• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.18 no.9
• /
• pp.52-57
• /
• 2019

The key technology of the fourth industrial revolution is artificial intelligence and machine learning. In this study, FMEA was performed on fuel pumps used as key items in most systems to identify major failure components, and artificial neural networks were built using big data. The main failure mode of the fuel pump identified by the test was coil damage due to overheating. Based on the artificial neural network built, machine learning was conducted to predict the failure and the mean error rate was 4.9% when the number of hidden nodes in the artificial neural network was three and the temperature increased to $140^{\circ}C$ rapidly.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.20 no.9
• /
• pp.28-34
• /
• 2021

The Fourth Industrial Revolution has led to the development of drones for commercial and private applications. Therefore, the malfunction of drones has become a prominent problem. Failure mode and effect analysis was used in this study to analyze the primary cause of drone failure, and blade breakage was observed to have the highest frequency of failure. This was tested using a vibration sensor placed on drones along the breakage length of the blades. The data exhibited a significant increase in vibration within the drone body for blade fracture length. Principal component analysis was used to reduce the data dimension and classify the state with machine learning algorithms such as support vector machine, k-nearest neighbor, Gaussian naive Bayes, and random forest. The performance of machine learning was higher than 0.95 for the four algorithms in terms of accuracy, precision, recall, and f1-score. A follow-up study on failure prediction will be conducted based on the results of fault diagnosis.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.20 no.12
• /
• pp.85-91
• /
• 2021

In our daily life, artificial intelligence performs simple and complicated tasks like us, including operating mobile phones and working at homes and workplaces. Artificial intelligence is used in industrial technology for diagnosing various types of equipment using the machine learning technology. This study presents a fault mode effect analysis (FMEA) of start motors using machine learning and big data. Through multiple data collection, we observed that the primary failure of the start motor was caused by the melting of the magnetic switch inside the start motor causing it to fail. Long-short-term memory (LSTM) was used to diagnose the condition of the magnetic locations, and synthetic data were generated using the synthetic minority oversampling technique (SMOTE). This technique has the advantage of increasing the data accuracy. LSTM can also predict a start motor failure.

• Journal of Drive and Control
• /
• v.16 no.3
• /
• pp.33-41
• /
• 2019

This study presents the development of a lifetime test bench for the strain wave reducer which is a precision gear reducer of the robot to realize fault diagnosis and failure prognostics. To this end, the lifetime test bench was designed to detect the vertical forward/reverse direction rotation load. Through the lifetime test bench, it is possible to apply the same load spectrum from robot working scenarios. We developed a data integration gateway for fault data collection. Through the development of dedicated software for fault diagnosis and failure prognostics, these data from vibration, noise and temperature sensors were collected and analyzed along with the operation of the lifetime evaluation.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.19 no.11
• /
• pp.94-101
• /
• 2020

In the age of industry 4.0, artificial intelligence is being widely used to realize machinery condition monitoring. Due to their excellent performance and the ability to handle large volumes of data, machine learning techniques have been applied to realize the fault diagnosis of different equipment. In this study, we performed the failure mode effect analysis (FMEA) of an aluminum electrolytic capacitor by using deep learning and big data. Several tests were performed to identify the main failure mode of the aluminum electrolytic capacitor, and it was noted that the capacitance reduced significantly over time due to overheating. To reflect the capacitance degradation behavior over time, we employed the Vanilla long short-term memory (LSTM) neural network architecture. The LSTM neural network has been demonstrated to achieve excellent long-term predictions. The prediction results and metrics of the LSTM and Vanilla LSTM models were examined and compared. The Vanilla LSTM outperformed the conventional LSTM in terms of the computational resources and time required to predict the capacitance degradation.

• Journal of Sasang Constitutional Medicine
• /
• v.8 no.1
• /
• pp.57-74
• /
• 1996

Donguisusaebowon, Kogchigo are wrritten by Dong-Mu. Dokhaengpyun of the Kogchigo has philosophy of Dong-Mu about Gi-In. In order to understand constitutional medicine of Dong-Mu, it is necessary to study about Bi-Bak-Tam-Ra'Ja(four types of man) in Dokhaengpyun. The results are summarized as follows : 1. In Dokhaengpyu, it is defined that In-Eui-Ye-JI - the nature of human - as In-Ja, Eui-Ja, Ye-Ja, Ji-Ja. This attribute is composed of Chung-Sin-Ip-Yong. We can know that this concept, that is Chung-Sin-Yeum-Hae'Ja, is relative to the Bi-Bak-Tam-Ra'Ja. 2. We can think and infer the relation of Sabujisim of Myeng-Ja and Bi-Bak-Tam-Ra'Ja from Bi-Bak-Tam-Ra'Bu that is attribute of In-Eui-Ye-ji'Ja. Bi-Bak-Tam-Ra'Ja can approach the behavior of Chung-Sin-Yeum-Hae'Ja, if they heard the attitude of YouHaHye and BaelYi which they have attribute of In-Eui-Ye-Ji'Ja. 3. They explain Tthat Bi-Bak-Tam-Ra-Jisim is quoted from SaBuJiSim of Dahak. Thinking that Bi-Bak-Tam-Ra-Jisim of Dokaengpyun and SaBujiSim of YuRiak, we know that there is no rule. So, it is difficult that we can infer the Simyok and make some pattern. 4. The relationship of Bi-Bak-Tam-Ra'Ja and In-Eui-Ye-Ji are different from the relationship of Dokhaegpyun, Sadanron, In-Eui-Ye-Ji of YuRiak and Bi-Bak-Tam-Ra'Ja. If we regard the In-Eui-Ye-Ji Sadan as the nature of human, many attritude can be possible and it may be different that apply a Sadan to the proper time and environment. Therefore, we have to be accepted change, as applying method than fixing idea.

• Asian Journal of Turfgrass Science
• /
• v.24 no.2
• /
• pp.145-148
• /
• 2010

Nitrogen (N) is one of the most important nutrients among 17 essential nutrients for maintaining turfgrass color and quality. The slow release fertilizers were initially developed to provide a more consistent release of nitrogen over a longer period and are often used to decrease leaching potential from sandy soils. The goal of this study is to determine if various slow release N sources affect the rate at which turfgrass establishes. Six nitrogen sources were evaluated; Nitroform (38-0-0), Nutralene (40-0-0), Organiform (30-0-0), Sulfur coated urea (SCU, 37-0-0), urea (46-0- 0), and Milorganite (6-0-0). The root zone media was seeded and sodded with 'Limousine' Kentucky bluegrass (Poa pratensis L.). Sodded pots produced 182 to 518 g more clipping dry weight than seeded pots. Among seeded pots, Milorganite produced greater amount of root dry weight than any other N sources. Because the period of turfgrass growth is different between sodded and seeded plots, there were differences on clipping yield and root growth. Overall, high N rate had turf color greater than acceptable color of 6 among seeded pots throughout the study. However, low N rate didn't produce acceptable turf color throughout the study. Based on the result of this tudy, ilorganite would be ecommended for new establishment of Kentucky bluegrass an urea with less clipping yield which can lead to reduce abor.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.26 no.6
• /
• pp.706-714
• /
• 2020

Currently, 90 % of the world's population breathes air with a fine dust content exceeding the World Health Organization's annual average exposure limit (10 ㎍/㎥). Global efforts have been devoted toward reducing secondary pollutants and ultra-fine dust through regulations on nitrogen oxides released over land and sea. Domestic efforts have also aimed at creating clean marine environments by reducing sulfur emissions, which are the primary cause of dust accumulation in ships, through developing and distributing environment-friendly ships. Among the technologies for reducing harmful emissions from diesel engines, electrostatic precipitator offer several advantages such as a low pressure loss, high dust collection efficiency, and NOx removal and maintenance. This study aims to increase the durability of a ship by improving equipment quality through failure mode effects analysis for the preventive maintenance of an electrostatic precipitator that was developed for reducing fine dust particles emitted from the 2,427 kW marine diesel engines in ships with a gross tonnage of 999 tons. With regard to risk priority, failure mode 241 (poor dust capture efficiency) was the highest, with an RPN of 180. It was necessary to determine the high-risk failure mode in the collecting electrode and manage it intensively. This was caused by clearance defects, owing to vibrations and consequent pin loosening. Given that pin loosening is mainly caused by vibrations generated in the hull or equipment, it is necessary to manage the position of pin loosening.

• Weed & Turfgrass Science
• /
• v.7 no.1
• /
• pp.62-71
• /
• 2018

This study was conducted to evaluate the effect of liquid fertilizer containing humate (LFH) on changes of turfgrass quality and growth by investigating visual quality, chlorophyll content, dry weight of clipping, and nutrient content in leaves tissue. Treatments were designed as follows; control fertilizer (CF), HF-1 ($CF+1.0mL\;m^{-2}\;LFH$), HF-2 ($CF+2.0mL\;m^{-2}\;LFH$), and HF-3 ($CF+4.0mL\;m^{-2}\;LFH$). As compared with CF, soil chemical properties of LFH treatments were not significantly. Visual quality and root dry weight of LFH treatments were higher than that of CF. Chlorophyll content, clipping yield and nitrogen uptake of HF-2 and HF-3 were increased 11.2-11.8%, 15.3-30.0%, 22-42% by application of LFH. The LFH level was positively correlated with visual quality, chlorophyll content, clipping yield or nutrient uptake amount. These results indicated that the application of LFH improved the growth and quality of creeping bentgrass by increasing nutrient uptake and by prompting root growth.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.44 no.1
• /
• pp.33-39
• /
• 2007

LonWorks over IP (LonWorks/IP) virtual device network (VDN) is an integrated form of LonWorks device network and IP data network. LonWorks/IP VDN can offer ubiquitous access to the information on the factory floor and make it possible for the predictive and preventive maintenance on the factory floor. Timely response is inevitable for predictive and preventive maintenance on the factory floor under the real-time distributed control. The network induced uncertain time delay deteriorates the performance and stability of the real-time distributed control system on LonWorks/IP virtual device network. Therefore, in order to guarantee the stability and to improve the performance of the networked distributed control system the time-varying uncertain time delay needs to be compensated for. In this paper, under the real-time distributed control on LonWorks/IP VDN with uncertain time delay, a control scheme based on disturbance observer and ZPETC(Zero Phase Error Tracking Controller) phase lag compensator is proposed and tested through computer simulation. The result of the proposed control is compared with that of internal model controller (IMC) based on Smith predictor and disturbance observer. It is shown that the proposed control scheme is disturbance and noise tolerant and can significantly improve the stability and the tracking performance of the periodic reference. Therefore, the proposed control scheme is well suited for the distributed servo control for predictive maintenance on LonWorks/IP-based virtual device network with time-varying delay.