal processing module to solve this problem. The line laser camera sensor was developed such that the resolution and speed of the camera for data acquisition could be modified according to the irradiation angle of the laser. Furthermore, it was developed considering the mountability of the entire system to prevent interference with the sealer ejection machine. In addition, a vision signal processing module was developed using the Zynq-7020 FPGA chip to improve the processing speed of the algorithm that converted the profile to the sealer shape image acquired from a 2D camera and calculated the width and height of the sealer using the converted profile. The performance of the developed sealer application inspection system was verified by establishing an experimental environment identical to that of an actual automobile production line. The experimental results confirmed the performance of the sealer application inspection at a level that satisfied the requirements of automotive field standards.

• The Journal of Bigdata
• /
• v.6 no.1
• /
• pp.23-35
• /
• 2021

In the era of the 4th industrial revolution, smart factories have received great attention, where production and manufacturing technology and ICT converge. With the development of IoT technology and big data, automation of production systems has become possible. In the advanced manufacturing industry, production systems are subject to unscheduled performance degradation and downtime, and there is a demand to reduce safety risks by detecting and reparing potential errors as soon as possible. This study designs a model based on supervised and unsupervised learning for detecting anomalies. The accuracy of XGBoost, LightGBM, and CNN models was compared as a supervised learning analysis method. Through the evaluation index based on the confusion matrix, it was confirmed that LightGBM is most predictive (97%). In addition, as an unsupervised learning analysis method, MD, AE, and LSTM-AE models were constructed. Comparing three unsupervised learning analysis methods, the LSTM-AE model detected 75% of anomalies and showed the best performance. This study aims to contribute to the advancement of the smart factory by combining supervised and unsupervised learning techniques to accurately diagnose equipment failures and predict when abnormal situations occur, thereby laying the foundation for preemptive responses to abnormal situations. do.

• Journal of Appropriate Technology
• /
• v.6 no.2
• /
• pp.126-135
• /
• 2020

Recently, with the development of the 4th Industrial Revolution era and the popularization of technologies the maker movement is spreading worldwide in various ways for education, entrepreneurship, and solving social problems. This paper introduces a case of establishing and operating a maker space in Tanzania, East Africa, one of the developing countries. iTEC Tech-shop was established in the first half of 2018 at the Nelson Mandela African Institution of Science and Technology (NM-AIST) in Arusha, Tanzania by Innovative Technology and Energy Center (iTEC), and has been operating for nearly two years. With the allocation of empty warehouse space from NM-AIST, physical facilities were established through the purchase and installation of equipment and hand tools. Based on the advice from Idea Factory of Seoul National University and Fab-Lab Seoul, iTEC Tech-shop operational system were established. Through a total of 7 technical workshops, iTEC Tech-shop provided training courses for about 180 local personnel. In addition, the smart Techshop test-bed project was promoted in order to improve the operation level along with securing sustainability of the Techshop. The case of the iTEC Tech-shop could be a useful case for institutions or organizations promoting the maker movement to developing countries.

• Journal of Appropriate Technology
• /
• v.5 no.2
• /
• pp.70-81
• /
• 2019

The garment industry is one of the most labor-intensive manufacturing industries, with its sewing process relying almost entirely on manual labor. Its costs highly depend on the efficiency of this production line and thus is crucial to determine the production rate in real-time for line balancing. However, current production tracking methods are costly and make it difficult for many Small and Medium-sized Enterprises (SMEs) to implement them. As a result, their reliance on manual counting of finished products is both time consuming and prone to error, leading to high manufacturing costs and inefficiencies. In this paper, a production tracking system that uses the sewing machines' energy consumption data to track and count the total number of sewing tasks completed through Convolutional Neural Network (CNN) classifiers is proposed. This system was tested on two target sewing tasks, with a resulting maximum classification accuracy of 98.6%; all sewing tasks were detected. In the developing countries, the garment sewing industry is a very important industry, but the use of a lot of capital is very limited, such as applying expensive high technology to solve the above problem. Applied with the appropriate technology, this system is expected to be of great help to the garment industry in developing countries.

• Food Science and Industry
• /
• v.55 no.2
• /
• pp.188-202
• /
• 2022

In the insect industry, as the scope of application of insects is expanded from pet insects and natural enemies to feed, edible and medicinal insects, the demand for quality control of insect raw materials is increasing, and interest in securing the safety of insect products is increasing. In the process of expanding the industrial scale, controlling the temperature and humidity and air quality in the insect breeding room and preventing the spread of pathogens and other pollutants are important success factors. It requires a controlled environment under the operating system. European commercial insect breeding facilities have attracted considerable investor interest, and insect companies are building large-scale production facilities, which became possible after the EU approved the use of insect protein as feedstock for fish farming in July 2017. Other fields, such as food and medicine, have also accelerated the application of cutting-edge technology. In the future, the global insect industry will purchase eggs or small larvae from suppliers and a system that focuses on the larval fattening, i.e., production raw material, until the insects mature, and a system that handles the entire production process from egg laying, harvesting, and initial pre-treatment of larvae., increasingly subdivided into large-scale production systems that cover all stages of insect larvae production and further processing steps such as milling, fat removal and protein or fat fractionation. In Korea, research and development of insect smart factory farms using artificial intelligence and ICT is accelerating, so insects can be used as carbon-free materials in secondary industries such as natural plastics or natural molding materials as well as existing feed and food. A Korean-style customized breeding system for shortening the breeding period or enhancing functionality is expected to be developed soon.

• Korean Journal of Environmental Agriculture
• /
• v.36 no.3
• /
• pp.193-200
• /
• 2017

BACKGROUND: Plant growth under smart greenhouse (that is plant factory system) conditions of an artificial light type is significantly depending on the artificial light sources such as a fluorescent lamps or Light-Emitting Diodes (LEDs) with specific spectral wavelengths regardless of the outside environmental changes. In this experiment, characteristics on the growth and compound synthesis of kale seedlings affected by light qualities and intensities provided by LEDs were mentioned. METHODS AND RESULTS: The kale seedlings which developed 3~4 true leaves were exposed by fluorescent lamps or LEDs lights of red (R), blue+white (BW), blue+red (BR) with 50 (L) or $100(H){\mu}mol/m^2/s^1$ photosynthetic photon flux (PPF) under hydroponic culture system of deep flow technique for 50 days. Shoot fresh weight increased under the RH, BWH, and BRH treatments with higher PPF. Shoot elongation of the seedlings decreased, and polyphenol synthesis promoted by the higher light intensity conditions. Sugar synthesis in the leaves was above 2 times greater under the RH treatment of monochromic red light quality with $100{\mu}mol/m^2/s^1\;PPF$ than $50{\mu}mol/m^2/s^1\;PPF$. CONCLUSION: The results show that the control of light quality and intensity in the smart greenhouse conditions with artificial lights significantly affects the growth and compound synthesis in the fresh kale leaves with higher culture efficiency compared to the conventional soil culture under greenhouse or field conditions. Researches on the optimum light intensities of the LEDs with special spectral wavelengths are necessary for maximum growth and metabolism in the seedlings.

• Journal of Applied Biological Chemistry
• /
• v.64 no.3
• /
• pp.253-261
• /
• 2021

In this study, the ginseng sprout has produced through smart farm was classified according to its size and divided into above-ground (AG) and below-ground (BG) parts to compare ginsenoside contents and antioxidant activity. In the case of the AG part, the total phenolic contents were the highest at 5.16 mg/g in medium (M) size and the lowest at 2.23 mg/g in largest (L) size. The BG part also showed the highest content in the M size, but there was no significant difference. Also, the total flavonoid contents were also high in the M size in both the AG (5.16 mg/g) and BG (1.28 mg/g) parts. The major ginsenosides in the AG part were Re (20.33-24.15 mg/g) > Rd (11.36-27.42 mg/g) > Rg1 (4.48-5.54 mg/g) and the main ginsenosides in the BG part were Rb1 (5.09-8.61 mg/g) > Re (4.48-5.54 mg/g) > Rc (3.11-4.11 mg/g) in orders. In the case of M size, Re and Rd were approximately 4- and 19-folds higher at 24.15 mg/g and at 27.42 mg/g in the AG part and 5.20 mg/g and 1.43 mg in the BG part, respectively. In addition, F3 and Rh1 were detected in the AG part, but not in the BG part. 2,2-diphenyl-1-picrylhydrazyl (74.95%), 2,4,6-azino-bis (3-ethylbenzothiazoline-6-sulphnoic acid) diammonium salt (94.47%), and hydroxyl (70.39%) radical scavenging activities and FRAP (2.169) assay were the highest in M size than other sizes.

• Journal of Applied Biological Chemistry
• /
• v.65 no.3
• /
• pp.129-142
• /
• 2022

Ginseng sprouts, which can be eaten from leaves to roots, has the advantage of not having to use pesticides without being affected by the season by using smart farms. The optimal cultivation timing of sprout ginseng was checked and the nutritional content and antioxidant activity were compared and analyzed. The values of total fatty acids and total minerals were no significant changes during the growth periods. The contents of total amino acids were slightly decreased to 45 days and after increased to 65 days. When the growth period was 65 days, arginine had the highest content of 3309.11 mg/100 g. The total phenolic contents were high at 3.73 GAE mg/g on the 45 days, and the total flavonoid contents were also the highest at 9.04 RE mg/g on the 45 days. The contents of total ginsenoside was not noticeable for the growth periods (29.83 on 25 days→32.77 on 45 days→26.02 mg/g on 65 days). The ginsenoside Rg2 (0.62 mg/g), Re (8.69 mg/g), Rb1 (4.75 mg/g) and Rd (3.47 mg/g) had highest contents on 45 days during growth. The values of phenolic acids and flavonols were gradually increased to 45 days (338.6 and 1277.14 ㎍/g) and then decreased to 65 days. The major compounds of phenolic acids and flavonols were confirmed to benzoic acid (99.03-142.33 ㎍/g) and epigallocatechin (416.03-554.64 ㎍/g), respectively. The values of 2,2-diphenyl-1-picrylhydrazyl (44.27%), 2,4,6-azino-bis (3-ethylbenzothiazoline-6-sulphnoic acid) diammonium salt (75.16%), and hydroxyl (63.29%) radical scavenging activities and ferric reducing/antioxidant power (1.573) showed the highest activity on the 45 days as well as results of total phenolic and total flavonoid contents.

• Journal of Korean Society of Steel Construction
• /
• v.27 no.6
• /
• pp.503-511
• /
• 2015

In long span steel structure, the plate girder reinforced with stiffeners are commonly used. When choosing the cross section with deep depth of girder as well as narrow width, however, out of plane buckling can be a problem due to web slenderness. In an effort to solve this issue, current study determined the applicability of using corrugated web girder with deep depth as bending member, which is generally being utilized in both factory and warehouse nationwide. To accomplish this, we performed the loading test of H-shaped beam with sinusoidal corrugated web. Corrugated web CP-2.3 specimen exhibited 12% less maximal bending strength but CP-3.2 specimen exerted 24% increase in strength compared to plate web P-4.5. this result indicates that corrugated web provides enough strength even with unfavorable width-thickness ratio of plate. And bending as well as shear strength estimated by the Eurocode (EN 1993-1-5) were compared with both bending strength by loading test and shear strength estimated by KBC2009. In case of eurocode, increase in plate thickness did not help in bending performance improvement. moreover, shear performance was sensitive to the thickness of the web folds and the shape of the web plate.

• Korean Chemical Engineering Research
• /
• v.58 no.4
• /
• pp.565-572
• /
• 2020

This study developed a software platform using machine learning of artificial intelligence to optimize the distillation column system. The distillation column is representative and core process in the petrochemical industry. Process stabilization is difficult due to various operating conditions and continuous process characteristics, and differences in process efficiency occur depending on operator skill. The process control based on the theoretical simulation was used to overcome this problem, but it has a limitation which it can't apply to complex processes and real-time systems. This study aims to develop an empirical simulation model based on machine learning and to suggest an optimal process operation method. The development of empirical simulations involves collecting big data from the actual process, feature extraction through data mining, and representative algorithm for the chemical process. Finally, the platform for the distillation column was developed with verification through a developed model and field tests. Through the developed platform, it is possible to predict the operating parameters and provided optimal operating conditions to achieve efficient process control. This study is the basic study applying the artificial intelligence machine learning technique for the chemical process. After application on a wide variety of processes and it can be utilized to the cornerstone of the smart factory of the industry 4.0.