• Journal of information and communication convergence engineering
• /
• v.20 no.4
• /
• pp.295-302
• /
• 2022

This paper contains the development of a smart power device designed to collect load power data from industrial manufacturing machines, predict future variations in load power data, and detect abnormal data in advance by applying a machine learning-based prediction algorithm. The proposed load power data prediction model is implemented using a Long Short-Term Memory (LSTM) algorithm with high accuracy and relatively low complexity. The Flask and REST API are used to provide prediction results to users in a graphical interface. In addition, we present the results of experiments conducted to evaluate the performance of the proposed approach, which show that our model exhibited the highest accuracy compared with Multilayer Perceptron (MLP), Random Forest (RF), and Support Vector Machine (SVM) models. Moreover, we expect our method's accuracy could be improved by further optimizing the hyperparameter values and training the model for a longer period of time using a larger amount of data.

• Annual Conference of KIPS
• /
• 2023.11a
• /
• pp.124-125
• /
• 2023

Defect detection during liquid crystal display (LCD) manufacturing has always been a critical challenge. This study aims to address this issue by proposing a data augmentation method based on generative adversarial networks (GAN) to improve defect identification accuracy in LCD production. By leveraging synthetically generated image data from GAN, we effectively augment the original dataset to make it more representative and diverse. This data augmentation strategy enhances the model's generalization capability and robustness on real-world data. Compared to traditional data augmentation techniques, the synthetic data from GAN are more realistic, diverse and broadly distributed. Experimental results demonstrate that training models with GAN-generated data combined with the original dataset significantly improves the detection accuracy of critical defects in LCD manufacturing, compared to using the original dataset alone. This study provides an effective data augmentation approach for intelligent quality control in LCD production.

• Asian Journal of Business Environment
• /
• v.6 no.4
• /
• pp.27-34
• /
• 2016

Purpose - The study sought to examine the relationship between individual characteristics and system features and Human Resource Information System (HRIS) success in Japanese manufacturing companies in Malaysia. Research Design, Data, and Methodology - This study adopt quantitative approach to investigate the relationship between individual characteristics and system features and HRIS. Toward this objective, a total of 700 questionnaires were mailed to a representative of the organization. A total of 187 questionnaires were returned, and only 145 were usable for further analysis, representing a response rate of 20.71%. Result - Results indicated that individual characteristics and two dimensions of system characteristics (ease of use and training) were significantly related to HRIS success. Unexpectedly, the results showed that the third dimension of system features (documentation) was unrelated to HRIS success. Conclusions - The results partially support the underlying arguments that individual characteristics and system characteristics have significant influences on HRIS success. The finding suggests that HRIS success in the organization can be generated as a result of good implementation of system support and employees' readiness to apply HRIS in their jobs.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.18 no.11
• /
• pp.47-56
• /
• 2019

A deep neural network (DNN) model was proposed to predict the upset in the inertia friction welding process using a database comprising results from a series of FEM analyses. For the database, the upset length, upset beginning time, and upset completion time were extracted from the results of the FEM analyses obtained with various of axial pressure and initial rotational speed. A total of 35 training sets were constructed to train the proposed DNN with 4 hidden layers and 512 neurons in each layer, which can relate the input parameters to the welding results. The mean of the summation of squared error between the predicted results and the true results can be constrained to within 1.0e-4 after the training. Further, the network model was tested with another 10 sets of welding input parameters and results for comparison with FEM. The test showed that the relative error of DNN was within 2.8% for the prediction of upset. The results of DNN application revealed that the model could effectively provide welding results with respect to the exactness and cost for each combination of the welding input parameters.

• Journal of the Korean Crystal Growth and Crystal Technology
• /
• v.33 no.1
• /
• pp.22-30
• /
• 2023

Currently, almost all product development in the jewelry industry utilizes 3D CAD and 3D printing. In this situation, 3D CAD modeling and 3D printing ability units in colleges, Tomorrow Learning Card Education, and Course Evaluation-type jewelry design related education are conducted with developed curriculum based on the standards for training standards, training hours, training equipment, and practice materials presented by NCS. Accordingly, this study analyzes 3D CAD modeling and 3D printing training facilities, training hours, training equipment, etc into three categories of NCS precious metal processing and jewelry design, and studies the development of educational systems such as 3D CAD/3D printing curriculum and various environments that meet these standards. Education using this 3D CAD/3D printing education system will enable us to continuously supply professional talent with practical skills not only in the jewelry industry but also in the entire 3D CAD/3D printing manufacturing industry, which is called as one of the pillars of the 4th Industry. The quality of employment of trainees receiving education and the long-term retention rate after employed can also have a positive effect. In addition, excellent educational performance will help improve the recruitment rate of new students in jewelry jobs or manufacturing-related departments, which are difficult to recruit new students in recent years.

• Journal of the Ergonomics Society of Korea
• /
• v.36 no.3
• /
• pp.231-244
• /
• 2017

Objective: This study aims to understand the occupational injury characteristics of the workers in the motor vehicle parts (automobile parts) manufacturing industry and to present basic guidelines on accident prevention through accident analysis. Background: There occur many occupational injuries in the motor vehicle parts manufacturing industry. But there were few researches for the occupational injuries of the workers in the motor vehicle parts manufacturing industry. Method: This study analyzed the data of occupational injuries of 1,609 workers in the motor vehicle parts manufacturing industry in 2015. The accident characteristics were analyzed by dividing them into worker related factors and accident related factors. Results: Among the occupational injuries of the workers in the motor vehicle parts manufacturing industry, 80.6% of the victims were males, 64.0% were older than 40. 57.8% of the victims were employed by the companies with less than 50 workers. In addition, there was a difference in accident characteristics according to age, work experience, employment type, events or exposures, accident time of the day, agents, natures of injuries and illnesses, injured organs and injured body part. Conclusion: It is important to prevent equipment/machinery accidents. For this purpose, more efforts should be made to establish safety measures faithful to the basics of safety devices and safety work procedures. It is also suggested that prevention of disasters should be intensively carried out for workplaces with less than 50 employees and middle-aged and elderly people. Application: The result can be used to present guidelines for preventative measures for the workers in the motor vehicle parts manufacturing industry including safety education/training.

• Journal of the Korea Safety Management & Science
• /
• v.11 no.4
• /
• pp.43-55
• /
• 2009

In terms of deregulation requests from business, incidents at construction sites are rapidly increasing after reducing the regular safety training hours. Especially, to prevent incidents through safety trainings for construction site workers, who have lots of hazardous tasks than general manufacturing, is not only to protect property of both the companies and the country but also to increase their profits. That is why there are loud voices regarding that the safety training is a core mandatory to prevent industrial incidents. But, most companies, as soon as the deregulation for safety training is implemented, mitigated conducting safety trainings to prevent incidents. With this, the incidents are currently to be increased and caught in a vicious circle of many incidents at the smaller companies because of their absentmindedness regarding safety training due to their poorness as subcontractors of major companies, comparing to major companies. This study explains that the difference between managers and workers are existing about safety awareness and knowledge. And, we confirmed that the educational factor led by deficiency of safety awareness and knowledge was the major factor.

• The Journal of Korean Institute for Practical Engineering Education
• /
• v.4 no.2
• /
• pp.91-97
• /
• 2012

The automated visual inspection system (machine vision system) for quality assurance is an important factory automation equipment in the manufacturing industries, such as display, semiconductor, etc. The world market of the machine vision components is expected 18 billon dollars in 2015. Therefore, there is a lot of demand for the machine vision engineers. However, there are no technical training courses for machine vision technologies in vocational schools, colleges and universities. In this paper, we propose a technical training program for the machine vision technology. The total time of training is 30 to 60 hours and the training program can operate flexibly by student's major, a priori knowledge and education level.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.6
• /
• pp.309-314
• /
• 2024

The medical device industry is changing rapidly by applying the latest scientific and technological advancements. In particular, with the development of biotechnology, the proportion of in vitro diagnostic medical devices that diagnose diseases by analyzing body fluids such as blood and implant medical devices that can replace the role of human tissues and organs has recently increased rapidly In order to educate and supply manpower in the newly changing medical device industry, the development of a new practical training course is necessary. In this paper, we develop and report a hands-on training course using nitinol stents and a model stent introducer. The model stent introducer for this practical training can be easily made using raw materials used by the manufacturer, and the stents used in the training were provided by the stent manufacturing company. Through this practicum, students can experience part of the work of an actual medical device company and understand engineering theories applied to medical devices through practicum. In order for the Korean medical device industry to become a global leader, it is necessary to develop practical training courses through close cooperation between universities and industry.

• The Journal of Korean Institute for Practical Engineering Education
• /
• v.3 no.2
• /
• pp.136-141
• /
• 2011

The current tendency on development and change of equipment system in the factory are overlapped with the specific field of the existing systems such as PLC, DCS and SCADA, and the limited portion of the systems in the specific field stands in their own field. Specially, systematic integration, inspection control system and manufacturing management system, management information system are getting closely linked and therefore we increasingly need the open system. Meeting the needs, manufacturing automated equipments in the factory overcoming the shortcomings of unlinked unit equipment recently are getting changed to the phase closely linking with other systems. The training systems for the university, however, have not kept up with the needs from the industry, in spite that fused complex function and performance are asked in the field. To solve the problems, we suggest that the training courses and the equipment designed for the undergraduate education.